diff --git a/CTCF_TF/config.json b/CTCF_TF/config.json new file mode 100644 index 0000000000000000000000000000000000000000..9d321b56dac4fc440968591bca13ad558673ae67 --- /dev/null +++ b/CTCF_TF/config.json @@ -0,0 +1,66 @@ +{ + "_name_or_path": "/nvme0/wb_ssd0/FishCaduceus/pretrained_model/FishCaduceus_train_l28_512/checkpoint-40000", + "architectures": [ + "CaduceusForSequenceClassification" + ], + "auto_map": { + "AutoConfig": "configuration_caduceus.CaduceusConfig", + "AutoModel": "modeling_caduceus.Caduceus", + "AutoModelForMaskedLM": "modeling_caduceus.CaduceusForMaskedLM", + "AutoModelForSequenceClassification": "modeling_caduceus.CaduceusForSequenceClassification" + }, + "bidirectional": true, + "bidirectional_strategy": "add", + "bidirectional_weight_tie": true, + "complement_map": { + "0": 0, + "1": 1, + "2": 2, + "3": 6, + "4": 5, + "5": 4, + "6": 3, + "7": 7 + }, + "d_model": 768, + "fused_add_norm": true, + "id2label": { + "0": "Not", + "1": "Yes" + }, + "initializer_cfg": { + "initializer_range": 0.02, + "n_residuals_per_layer": 1, + "rescale_prenorm_residual": true + }, + "label2id": { + "Not": 0, + "Yes": 1 + }, + "model_type": "caduceus", + "n_layer": 28, + "norm_epsilon": 1e-05, + "pad_token_id": 0, + "pad_vocab_size_multiple": 8, + "problem_type": "single_label_classification", + "rcps": true, + "residual_in_fp32": true, + "rms_norm": true, + "ssm_cfg": { + "bias": false, + "conv_bias": true, + "d_conv": 4, + "d_state": 16, + "dt_init": "random", + "dt_init_floor": 0.0001, + "dt_max": 0.1, + "dt_min": 0.001, + "dt_rank": "auto", + "dt_scale": 1.0, + "expand": 2, + "use_fast_path": true + }, + "torch_dtype": "float32", + "transformers_version": "4.30.2", + "vocab_size": 8 +} diff --git a/CTCF_TF/pytorch_model.bin b/CTCF_TF/pytorch_model.bin new file mode 100644 index 0000000000000000000000000000000000000000..cef84c79e6f83eb8d2b19a9c1b69047807d3728c --- /dev/null +++ b/CTCF_TF/pytorch_model.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3e8dda5cf6acab5031c20201af194fe45734c61b186b098dbafa50c33eb76fa8 +size 448617482 diff --git a/CTCF_TF/special_tokens_map.json b/CTCF_TF/special_tokens_map.json new file mode 100644 index 0000000000000000000000000000000000000000..962961477153a31b5606b5dc1cd6c37a2a290f5a --- /dev/null +++ b/CTCF_TF/special_tokens_map.json @@ -0,0 +1,23 @@ +{ + "mask_token": { + "content": "[MASK]", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false + }, + "pad_token": { + "content": "[PAD]", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false + }, + "unk_token": { + "content": "[UNK]", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false + } +} diff --git a/CTCF_TF/tokenizer.json b/CTCF_TF/tokenizer.json new file mode 100644 index 0000000000000000000000000000000000000000..f4d365b915d8322e842b2df8c23cca5a8e62920d --- /dev/null +++ b/CTCF_TF/tokenizer.json @@ -0,0 +1,75 @@ +{ + "version": "1.0", + "truncation": { + "direction": "Right", + "max_length": 800, + "strategy": "LongestFirst", + "stride": 0 + }, + "padding": { + "strategy": { + "Fixed": 800 + }, + "direction": "Right", + "pad_to_multiple_of": null, + "pad_id": 0, + "pad_type_id": 0, + "pad_token": "[PAD]" + }, + "added_tokens": [ + { + "id": 0, + "content": "[PAD]", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false, + "special": true + }, + { + "id": 1, + "content": "[MASK]", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false, + "special": true + }, + { + "id": 2, + "content": "[UNK]", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false, + "special": true + } + ], + "normalizer": { + "type": "Lowercase" + }, + "pre_tokenizer": { + "type": "Whitespace" + }, + "post_processor": null, + "decoder": null, + "model": { + "type": "BPE", + "dropout": null, + "unk_token": "[UNK]", + "continuing_subword_prefix": null, + "end_of_word_suffix": null, + "fuse_unk": false, + "byte_fallback": false, + "vocab": { + "[PAD]": 0, + "[MASK]": 1, + "[UNK]": 2, + "a": 3, + "c": 4, + "g": 5, + "t": 6 + }, + "merges": [] + } +} \ No newline at end of file diff --git a/CTCF_TF/tokenizer_config.json b/CTCF_TF/tokenizer_config.json new file mode 100644 index 0000000000000000000000000000000000000000..ffdec809295764641445d01323aaee8e553854be --- /dev/null +++ b/CTCF_TF/tokenizer_config.json @@ -0,0 +1,34 @@ +{ + "added_tokens_decoder": { + "0": { + "content": "[PAD]", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "1": { + "content": "[MASK]", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "2": { + "content": "[UNK]", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + } + }, + "clean_up_tokenization_spaces": true, + "mask_token": "[MASK]", + "model_max_length": 800, + "pad_token": "[PAD]", + "tokenizer_class": "PreTrainedTokenizerFast", + "unk_token": "[UNK]" +} diff --git a/H3K27me3/config.json b/H3K27me3/config.json new file mode 100644 index 0000000000000000000000000000000000000000..9d321b56dac4fc440968591bca13ad558673ae67 --- /dev/null +++ b/H3K27me3/config.json @@ -0,0 +1,66 @@ +{ + "_name_or_path": "/nvme0/wb_ssd0/FishCaduceus/pretrained_model/FishCaduceus_train_l28_512/checkpoint-40000", + "architectures": [ + "CaduceusForSequenceClassification" + ], + "auto_map": { + "AutoConfig": "configuration_caduceus.CaduceusConfig", + "AutoModel": "modeling_caduceus.Caduceus", + "AutoModelForMaskedLM": "modeling_caduceus.CaduceusForMaskedLM", + "AutoModelForSequenceClassification": "modeling_caduceus.CaduceusForSequenceClassification" + }, + "bidirectional": true, + "bidirectional_strategy": "add", + "bidirectional_weight_tie": true, + "complement_map": { + "0": 0, + "1": 1, + "2": 2, + "3": 6, + "4": 5, + "5": 4, + "6": 3, + "7": 7 + }, + "d_model": 768, + "fused_add_norm": true, + "id2label": { + "0": "Not", + "1": "Yes" + }, + "initializer_cfg": { + "initializer_range": 0.02, + "n_residuals_per_layer": 1, + "rescale_prenorm_residual": true + }, + "label2id": { + "Not": 0, + "Yes": 1 + }, + "model_type": "caduceus", + "n_layer": 28, + "norm_epsilon": 1e-05, + "pad_token_id": 0, + "pad_vocab_size_multiple": 8, + "problem_type": "single_label_classification", + "rcps": true, + "residual_in_fp32": true, + "rms_norm": true, + "ssm_cfg": { + "bias": false, + "conv_bias": true, + "d_conv": 4, + "d_state": 16, + "dt_init": "random", + "dt_init_floor": 0.0001, + "dt_max": 0.1, + "dt_min": 0.001, + "dt_rank": "auto", + "dt_scale": 1.0, + "expand": 2, + "use_fast_path": true + }, + "torch_dtype": "float32", + "transformers_version": "4.30.2", + "vocab_size": 8 +} diff --git a/H3K27me3/pytorch_model.bin b/H3K27me3/pytorch_model.bin new file mode 100644 index 0000000000000000000000000000000000000000..8213ed3ef7ec0aec7dbb5085d929cb6d0a91be00 --- /dev/null +++ b/H3K27me3/pytorch_model.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a3913e3e4a2b32bc59630148dacf338975e90d26a390b78eaa19cbf38f1f26ee +size 448617482 diff --git a/H3K27me3/special_tokens_map.json b/H3K27me3/special_tokens_map.json new file mode 100644 index 0000000000000000000000000000000000000000..962961477153a31b5606b5dc1cd6c37a2a290f5a --- /dev/null +++ b/H3K27me3/special_tokens_map.json @@ -0,0 +1,23 @@ +{ + "mask_token": { + "content": "[MASK]", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false + }, + "pad_token": { + "content": "[PAD]", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false + }, + "unk_token": { + "content": "[UNK]", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false + } +} diff --git a/H3K27me3/tokenizer.json b/H3K27me3/tokenizer.json new file mode 100644 index 0000000000000000000000000000000000000000..24906c9d648f5357eb9554825797660310af37a8 --- /dev/null +++ b/H3K27me3/tokenizer.json @@ -0,0 +1,75 @@ +{ + "version": "1.0", + "truncation": { + "direction": "Right", + "max_length": 2500, + "strategy": "LongestFirst", + "stride": 0 + }, + "padding": { + "strategy": { + "Fixed": 2500 + }, + "direction": "Right", + "pad_to_multiple_of": null, + "pad_id": 0, + "pad_type_id": 0, + "pad_token": "[PAD]" + }, + "added_tokens": [ + { + "id": 0, + "content": "[PAD]", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false, + "special": true + }, + { + "id": 1, + "content": "[MASK]", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false, + "special": true + }, + { + "id": 2, + "content": "[UNK]", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false, + "special": true + } + ], + "normalizer": { + "type": "Lowercase" + }, + "pre_tokenizer": { + "type": "Whitespace" + }, + "post_processor": null, + "decoder": null, + "model": { + "type": "BPE", + "dropout": null, + "unk_token": "[UNK]", + "continuing_subword_prefix": null, + "end_of_word_suffix": null, + "fuse_unk": false, + "byte_fallback": false, + "vocab": { + "[PAD]": 0, + "[MASK]": 1, + "[UNK]": 2, + "a": 3, + "c": 4, + "g": 5, + "t": 6 + }, + "merges": [] + } +} \ No newline at end of file diff --git a/H3K27me3/tokenizer_config.json b/H3K27me3/tokenizer_config.json new file mode 100644 index 0000000000000000000000000000000000000000..9a52165c8c2f352aff39336d757e320f13ba1c17 --- /dev/null +++ b/H3K27me3/tokenizer_config.json @@ -0,0 +1,34 @@ +{ + "added_tokens_decoder": { + "0": { + "content": "[PAD]", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "1": { + "content": "[MASK]", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "2": { + "content": "[UNK]", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + } + }, + "clean_up_tokenization_spaces": true, + "mask_token": "[MASK]", + "model_max_length": 2500, + "pad_token": "[PAD]", + "tokenizer_class": "PreTrainedTokenizerFast", + "unk_token": "[UNK]" +} diff --git a/H3K4me1/config.json b/H3K4me1/config.json new file mode 100644 index 0000000000000000000000000000000000000000..9d321b56dac4fc440968591bca13ad558673ae67 --- /dev/null +++ b/H3K4me1/config.json @@ -0,0 +1,66 @@ +{ + "_name_or_path": "/nvme0/wb_ssd0/FishCaduceus/pretrained_model/FishCaduceus_train_l28_512/checkpoint-40000", + "architectures": [ + "CaduceusForSequenceClassification" + ], + "auto_map": { + "AutoConfig": "configuration_caduceus.CaduceusConfig", + "AutoModel": "modeling_caduceus.Caduceus", + "AutoModelForMaskedLM": "modeling_caduceus.CaduceusForMaskedLM", + "AutoModelForSequenceClassification": "modeling_caduceus.CaduceusForSequenceClassification" + }, + "bidirectional": true, + "bidirectional_strategy": "add", + "bidirectional_weight_tie": true, + "complement_map": { + "0": 0, + "1": 1, + "2": 2, + "3": 6, + "4": 5, + "5": 4, + "6": 3, + "7": 7 + }, + "d_model": 768, + "fused_add_norm": true, + "id2label": { + "0": "Not", + "1": "Yes" + }, + "initializer_cfg": { + "initializer_range": 0.02, + "n_residuals_per_layer": 1, + "rescale_prenorm_residual": true + }, + "label2id": { + "Not": 0, + "Yes": 1 + }, + "model_type": "caduceus", + "n_layer": 28, + "norm_epsilon": 1e-05, + "pad_token_id": 0, + "pad_vocab_size_multiple": 8, + "problem_type": "single_label_classification", + "rcps": true, + "residual_in_fp32": true, + "rms_norm": true, + "ssm_cfg": { + "bias": false, + "conv_bias": true, + "d_conv": 4, + "d_state": 16, + "dt_init": "random", + "dt_init_floor": 0.0001, + "dt_max": 0.1, + "dt_min": 0.001, + "dt_rank": "auto", + "dt_scale": 1.0, + "expand": 2, + "use_fast_path": true + }, + "torch_dtype": "float32", + "transformers_version": "4.30.2", + "vocab_size": 8 +} diff --git a/H3K4me1/pytorch_model.bin b/H3K4me1/pytorch_model.bin new file mode 100644 index 0000000000000000000000000000000000000000..74cd1033d844bb4cae6250d9b11942d2d635a719 --- /dev/null +++ b/H3K4me1/pytorch_model.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3ee35d6f7adca370081f96c4d74a5f2e8ac68ce58b187c5c9c3962803a3f3f0f +size 448617482 diff --git a/H3K4me1/special_tokens_map.json b/H3K4me1/special_tokens_map.json new file mode 100644 index 0000000000000000000000000000000000000000..962961477153a31b5606b5dc1cd6c37a2a290f5a --- /dev/null +++ b/H3K4me1/special_tokens_map.json @@ -0,0 +1,23 @@ +{ + "mask_token": { + "content": "[MASK]", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false + }, + "pad_token": { + "content": "[PAD]", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false + }, + "unk_token": { + "content": "[UNK]", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false + } +} diff --git a/H3K4me1/tokenizer.json b/H3K4me1/tokenizer.json new file mode 100644 index 0000000000000000000000000000000000000000..24906c9d648f5357eb9554825797660310af37a8 --- /dev/null +++ b/H3K4me1/tokenizer.json @@ -0,0 +1,75 @@ +{ + "version": "1.0", + "truncation": { + "direction": "Right", + "max_length": 2500, + "strategy": "LongestFirst", + "stride": 0 + }, + "padding": { + "strategy": { + "Fixed": 2500 + }, + "direction": "Right", + "pad_to_multiple_of": null, + "pad_id": 0, + "pad_type_id": 0, + "pad_token": "[PAD]" + }, + "added_tokens": [ + { + "id": 0, + "content": "[PAD]", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false, + "special": true + }, + { + "id": 1, + "content": "[MASK]", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false, + "special": true + }, + { + "id": 2, + "content": "[UNK]", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false, + "special": true + } + ], + "normalizer": { + "type": "Lowercase" + }, + "pre_tokenizer": { + "type": "Whitespace" + }, + "post_processor": null, + "decoder": null, + "model": { + "type": "BPE", + "dropout": null, + "unk_token": "[UNK]", + "continuing_subword_prefix": null, + "end_of_word_suffix": null, + "fuse_unk": false, + "byte_fallback": false, + "vocab": { + "[PAD]": 0, + "[MASK]": 1, + "[UNK]": 2, + "a": 3, + "c": 4, + "g": 5, + "t": 6 + }, + "merges": [] + } +} \ No newline at end of file diff --git a/H3K4me1/tokenizer_config.json b/H3K4me1/tokenizer_config.json new file mode 100644 index 0000000000000000000000000000000000000000..9a52165c8c2f352aff39336d757e320f13ba1c17 --- /dev/null +++ b/H3K4me1/tokenizer_config.json @@ -0,0 +1,34 @@ +{ + "added_tokens_decoder": { + "0": { + "content": "[PAD]", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "1": { + "content": "[MASK]", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "2": { + "content": "[UNK]", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + } + }, + "clean_up_tokenization_spaces": true, + "mask_token": "[MASK]", + "model_max_length": 2500, + "pad_token": "[PAD]", + "tokenizer_class": "PreTrainedTokenizerFast", + "unk_token": "[UNK]" +} diff --git a/H3K4me3/config.json b/H3K4me3/config.json new file mode 100644 index 0000000000000000000000000000000000000000..9d321b56dac4fc440968591bca13ad558673ae67 --- /dev/null +++ b/H3K4me3/config.json @@ -0,0 +1,66 @@ +{ + "_name_or_path": "/nvme0/wb_ssd0/FishCaduceus/pretrained_model/FishCaduceus_train_l28_512/checkpoint-40000", + "architectures": [ + "CaduceusForSequenceClassification" + ], + "auto_map": { + "AutoConfig": "configuration_caduceus.CaduceusConfig", + "AutoModel": "modeling_caduceus.Caduceus", + "AutoModelForMaskedLM": "modeling_caduceus.CaduceusForMaskedLM", + "AutoModelForSequenceClassification": "modeling_caduceus.CaduceusForSequenceClassification" + }, + "bidirectional": true, + "bidirectional_strategy": "add", + "bidirectional_weight_tie": true, + "complement_map": { + "0": 0, + "1": 1, + "2": 2, + "3": 6, + "4": 5, + "5": 4, + "6": 3, + "7": 7 + }, + "d_model": 768, + "fused_add_norm": true, + "id2label": { + "0": "Not", + "1": "Yes" + }, + "initializer_cfg": { + "initializer_range": 0.02, + "n_residuals_per_layer": 1, + "rescale_prenorm_residual": true + }, + "label2id": { + "Not": 0, + "Yes": 1 + }, + "model_type": "caduceus", + "n_layer": 28, + "norm_epsilon": 1e-05, + "pad_token_id": 0, + "pad_vocab_size_multiple": 8, + "problem_type": "single_label_classification", + "rcps": true, + "residual_in_fp32": true, + "rms_norm": true, + "ssm_cfg": { + "bias": false, + "conv_bias": true, + "d_conv": 4, + "d_state": 16, + "dt_init": "random", + "dt_init_floor": 0.0001, + "dt_max": 0.1, + "dt_min": 0.001, + "dt_rank": "auto", + "dt_scale": 1.0, + "expand": 2, + "use_fast_path": true + }, + "torch_dtype": "float32", + "transformers_version": "4.30.2", + "vocab_size": 8 +} diff --git a/H3K4me3/pytorch_model.bin b/H3K4me3/pytorch_model.bin new file mode 100644 index 0000000000000000000000000000000000000000..80003cb8053031f627a6e553aba3f836bcec02e9 --- /dev/null +++ b/H3K4me3/pytorch_model.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e4071e9692a2cd55fe394130810326106cfa160a346d3d9d968ccb3c65877c72 +size 448617482 diff --git a/H3K4me3/special_tokens_map.json b/H3K4me3/special_tokens_map.json new file mode 100644 index 0000000000000000000000000000000000000000..962961477153a31b5606b5dc1cd6c37a2a290f5a --- /dev/null +++ b/H3K4me3/special_tokens_map.json @@ -0,0 +1,23 @@ +{ + "mask_token": { + "content": "[MASK]", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false + }, + "pad_token": { + "content": "[PAD]", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false + }, + "unk_token": { + "content": "[UNK]", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false + } +} diff --git a/H3K4me3/tokenizer.json b/H3K4me3/tokenizer.json new file mode 100644 index 0000000000000000000000000000000000000000..24906c9d648f5357eb9554825797660310af37a8 --- /dev/null +++ b/H3K4me3/tokenizer.json @@ -0,0 +1,75 @@ +{ + "version": "1.0", + "truncation": { + "direction": "Right", + "max_length": 2500, + "strategy": "LongestFirst", + "stride": 0 + }, + "padding": { + "strategy": { + "Fixed": 2500 + }, + "direction": "Right", + "pad_to_multiple_of": null, + "pad_id": 0, + "pad_type_id": 0, + "pad_token": "[PAD]" + }, + "added_tokens": [ + { + "id": 0, + "content": "[PAD]", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false, + "special": true + }, + { + "id": 1, + "content": "[MASK]", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false, + "special": true + }, + { + "id": 2, + "content": "[UNK]", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false, + "special": true + } + ], + "normalizer": { + "type": "Lowercase" + }, + "pre_tokenizer": { + "type": "Whitespace" + }, + "post_processor": null, + "decoder": null, + "model": { + "type": "BPE", + "dropout": null, + "unk_token": "[UNK]", + "continuing_subword_prefix": null, + "end_of_word_suffix": null, + "fuse_unk": false, + "byte_fallback": false, + "vocab": { + "[PAD]": 0, + "[MASK]": 1, + "[UNK]": 2, + "a": 3, + "c": 4, + "g": 5, + "t": 6 + }, + "merges": [] + } +} \ No newline at end of file diff --git a/H3K4me3/tokenizer_config.json b/H3K4me3/tokenizer_config.json new file mode 100644 index 0000000000000000000000000000000000000000..9a52165c8c2f352aff39336d757e320f13ba1c17 --- /dev/null +++ b/H3K4me3/tokenizer_config.json @@ -0,0 +1,34 @@ +{ + "added_tokens_decoder": { + "0": { + "content": "[PAD]", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "1": { + "content": "[MASK]", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "2": { + "content": "[UNK]", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + } + }, + "clean_up_tokenization_spaces": true, + "mask_token": "[MASK]", + "model_max_length": 2500, + "pad_token": "[PAD]", + "tokenizer_class": "PreTrainedTokenizerFast", + "unk_token": "[UNK]" +} diff --git a/H3K9me3/config.json b/H3K9me3/config.json new file mode 100644 index 0000000000000000000000000000000000000000..9d321b56dac4fc440968591bca13ad558673ae67 --- /dev/null +++ b/H3K9me3/config.json @@ -0,0 +1,66 @@ +{ + "_name_or_path": "/nvme0/wb_ssd0/FishCaduceus/pretrained_model/FishCaduceus_train_l28_512/checkpoint-40000", + "architectures": [ + "CaduceusForSequenceClassification" + ], + "auto_map": { + "AutoConfig": "configuration_caduceus.CaduceusConfig", + "AutoModel": "modeling_caduceus.Caduceus", + "AutoModelForMaskedLM": "modeling_caduceus.CaduceusForMaskedLM", + "AutoModelForSequenceClassification": "modeling_caduceus.CaduceusForSequenceClassification" + }, + "bidirectional": true, + "bidirectional_strategy": "add", + "bidirectional_weight_tie": true, + "complement_map": { + "0": 0, + "1": 1, + "2": 2, + "3": 6, + "4": 5, + "5": 4, + "6": 3, + "7": 7 + }, + "d_model": 768, + "fused_add_norm": true, + "id2label": { + "0": "Not", + "1": "Yes" + }, + "initializer_cfg": { + "initializer_range": 0.02, + "n_residuals_per_layer": 1, + "rescale_prenorm_residual": true + }, + "label2id": { + "Not": 0, + "Yes": 1 + }, + "model_type": "caduceus", + "n_layer": 28, + "norm_epsilon": 1e-05, + "pad_token_id": 0, + "pad_vocab_size_multiple": 8, + "problem_type": "single_label_classification", + "rcps": true, + "residual_in_fp32": true, + "rms_norm": true, + "ssm_cfg": { + "bias": false, + "conv_bias": true, + "d_conv": 4, + "d_state": 16, + "dt_init": "random", + "dt_init_floor": 0.0001, + "dt_max": 0.1, + "dt_min": 0.001, + "dt_rank": "auto", + "dt_scale": 1.0, + "expand": 2, + "use_fast_path": true + }, + "torch_dtype": "float32", + "transformers_version": "4.30.2", + "vocab_size": 8 +} diff --git a/H3K9me3/pytorch_model.bin b/H3K9me3/pytorch_model.bin new file mode 100644 index 0000000000000000000000000000000000000000..90ceef80a15cf2739ff31e1761ea13f0831f333c --- /dev/null +++ b/H3K9me3/pytorch_model.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b69c48115f5192a694e042cd849bfc9133f891457f308ddb603fe6e96b90680f +size 448617482 diff --git a/H3K9me3/special_tokens_map.json b/H3K9me3/special_tokens_map.json new file mode 100644 index 0000000000000000000000000000000000000000..962961477153a31b5606b5dc1cd6c37a2a290f5a --- /dev/null +++ b/H3K9me3/special_tokens_map.json @@ -0,0 +1,23 @@ +{ + "mask_token": { + "content": "[MASK]", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false + }, + "pad_token": { + "content": "[PAD]", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false + }, + "unk_token": { + "content": "[UNK]", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false + } +} diff --git a/H3K9me3/tokenizer.json b/H3K9me3/tokenizer.json new file mode 100644 index 0000000000000000000000000000000000000000..24906c9d648f5357eb9554825797660310af37a8 --- /dev/null +++ b/H3K9me3/tokenizer.json @@ -0,0 +1,75 @@ +{ + "version": "1.0", + "truncation": { + "direction": "Right", + "max_length": 2500, + "strategy": "LongestFirst", + "stride": 0 + }, + "padding": { + "strategy": { + "Fixed": 2500 + }, + "direction": "Right", + "pad_to_multiple_of": null, + "pad_id": 0, + "pad_type_id": 0, + "pad_token": "[PAD]" + }, + "added_tokens": [ + { + "id": 0, + "content": "[PAD]", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false, + "special": true + }, + { + "id": 1, + "content": "[MASK]", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false, + "special": true + }, + { + "id": 2, + "content": "[UNK]", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false, + "special": true + } + ], + "normalizer": { + "type": "Lowercase" + }, + "pre_tokenizer": { + "type": "Whitespace" + }, + "post_processor": null, + "decoder": null, + "model": { + "type": "BPE", + "dropout": null, + "unk_token": "[UNK]", + "continuing_subword_prefix": null, + "end_of_word_suffix": null, + "fuse_unk": false, + "byte_fallback": false, + "vocab": { + "[PAD]": 0, + "[MASK]": 1, + "[UNK]": 2, + "a": 3, + "c": 4, + "g": 5, + "t": 6 + }, + "merges": [] + } +} \ No newline at end of file diff --git a/H3K9me3/tokenizer_config.json b/H3K9me3/tokenizer_config.json new file mode 100644 index 0000000000000000000000000000000000000000..9a52165c8c2f352aff39336d757e320f13ba1c17 --- /dev/null +++ b/H3K9me3/tokenizer_config.json @@ -0,0 +1,34 @@ +{ + "added_tokens_decoder": { + "0": { + "content": "[PAD]", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "1": { + "content": "[MASK]", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "2": { + "content": "[UNK]", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + } + }, + "clean_up_tokenization_spaces": true, + "mask_token": "[MASK]", + "model_max_length": 2500, + "pad_token": "[PAD]", + "tokenizer_class": "PreTrainedTokenizerFast", + "unk_token": "[UNK]" +} diff --git a/H3k27ac/config.json b/H3k27ac/config.json new file mode 100644 index 0000000000000000000000000000000000000000..9d321b56dac4fc440968591bca13ad558673ae67 --- /dev/null +++ b/H3k27ac/config.json @@ -0,0 +1,66 @@ +{ + "_name_or_path": "/nvme0/wb_ssd0/FishCaduceus/pretrained_model/FishCaduceus_train_l28_512/checkpoint-40000", + "architectures": [ + "CaduceusForSequenceClassification" + ], + "auto_map": { + "AutoConfig": "configuration_caduceus.CaduceusConfig", + "AutoModel": "modeling_caduceus.Caduceus", + "AutoModelForMaskedLM": "modeling_caduceus.CaduceusForMaskedLM", + "AutoModelForSequenceClassification": "modeling_caduceus.CaduceusForSequenceClassification" + }, + "bidirectional": true, + "bidirectional_strategy": "add", + "bidirectional_weight_tie": true, + "complement_map": { + "0": 0, + "1": 1, + "2": 2, + "3": 6, + "4": 5, + "5": 4, + "6": 3, + "7": 7 + }, + "d_model": 768, + "fused_add_norm": true, + "id2label": { + "0": "Not", + "1": "Yes" + }, + "initializer_cfg": { + "initializer_range": 0.02, + "n_residuals_per_layer": 1, + "rescale_prenorm_residual": true + }, + "label2id": { + "Not": 0, + "Yes": 1 + }, + "model_type": "caduceus", + "n_layer": 28, + "norm_epsilon": 1e-05, + "pad_token_id": 0, + "pad_vocab_size_multiple": 8, + "problem_type": "single_label_classification", + "rcps": true, + "residual_in_fp32": true, + "rms_norm": true, + "ssm_cfg": { + "bias": false, + "conv_bias": true, + "d_conv": 4, + "d_state": 16, + "dt_init": "random", + "dt_init_floor": 0.0001, + "dt_max": 0.1, + "dt_min": 0.001, + "dt_rank": "auto", + "dt_scale": 1.0, + "expand": 2, + "use_fast_path": true + }, + "torch_dtype": "float32", + "transformers_version": "4.30.2", + "vocab_size": 8 +} diff --git a/H3k27ac/pytorch_model.bin b/H3k27ac/pytorch_model.bin new file mode 100644 index 0000000000000000000000000000000000000000..b800362a66472b36416b2dc46876fa5b62cb604f --- /dev/null +++ b/H3k27ac/pytorch_model.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d9b8373e811ee0c6ca80f5178606cba651639c9984c417d6b58cddf40e104d53 +size 448617482 diff --git a/H3k27ac/special_tokens_map.json b/H3k27ac/special_tokens_map.json new file mode 100644 index 0000000000000000000000000000000000000000..962961477153a31b5606b5dc1cd6c37a2a290f5a --- /dev/null +++ b/H3k27ac/special_tokens_map.json @@ -0,0 +1,23 @@ +{ + "mask_token": { + "content": "[MASK]", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false + }, + "pad_token": { + "content": "[PAD]", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false + }, + "unk_token": { + "content": "[UNK]", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false + } +} diff --git a/H3k27ac/tokenizer.json b/H3k27ac/tokenizer.json new file mode 100644 index 0000000000000000000000000000000000000000..24906c9d648f5357eb9554825797660310af37a8 --- /dev/null +++ b/H3k27ac/tokenizer.json @@ -0,0 +1,75 @@ +{ + "version": "1.0", + "truncation": { + "direction": "Right", + "max_length": 2500, + "strategy": "LongestFirst", + "stride": 0 + }, + "padding": { + "strategy": { + "Fixed": 2500 + }, + "direction": "Right", + "pad_to_multiple_of": null, + "pad_id": 0, + "pad_type_id": 0, + "pad_token": "[PAD]" + }, + "added_tokens": [ + { + "id": 0, + "content": "[PAD]", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false, + "special": true + }, + { + "id": 1, + "content": "[MASK]", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false, + "special": true + }, + { + "id": 2, + "content": "[UNK]", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false, + "special": true + } + ], + "normalizer": { + "type": "Lowercase" + }, + "pre_tokenizer": { + "type": "Whitespace" + }, + "post_processor": null, + "decoder": null, + "model": { + "type": "BPE", + "dropout": null, + "unk_token": "[UNK]", + "continuing_subword_prefix": null, + "end_of_word_suffix": null, + "fuse_unk": false, + "byte_fallback": false, + "vocab": { + "[PAD]": 0, + "[MASK]": 1, + "[UNK]": 2, + "a": 3, + "c": 4, + "g": 5, + "t": 6 + }, + "merges": [] + } +} \ No newline at end of file diff --git a/H3k27ac/tokenizer_config.json b/H3k27ac/tokenizer_config.json new file mode 100644 index 0000000000000000000000000000000000000000..9a52165c8c2f352aff39336d757e320f13ba1c17 --- /dev/null +++ b/H3k27ac/tokenizer_config.json @@ -0,0 +1,34 @@ +{ + "added_tokens_decoder": { + "0": { + "content": "[PAD]", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "1": { + "content": "[MASK]", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "2": { + "content": "[UNK]", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + } + }, + "clean_up_tokenization_spaces": true, + "mask_token": "[MASK]", + "model_max_length": 2500, + "pad_token": "[PAD]", + "tokenizer_class": "PreTrainedTokenizerFast", + "unk_token": "[UNK]" +} diff --git a/Pou5f1_TF/config.json b/Pou5f1_TF/config.json new file mode 100644 index 0000000000000000000000000000000000000000..9d321b56dac4fc440968591bca13ad558673ae67 --- /dev/null +++ b/Pou5f1_TF/config.json @@ -0,0 +1,66 @@ +{ + "_name_or_path": "/nvme0/wb_ssd0/FishCaduceus/pretrained_model/FishCaduceus_train_l28_512/checkpoint-40000", + "architectures": [ + "CaduceusForSequenceClassification" + ], + "auto_map": { + "AutoConfig": "configuration_caduceus.CaduceusConfig", + "AutoModel": "modeling_caduceus.Caduceus", + "AutoModelForMaskedLM": "modeling_caduceus.CaduceusForMaskedLM", + "AutoModelForSequenceClassification": "modeling_caduceus.CaduceusForSequenceClassification" + }, + "bidirectional": true, + "bidirectional_strategy": "add", + "bidirectional_weight_tie": true, + "complement_map": { + "0": 0, + "1": 1, + "2": 2, + "3": 6, + "4": 5, + "5": 4, + "6": 3, + "7": 7 + }, + "d_model": 768, + "fused_add_norm": true, + "id2label": { + "0": "Not", + "1": "Yes" + }, + "initializer_cfg": { + "initializer_range": 0.02, + "n_residuals_per_layer": 1, + "rescale_prenorm_residual": true + }, + "label2id": { + "Not": 0, + "Yes": 1 + }, + "model_type": "caduceus", + "n_layer": 28, + "norm_epsilon": 1e-05, + "pad_token_id": 0, + "pad_vocab_size_multiple": 8, + "problem_type": "single_label_classification", + "rcps": true, + "residual_in_fp32": true, + "rms_norm": true, + "ssm_cfg": { + "bias": false, + "conv_bias": true, + "d_conv": 4, + "d_state": 16, + "dt_init": "random", + "dt_init_floor": 0.0001, + "dt_max": 0.1, + "dt_min": 0.001, + "dt_rank": "auto", + "dt_scale": 1.0, + "expand": 2, + "use_fast_path": true + }, + "torch_dtype": "float32", + "transformers_version": "4.30.2", + "vocab_size": 8 +} diff --git a/Pou5f1_TF/pytorch_model.bin b/Pou5f1_TF/pytorch_model.bin new file mode 100644 index 0000000000000000000000000000000000000000..93fead92b5591861255d2494bafad83f09d28d36 --- /dev/null +++ b/Pou5f1_TF/pytorch_model.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3ca6135205cadf782f624110f7e795f80f0940f1f96536ca0228adf6bb2df846 +size 448617482 diff --git a/Pou5f1_TF/special_tokens_map.json b/Pou5f1_TF/special_tokens_map.json new file mode 100644 index 0000000000000000000000000000000000000000..962961477153a31b5606b5dc1cd6c37a2a290f5a --- /dev/null +++ b/Pou5f1_TF/special_tokens_map.json @@ -0,0 +1,23 @@ +{ + "mask_token": { + "content": "[MASK]", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false + }, + "pad_token": { + "content": "[PAD]", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false + }, + "unk_token": { + "content": "[UNK]", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false + } +} diff --git a/Pou5f1_TF/tokenizer.json b/Pou5f1_TF/tokenizer.json new file mode 100644 index 0000000000000000000000000000000000000000..f4d365b915d8322e842b2df8c23cca5a8e62920d --- /dev/null +++ b/Pou5f1_TF/tokenizer.json @@ -0,0 +1,75 @@ +{ + "version": "1.0", + "truncation": { + "direction": "Right", + "max_length": 800, + "strategy": "LongestFirst", + "stride": 0 + }, + "padding": { + "strategy": { + "Fixed": 800 + }, + "direction": "Right", + "pad_to_multiple_of": null, + "pad_id": 0, + "pad_type_id": 0, + "pad_token": "[PAD]" + }, + "added_tokens": [ + { + "id": 0, + "content": "[PAD]", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false, + "special": true + }, + { + "id": 1, + "content": "[MASK]", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false, + "special": true + }, + { + "id": 2, + "content": "[UNK]", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false, + "special": true + } + ], + "normalizer": { + "type": "Lowercase" + }, + "pre_tokenizer": { + "type": "Whitespace" + }, + "post_processor": null, + "decoder": null, + "model": { + "type": "BPE", + "dropout": null, + "unk_token": "[UNK]", + "continuing_subword_prefix": null, + "end_of_word_suffix": null, + "fuse_unk": false, + "byte_fallback": false, + "vocab": { + "[PAD]": 0, + "[MASK]": 1, + "[UNK]": 2, + "a": 3, + "c": 4, + "g": 5, + "t": 6 + }, + "merges": [] + } +} \ No newline at end of file diff --git a/Pou5f1_TF/tokenizer_config.json b/Pou5f1_TF/tokenizer_config.json new file mode 100644 index 0000000000000000000000000000000000000000..ffdec809295764641445d01323aaee8e553854be --- /dev/null +++ b/Pou5f1_TF/tokenizer_config.json @@ -0,0 +1,34 @@ +{ + "added_tokens_decoder": { + "0": { + "content": "[PAD]", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "1": { + "content": "[MASK]", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "2": { + "content": "[UNK]", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + } + }, + "clean_up_tokenization_spaces": true, + "mask_token": "[MASK]", + "model_max_length": 800, + "pad_token": "[PAD]", + "tokenizer_class": "PreTrainedTokenizerFast", + "unk_token": "[UNK]" +} diff --git a/README.md b/README.md index 3c7c6a10d0d6f251612d9fbc86faab06d66fd918..c371a8583979b24fec707610637a40a10bb140dc 100644 --- a/README.md +++ b/README.md @@ -1,3 +1,87 @@ --- -license: cc-by-nc-sa-4.0 +language: +- en +library_name: transformers +tags: +- DNA +- genomics +- fish +- sequence-classification +- FishCaduceus +- Fish_GUE +- fine-tuned +- single-nucleotide --- + +# FishCaduceus-28L-512-FishGUE + +`FishCaduceus-28L-512-FishGUE` is a collection of 17 task-specific models obtained by fine-tuning the pretrained `FishCaduceus-28L-512` DNA language model on downstream fish genomic function prediction tasks from Fish_GUE. + +## Model description + +This repository contains one FishCaduceus backbone family and one fine-tuned sequence-classification model for each included task. The original task directory names are retained so that the repository can be used with `subfolder`-based loading. + +## Base model + +The base model is [`FishCaduceus/FishCaduceus-28L-512`](https://huggingface.co/FishCaduceus/FishCaduceus-28L-512). + +## Included downstream tasks + +| Task directory | Task description | +|---|---| +| `CTCF_TF` | CTCF transcription factor binding site prediction | +| `H3k27ac` | H3K27ac histone modification prediction | +| `H3K27me3` | H3K27me3 histone modification prediction | +| `H3K4me1` | H3K4me1 histone modification prediction | +| `H3K4me3` | H3K4me3 histone modification prediction | +| `H3K9me3` | H3K9me3 histone modification prediction | +| `Pou5f1_TF` | Pou5f1 transcription factor binding site prediction | +| `Sox2_TF` | Sox2 transcription factor binding site prediction | +| `prom_1k_all` | Promoter prediction using 1-kb sequences | +| `prom_1k_notata` | Promoter prediction using 1-kb sequences for the non-TATA promoter subset | +| `prom_1k_tata` | Promoter prediction using 1-kb sequences for the TATA promoter subset | +| `prom_300_all` | Promoter prediction using 300-bp sequences | +| `prom_300_notata` | Promoter prediction using 300-bp sequences for the non-TATA promoter subset | +| `prom_300_tata` | Promoter prediction using 300-bp sequences for the TATA promoter subset | +| `splice_acceptor` | Splice acceptor site prediction | +| `splice_donor` | Splice donor site prediction | +| `splice_all` | Splice site classification | + +## Repository structure + +The repository contains 17 task directories. Each task retains its original name and contains a configuration, model weight file, and tokenizer files where present. + +## Training data + +These models were fine-tuned on the corresponding downstream genomic function prediction tasks from Fish_GUE. No task sample counts are asserted here. + +## Intended uses + +The models are intended for research on fish genomic sequence representation and task-specific genomic function prediction. + +## Limitations + +The task models reflect the training data and task definitions used by Fish_GUE. Transfer to other species, assemblies, sequence lengths, or label definitions should be validated independently. + +## How to use + +The audited task configurations declare `CaduceusForSequenceClassification`, `model_type: caduceus`, binary or three-way label mappings through `id2label`/`label2id`, and an `auto_map` for Caduceus classes. Loading with Transformers is expected to require `trust_remote_code=True` and an environment that provides the referenced Caduceus implementation. The task directories do not contain custom Python implementation files, so standalone execution from this repository alone is not guaranteed. + +## Files in this repository + +Intermediate checkpoints, test metrics, test predictions, and training argument files were deliberately excluded. Model weights, configurations, and tokenizer files needed by the original task exports were retained. + +## Citation + +The FishCaduceus manuscript is in preparation. Citation information will be added after publication. + +## Acknowledgements + +FishCaduceus was developed for research on fish genomes at the Institute of Hydrobiology, Chinese Academy of Sciences. + +## Contact + +Xiao-Qin Xia +Institute of Hydrobiology, Chinese Academy of Sciences +Email: xqxia@ihb.ac.cn + diff --git a/Sox2_TF/config.json b/Sox2_TF/config.json new file mode 100644 index 0000000000000000000000000000000000000000..9d321b56dac4fc440968591bca13ad558673ae67 --- /dev/null +++ b/Sox2_TF/config.json @@ -0,0 +1,66 @@ +{ + "_name_or_path": "/nvme0/wb_ssd0/FishCaduceus/pretrained_model/FishCaduceus_train_l28_512/checkpoint-40000", + "architectures": [ + "CaduceusForSequenceClassification" + ], + "auto_map": { + "AutoConfig": "configuration_caduceus.CaduceusConfig", + "AutoModel": "modeling_caduceus.Caduceus", + "AutoModelForMaskedLM": "modeling_caduceus.CaduceusForMaskedLM", + "AutoModelForSequenceClassification": "modeling_caduceus.CaduceusForSequenceClassification" + }, + "bidirectional": true, + "bidirectional_strategy": "add", + "bidirectional_weight_tie": true, + "complement_map": { + "0": 0, + "1": 1, + "2": 2, + "3": 6, + "4": 5, + "5": 4, + "6": 3, + "7": 7 + }, + "d_model": 768, + "fused_add_norm": true, + "id2label": { + "0": "Not", + "1": "Yes" + }, + "initializer_cfg": { + "initializer_range": 0.02, + "n_residuals_per_layer": 1, + "rescale_prenorm_residual": true + }, + "label2id": { + "Not": 0, + "Yes": 1 + }, + "model_type": "caduceus", + "n_layer": 28, + "norm_epsilon": 1e-05, + "pad_token_id": 0, + "pad_vocab_size_multiple": 8, + "problem_type": "single_label_classification", + "rcps": true, + "residual_in_fp32": true, + "rms_norm": true, + "ssm_cfg": { + "bias": false, + "conv_bias": true, + "d_conv": 4, + "d_state": 16, + "dt_init": "random", + "dt_init_floor": 0.0001, + "dt_max": 0.1, + "dt_min": 0.001, + "dt_rank": "auto", + "dt_scale": 1.0, + "expand": 2, + "use_fast_path": true + }, + "torch_dtype": "float32", + "transformers_version": "4.30.2", + "vocab_size": 8 +} diff --git a/Sox2_TF/pytorch_model.bin b/Sox2_TF/pytorch_model.bin new file mode 100644 index 0000000000000000000000000000000000000000..ab576e448b8777322ef6d616ff6cea52c7d98e1f --- /dev/null +++ b/Sox2_TF/pytorch_model.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:942cd5cdd707aec9d95b2170172ba7658e278e5ce539c03dea62db2c81ba2121 +size 448617482 diff --git a/Sox2_TF/special_tokens_map.json b/Sox2_TF/special_tokens_map.json new file mode 100644 index 0000000000000000000000000000000000000000..962961477153a31b5606b5dc1cd6c37a2a290f5a --- /dev/null +++ b/Sox2_TF/special_tokens_map.json @@ -0,0 +1,23 @@ +{ + "mask_token": { + "content": "[MASK]", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false + }, + "pad_token": { + "content": "[PAD]", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false + }, + "unk_token": { + "content": "[UNK]", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false + } +} diff --git a/Sox2_TF/tokenizer.json b/Sox2_TF/tokenizer.json new file mode 100644 index 0000000000000000000000000000000000000000..f4d365b915d8322e842b2df8c23cca5a8e62920d --- /dev/null +++ b/Sox2_TF/tokenizer.json @@ -0,0 +1,75 @@ +{ + "version": "1.0", + "truncation": { + "direction": "Right", + "max_length": 800, + "strategy": "LongestFirst", + "stride": 0 + }, + "padding": { + "strategy": { + "Fixed": 800 + }, + "direction": "Right", + "pad_to_multiple_of": null, + "pad_id": 0, + "pad_type_id": 0, + "pad_token": "[PAD]" + }, + "added_tokens": [ + { + "id": 0, + "content": "[PAD]", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false, + "special": true + }, + { + "id": 1, + "content": "[MASK]", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false, + "special": true + }, + { + "id": 2, + "content": "[UNK]", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false, + "special": true + } + ], + "normalizer": { + "type": "Lowercase" + }, + "pre_tokenizer": { + "type": "Whitespace" + }, + "post_processor": null, + "decoder": null, + "model": { + "type": "BPE", + "dropout": null, + "unk_token": "[UNK]", + "continuing_subword_prefix": null, + "end_of_word_suffix": null, + "fuse_unk": false, + "byte_fallback": false, + "vocab": { + "[PAD]": 0, + "[MASK]": 1, + "[UNK]": 2, + "a": 3, + "c": 4, + "g": 5, + "t": 6 + }, + "merges": [] + } +} \ No newline at end of file diff --git a/Sox2_TF/tokenizer_config.json b/Sox2_TF/tokenizer_config.json new file mode 100644 index 0000000000000000000000000000000000000000..ffdec809295764641445d01323aaee8e553854be --- /dev/null +++ b/Sox2_TF/tokenizer_config.json @@ -0,0 +1,34 @@ +{ + "added_tokens_decoder": { + "0": { + "content": "[PAD]", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "1": { + "content": "[MASK]", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "2": { + "content": "[UNK]", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + } + }, + "clean_up_tokenization_spaces": true, + "mask_token": "[MASK]", + "model_max_length": 800, + "pad_token": "[PAD]", + "tokenizer_class": "PreTrainedTokenizerFast", + "unk_token": "[UNK]" +} diff --git a/prom_1k_all/config.json b/prom_1k_all/config.json new file mode 100644 index 0000000000000000000000000000000000000000..9d321b56dac4fc440968591bca13ad558673ae67 --- /dev/null +++ b/prom_1k_all/config.json @@ -0,0 +1,66 @@ +{ + "_name_or_path": "/nvme0/wb_ssd0/FishCaduceus/pretrained_model/FishCaduceus_train_l28_512/checkpoint-40000", + "architectures": [ + "CaduceusForSequenceClassification" + ], + "auto_map": { + "AutoConfig": "configuration_caduceus.CaduceusConfig", + "AutoModel": "modeling_caduceus.Caduceus", + "AutoModelForMaskedLM": "modeling_caduceus.CaduceusForMaskedLM", + "AutoModelForSequenceClassification": "modeling_caduceus.CaduceusForSequenceClassification" + }, + "bidirectional": true, + "bidirectional_strategy": "add", + "bidirectional_weight_tie": true, + "complement_map": { + "0": 0, + "1": 1, + "2": 2, + "3": 6, + "4": 5, + "5": 4, + "6": 3, + "7": 7 + }, + "d_model": 768, + "fused_add_norm": true, + "id2label": { + "0": "Not", + "1": "Yes" + }, + "initializer_cfg": { + "initializer_range": 0.02, + "n_residuals_per_layer": 1, + "rescale_prenorm_residual": true + }, + "label2id": { + "Not": 0, + "Yes": 1 + }, + "model_type": "caduceus", + "n_layer": 28, + "norm_epsilon": 1e-05, + "pad_token_id": 0, + "pad_vocab_size_multiple": 8, + "problem_type": "single_label_classification", + "rcps": true, + "residual_in_fp32": true, + "rms_norm": true, + "ssm_cfg": { + "bias": false, + "conv_bias": true, + "d_conv": 4, + "d_state": 16, + "dt_init": "random", + "dt_init_floor": 0.0001, + "dt_max": 0.1, + "dt_min": 0.001, + "dt_rank": "auto", + "dt_scale": 1.0, + "expand": 2, + "use_fast_path": true + }, + "torch_dtype": "float32", + "transformers_version": "4.30.2", + "vocab_size": 8 +} diff --git a/prom_1k_all/pytorch_model.bin b/prom_1k_all/pytorch_model.bin new file mode 100644 index 0000000000000000000000000000000000000000..606a4cb34314b1b5330d0eeec492983fd06fd1a7 --- /dev/null +++ b/prom_1k_all/pytorch_model.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5d782300acb5388969f0d664a3ce08f23c94b203482c5bf0b0631b243525bd70 +size 448617482 diff --git a/prom_1k_all/special_tokens_map.json b/prom_1k_all/special_tokens_map.json new file mode 100644 index 0000000000000000000000000000000000000000..962961477153a31b5606b5dc1cd6c37a2a290f5a --- /dev/null +++ b/prom_1k_all/special_tokens_map.json @@ -0,0 +1,23 @@ +{ + "mask_token": { + "content": "[MASK]", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false + }, + "pad_token": { + "content": "[PAD]", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false + }, + "unk_token": { + "content": "[UNK]", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false + } +} diff --git a/prom_1k_all/tokenizer.json b/prom_1k_all/tokenizer.json new file mode 100644 index 0000000000000000000000000000000000000000..b7081ad936c9c70c42613b06e9d5853c31d9c91b --- /dev/null +++ b/prom_1k_all/tokenizer.json @@ -0,0 +1,75 @@ +{ + "version": "1.0", + "truncation": { + "direction": "Right", + "max_length": 1000, + "strategy": "LongestFirst", + "stride": 0 + }, + "padding": { + "strategy": { + "Fixed": 1000 + }, + "direction": "Right", + "pad_to_multiple_of": null, + "pad_id": 0, + "pad_type_id": 0, + "pad_token": "[PAD]" + }, + "added_tokens": [ + { + "id": 0, + "content": "[PAD]", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false, + "special": true + }, + { + "id": 1, + "content": "[MASK]", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false, + "special": true + }, + { + "id": 2, + "content": "[UNK]", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false, + "special": true + } + ], + "normalizer": { + "type": "Lowercase" + }, + "pre_tokenizer": { + "type": "Whitespace" + }, + "post_processor": null, + "decoder": null, + "model": { + "type": "BPE", + "dropout": null, + "unk_token": "[UNK]", + "continuing_subword_prefix": null, + "end_of_word_suffix": null, + "fuse_unk": false, + "byte_fallback": false, + "vocab": { + "[PAD]": 0, + "[MASK]": 1, + "[UNK]": 2, + "a": 3, + "c": 4, + "g": 5, + "t": 6 + }, + "merges": [] + } +} \ No newline at end of file diff --git a/prom_1k_all/tokenizer_config.json b/prom_1k_all/tokenizer_config.json new file mode 100644 index 0000000000000000000000000000000000000000..aab66f66155cda4f65447236908b791d8e30dbf9 --- /dev/null +++ b/prom_1k_all/tokenizer_config.json @@ -0,0 +1,34 @@ +{ + "added_tokens_decoder": { + "0": { + "content": "[PAD]", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "1": { + "content": "[MASK]", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "2": { + "content": "[UNK]", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + } + }, + "clean_up_tokenization_spaces": true, + "mask_token": "[MASK]", + "model_max_length": 1000, + "pad_token": "[PAD]", + "tokenizer_class": "PreTrainedTokenizerFast", + "unk_token": "[UNK]" +} diff --git a/prom_1k_notata/config.json b/prom_1k_notata/config.json new file mode 100644 index 0000000000000000000000000000000000000000..9d321b56dac4fc440968591bca13ad558673ae67 --- /dev/null +++ b/prom_1k_notata/config.json @@ -0,0 +1,66 @@ +{ + "_name_or_path": "/nvme0/wb_ssd0/FishCaduceus/pretrained_model/FishCaduceus_train_l28_512/checkpoint-40000", + "architectures": [ + "CaduceusForSequenceClassification" + ], + "auto_map": { + "AutoConfig": "configuration_caduceus.CaduceusConfig", + "AutoModel": "modeling_caduceus.Caduceus", + "AutoModelForMaskedLM": "modeling_caduceus.CaduceusForMaskedLM", + "AutoModelForSequenceClassification": "modeling_caduceus.CaduceusForSequenceClassification" + }, + "bidirectional": true, + "bidirectional_strategy": "add", + "bidirectional_weight_tie": true, + "complement_map": { + "0": 0, + "1": 1, + "2": 2, + "3": 6, + "4": 5, + "5": 4, + "6": 3, + "7": 7 + }, + "d_model": 768, + "fused_add_norm": true, + "id2label": { + "0": "Not", + "1": "Yes" + }, + "initializer_cfg": { + "initializer_range": 0.02, + "n_residuals_per_layer": 1, + "rescale_prenorm_residual": true + }, + "label2id": { + "Not": 0, + "Yes": 1 + }, + "model_type": "caduceus", + "n_layer": 28, + "norm_epsilon": 1e-05, + "pad_token_id": 0, + "pad_vocab_size_multiple": 8, + "problem_type": "single_label_classification", + "rcps": true, + "residual_in_fp32": true, + "rms_norm": true, + "ssm_cfg": { + "bias": false, + "conv_bias": true, + "d_conv": 4, + "d_state": 16, + "dt_init": "random", + "dt_init_floor": 0.0001, + "dt_max": 0.1, + "dt_min": 0.001, + "dt_rank": "auto", + "dt_scale": 1.0, + "expand": 2, + "use_fast_path": true + }, + "torch_dtype": "float32", + "transformers_version": "4.30.2", + "vocab_size": 8 +} diff --git a/prom_1k_notata/pytorch_model.bin b/prom_1k_notata/pytorch_model.bin new file mode 100644 index 0000000000000000000000000000000000000000..66024e9b8911b693034d0fe5a88adcd75305f99c --- /dev/null +++ b/prom_1k_notata/pytorch_model.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:86e0c0dab34b7ab3bf6562978e20846548dc0fcd007c52e5eab6dbf8e2136f31 +size 448617482 diff --git a/prom_1k_notata/special_tokens_map.json b/prom_1k_notata/special_tokens_map.json new file mode 100644 index 0000000000000000000000000000000000000000..962961477153a31b5606b5dc1cd6c37a2a290f5a --- /dev/null +++ b/prom_1k_notata/special_tokens_map.json @@ -0,0 +1,23 @@ +{ + "mask_token": { + "content": "[MASK]", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false + }, + "pad_token": { + "content": "[PAD]", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false + }, + "unk_token": { + "content": "[UNK]", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false + } +} diff --git a/prom_1k_notata/tokenizer.json b/prom_1k_notata/tokenizer.json new file mode 100644 index 0000000000000000000000000000000000000000..b7081ad936c9c70c42613b06e9d5853c31d9c91b --- /dev/null +++ b/prom_1k_notata/tokenizer.json @@ -0,0 +1,75 @@ +{ + "version": "1.0", + "truncation": { + "direction": "Right", + "max_length": 1000, + "strategy": "LongestFirst", + "stride": 0 + }, + "padding": { + "strategy": { + "Fixed": 1000 + }, + "direction": "Right", + "pad_to_multiple_of": null, + "pad_id": 0, + "pad_type_id": 0, + "pad_token": "[PAD]" + }, + "added_tokens": [ + { + "id": 0, + "content": "[PAD]", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false, + "special": true + }, + { + "id": 1, + "content": "[MASK]", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false, + "special": true + }, + { + "id": 2, + "content": "[UNK]", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false, + "special": true + } + ], + "normalizer": { + "type": "Lowercase" + }, + "pre_tokenizer": { + "type": "Whitespace" + }, + "post_processor": null, + "decoder": null, + "model": { + "type": "BPE", + "dropout": null, + "unk_token": "[UNK]", + "continuing_subword_prefix": null, + "end_of_word_suffix": null, + "fuse_unk": false, + "byte_fallback": false, + "vocab": { + "[PAD]": 0, + "[MASK]": 1, + "[UNK]": 2, + "a": 3, + "c": 4, + "g": 5, + "t": 6 + }, + "merges": [] + } +} \ No newline at end of file diff --git a/prom_1k_notata/tokenizer_config.json b/prom_1k_notata/tokenizer_config.json new file mode 100644 index 0000000000000000000000000000000000000000..aab66f66155cda4f65447236908b791d8e30dbf9 --- /dev/null +++ b/prom_1k_notata/tokenizer_config.json @@ -0,0 +1,34 @@ +{ + "added_tokens_decoder": { + "0": { + "content": "[PAD]", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "1": { + "content": "[MASK]", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "2": { + "content": "[UNK]", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + } + }, + "clean_up_tokenization_spaces": true, + "mask_token": "[MASK]", + "model_max_length": 1000, + "pad_token": "[PAD]", + "tokenizer_class": "PreTrainedTokenizerFast", + "unk_token": "[UNK]" +} diff --git a/prom_1k_tata/config.json b/prom_1k_tata/config.json new file mode 100644 index 0000000000000000000000000000000000000000..9d321b56dac4fc440968591bca13ad558673ae67 --- /dev/null +++ b/prom_1k_tata/config.json @@ -0,0 +1,66 @@ +{ + "_name_or_path": "/nvme0/wb_ssd0/FishCaduceus/pretrained_model/FishCaduceus_train_l28_512/checkpoint-40000", + "architectures": [ + "CaduceusForSequenceClassification" + ], + "auto_map": { + "AutoConfig": "configuration_caduceus.CaduceusConfig", + "AutoModel": "modeling_caduceus.Caduceus", + "AutoModelForMaskedLM": "modeling_caduceus.CaduceusForMaskedLM", + "AutoModelForSequenceClassification": "modeling_caduceus.CaduceusForSequenceClassification" + }, + "bidirectional": true, + "bidirectional_strategy": "add", + "bidirectional_weight_tie": true, + "complement_map": { + "0": 0, + "1": 1, + "2": 2, + "3": 6, + "4": 5, + "5": 4, + "6": 3, + "7": 7 + }, + "d_model": 768, + "fused_add_norm": true, + "id2label": { + "0": "Not", + "1": "Yes" + }, + "initializer_cfg": { + "initializer_range": 0.02, + "n_residuals_per_layer": 1, + "rescale_prenorm_residual": true + }, + "label2id": { + "Not": 0, + "Yes": 1 + }, + "model_type": "caduceus", + "n_layer": 28, + "norm_epsilon": 1e-05, + "pad_token_id": 0, + "pad_vocab_size_multiple": 8, + "problem_type": "single_label_classification", + "rcps": true, + "residual_in_fp32": true, + "rms_norm": true, + "ssm_cfg": { + "bias": false, + "conv_bias": true, + "d_conv": 4, + "d_state": 16, + "dt_init": "random", + "dt_init_floor": 0.0001, + "dt_max": 0.1, + "dt_min": 0.001, + "dt_rank": "auto", + "dt_scale": 1.0, + "expand": 2, + "use_fast_path": true + }, + "torch_dtype": "float32", + "transformers_version": "4.30.2", + "vocab_size": 8 +} diff --git a/prom_1k_tata/pytorch_model.bin b/prom_1k_tata/pytorch_model.bin new file mode 100644 index 0000000000000000000000000000000000000000..07e8de05bdfb82cb90e15416fc5c864d7dbcb6ad --- /dev/null +++ b/prom_1k_tata/pytorch_model.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2b9951ad3d1fa279b5fb503c7e6523f3ad80d2b5ccf39dd5d0dfc560b7cc5099 +size 448617482 diff --git a/prom_1k_tata/special_tokens_map.json b/prom_1k_tata/special_tokens_map.json new file mode 100644 index 0000000000000000000000000000000000000000..962961477153a31b5606b5dc1cd6c37a2a290f5a --- /dev/null +++ b/prom_1k_tata/special_tokens_map.json @@ -0,0 +1,23 @@ +{ + "mask_token": { + "content": "[MASK]", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false + }, + "pad_token": { + "content": "[PAD]", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false + }, + "unk_token": { + "content": "[UNK]", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false + } +} diff --git a/prom_1k_tata/tokenizer.json b/prom_1k_tata/tokenizer.json new file mode 100644 index 0000000000000000000000000000000000000000..b7081ad936c9c70c42613b06e9d5853c31d9c91b --- /dev/null +++ b/prom_1k_tata/tokenizer.json @@ -0,0 +1,75 @@ +{ + "version": "1.0", + "truncation": { + "direction": "Right", + "max_length": 1000, + "strategy": "LongestFirst", + "stride": 0 + }, + "padding": { + "strategy": { + "Fixed": 1000 + }, + "direction": "Right", + "pad_to_multiple_of": null, + "pad_id": 0, + "pad_type_id": 0, + "pad_token": "[PAD]" + }, + "added_tokens": [ + { + "id": 0, + "content": "[PAD]", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false, + "special": true + }, + { + "id": 1, + "content": "[MASK]", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false, + "special": true + }, + { + "id": 2, + "content": "[UNK]", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false, + "special": true + } + ], + "normalizer": { + "type": "Lowercase" + }, + "pre_tokenizer": { + "type": "Whitespace" + }, + "post_processor": null, + "decoder": null, + "model": { + "type": "BPE", + "dropout": null, + "unk_token": "[UNK]", + "continuing_subword_prefix": null, + "end_of_word_suffix": null, + "fuse_unk": false, + "byte_fallback": false, + "vocab": { + "[PAD]": 0, + "[MASK]": 1, + "[UNK]": 2, + "a": 3, + "c": 4, + "g": 5, + "t": 6 + }, + "merges": [] + } +} \ No newline at end of file diff --git a/prom_1k_tata/tokenizer_config.json b/prom_1k_tata/tokenizer_config.json new file mode 100644 index 0000000000000000000000000000000000000000..aab66f66155cda4f65447236908b791d8e30dbf9 --- /dev/null +++ b/prom_1k_tata/tokenizer_config.json @@ -0,0 +1,34 @@ +{ + "added_tokens_decoder": { + "0": { + "content": "[PAD]", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "1": { + "content": "[MASK]", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "2": { + "content": "[UNK]", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + } + }, + "clean_up_tokenization_spaces": true, + "mask_token": "[MASK]", + "model_max_length": 1000, + "pad_token": "[PAD]", + "tokenizer_class": "PreTrainedTokenizerFast", + "unk_token": "[UNK]" +} diff --git a/prom_300_all/config.json b/prom_300_all/config.json new file mode 100644 index 0000000000000000000000000000000000000000..9d321b56dac4fc440968591bca13ad558673ae67 --- /dev/null +++ b/prom_300_all/config.json @@ -0,0 +1,66 @@ +{ + "_name_or_path": "/nvme0/wb_ssd0/FishCaduceus/pretrained_model/FishCaduceus_train_l28_512/checkpoint-40000", + "architectures": [ + "CaduceusForSequenceClassification" + ], + "auto_map": { + "AutoConfig": "configuration_caduceus.CaduceusConfig", + "AutoModel": "modeling_caduceus.Caduceus", + "AutoModelForMaskedLM": "modeling_caduceus.CaduceusForMaskedLM", + "AutoModelForSequenceClassification": "modeling_caduceus.CaduceusForSequenceClassification" + }, + "bidirectional": true, + "bidirectional_strategy": "add", + "bidirectional_weight_tie": true, + "complement_map": { + "0": 0, + "1": 1, + "2": 2, + "3": 6, + "4": 5, + "5": 4, + "6": 3, + "7": 7 + }, + "d_model": 768, + "fused_add_norm": true, + "id2label": { + "0": "Not", + "1": "Yes" + }, + "initializer_cfg": { + "initializer_range": 0.02, + "n_residuals_per_layer": 1, + "rescale_prenorm_residual": true + }, + "label2id": { + "Not": 0, + "Yes": 1 + }, + "model_type": "caduceus", + "n_layer": 28, + "norm_epsilon": 1e-05, + "pad_token_id": 0, + "pad_vocab_size_multiple": 8, + "problem_type": "single_label_classification", + "rcps": true, + "residual_in_fp32": true, + "rms_norm": true, + "ssm_cfg": { + "bias": false, + "conv_bias": true, + "d_conv": 4, + "d_state": 16, + "dt_init": "random", + "dt_init_floor": 0.0001, + "dt_max": 0.1, + "dt_min": 0.001, + "dt_rank": "auto", + "dt_scale": 1.0, + "expand": 2, + "use_fast_path": true + }, + "torch_dtype": "float32", + "transformers_version": "4.30.2", + "vocab_size": 8 +} diff --git a/prom_300_all/pytorch_model.bin b/prom_300_all/pytorch_model.bin new file mode 100644 index 0000000000000000000000000000000000000000..e7dc1d20e12030390cef72049c58632402c59614 --- /dev/null +++ b/prom_300_all/pytorch_model.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:26debd64bcd9d981de4e022fb990f1d172e58f37f9e8b849f9c7b30ab7924b0e +size 448617482 diff --git a/prom_300_all/special_tokens_map.json b/prom_300_all/special_tokens_map.json new file mode 100644 index 0000000000000000000000000000000000000000..962961477153a31b5606b5dc1cd6c37a2a290f5a --- /dev/null +++ b/prom_300_all/special_tokens_map.json @@ -0,0 +1,23 @@ +{ + "mask_token": { + "content": "[MASK]", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false + }, + "pad_token": { + "content": "[PAD]", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false + }, + "unk_token": { + "content": "[UNK]", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false + } +} diff --git a/prom_300_all/tokenizer.json b/prom_300_all/tokenizer.json new file mode 100644 index 0000000000000000000000000000000000000000..7119d0e651854dc119609c139a0babbd2cc55e9a --- /dev/null +++ b/prom_300_all/tokenizer.json @@ -0,0 +1,75 @@ +{ + "version": "1.0", + "truncation": { + "direction": "Right", + "max_length": 300, + "strategy": "LongestFirst", + "stride": 0 + }, + "padding": { + "strategy": { + "Fixed": 300 + }, + "direction": "Right", + "pad_to_multiple_of": null, + "pad_id": 0, + "pad_type_id": 0, + "pad_token": "[PAD]" + }, + "added_tokens": [ + { + "id": 0, + "content": "[PAD]", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false, + "special": true + }, + { + "id": 1, + "content": "[MASK]", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false, + "special": true + }, + { + "id": 2, + "content": "[UNK]", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false, + "special": true + } + ], + "normalizer": { + "type": "Lowercase" + }, + "pre_tokenizer": { + "type": "Whitespace" + }, + "post_processor": null, + "decoder": null, + "model": { + "type": "BPE", + "dropout": null, + "unk_token": "[UNK]", + "continuing_subword_prefix": null, + "end_of_word_suffix": null, + "fuse_unk": false, + "byte_fallback": false, + "vocab": { + "[PAD]": 0, + "[MASK]": 1, + "[UNK]": 2, + "a": 3, + "c": 4, + "g": 5, + "t": 6 + }, + "merges": [] + } +} \ No newline at end of file diff --git a/prom_300_all/tokenizer_config.json b/prom_300_all/tokenizer_config.json new file mode 100644 index 0000000000000000000000000000000000000000..5b4598766946a32e9172f7d704564217f5293196 --- /dev/null +++ b/prom_300_all/tokenizer_config.json @@ -0,0 +1,34 @@ +{ + "added_tokens_decoder": { + "0": { + "content": "[PAD]", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "1": { + "content": "[MASK]", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "2": { + "content": "[UNK]", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + } + }, + "clean_up_tokenization_spaces": true, + "mask_token": "[MASK]", + "model_max_length": 300, + "pad_token": "[PAD]", + "tokenizer_class": "PreTrainedTokenizerFast", + "unk_token": "[UNK]" +} diff --git a/prom_300_notata/config.json b/prom_300_notata/config.json new file mode 100644 index 0000000000000000000000000000000000000000..9d321b56dac4fc440968591bca13ad558673ae67 --- /dev/null +++ b/prom_300_notata/config.json @@ -0,0 +1,66 @@ +{ + "_name_or_path": "/nvme0/wb_ssd0/FishCaduceus/pretrained_model/FishCaduceus_train_l28_512/checkpoint-40000", + "architectures": [ + "CaduceusForSequenceClassification" + ], + "auto_map": { + "AutoConfig": "configuration_caduceus.CaduceusConfig", + "AutoModel": "modeling_caduceus.Caduceus", + "AutoModelForMaskedLM": "modeling_caduceus.CaduceusForMaskedLM", + "AutoModelForSequenceClassification": "modeling_caduceus.CaduceusForSequenceClassification" + }, + "bidirectional": true, + "bidirectional_strategy": "add", + "bidirectional_weight_tie": true, + "complement_map": { + "0": 0, + "1": 1, + "2": 2, + "3": 6, + "4": 5, + "5": 4, + "6": 3, + "7": 7 + }, + "d_model": 768, + "fused_add_norm": true, + "id2label": { + "0": "Not", + "1": "Yes" + }, + "initializer_cfg": { + "initializer_range": 0.02, + "n_residuals_per_layer": 1, + "rescale_prenorm_residual": true + }, + "label2id": { + "Not": 0, + "Yes": 1 + }, + "model_type": "caduceus", + "n_layer": 28, + "norm_epsilon": 1e-05, + "pad_token_id": 0, + "pad_vocab_size_multiple": 8, + "problem_type": "single_label_classification", + "rcps": true, + "residual_in_fp32": true, + "rms_norm": true, + "ssm_cfg": { + "bias": false, + "conv_bias": true, + "d_conv": 4, + "d_state": 16, + "dt_init": "random", + "dt_init_floor": 0.0001, + "dt_max": 0.1, + "dt_min": 0.001, + "dt_rank": "auto", + "dt_scale": 1.0, + "expand": 2, + "use_fast_path": true + }, + "torch_dtype": "float32", + "transformers_version": "4.30.2", + "vocab_size": 8 +} diff --git a/prom_300_notata/pytorch_model.bin b/prom_300_notata/pytorch_model.bin new file mode 100644 index 0000000000000000000000000000000000000000..ed280fb0313c59fc8115dec7de1edfbc39a471d4 --- /dev/null +++ b/prom_300_notata/pytorch_model.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:293612d8fc8bb27d3bcbd0c6e8a2f7f47095ba55b12a22ab111dc4928aee67e8 +size 448617482 diff --git a/prom_300_notata/special_tokens_map.json b/prom_300_notata/special_tokens_map.json new file mode 100644 index 0000000000000000000000000000000000000000..962961477153a31b5606b5dc1cd6c37a2a290f5a --- /dev/null +++ b/prom_300_notata/special_tokens_map.json @@ -0,0 +1,23 @@ +{ + "mask_token": { + "content": "[MASK]", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false + }, + "pad_token": { + "content": "[PAD]", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false + }, + "unk_token": { + "content": "[UNK]", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false + } +} diff --git a/prom_300_notata/tokenizer.json b/prom_300_notata/tokenizer.json new file mode 100644 index 0000000000000000000000000000000000000000..7119d0e651854dc119609c139a0babbd2cc55e9a --- /dev/null +++ b/prom_300_notata/tokenizer.json @@ -0,0 +1,75 @@ +{ + "version": "1.0", + "truncation": { + "direction": "Right", + "max_length": 300, + "strategy": "LongestFirst", + "stride": 0 + }, + "padding": { + "strategy": { + "Fixed": 300 + }, + "direction": "Right", + "pad_to_multiple_of": null, + "pad_id": 0, + "pad_type_id": 0, + "pad_token": "[PAD]" + }, + "added_tokens": [ + { + "id": 0, + "content": "[PAD]", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false, + "special": true + }, + { + "id": 1, + "content": "[MASK]", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false, + "special": true + }, + { + "id": 2, + "content": "[UNK]", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false, + "special": true + } + ], + "normalizer": { + "type": "Lowercase" + }, + "pre_tokenizer": { + "type": "Whitespace" + }, + "post_processor": null, + "decoder": null, + "model": { + "type": "BPE", + "dropout": null, + "unk_token": "[UNK]", + "continuing_subword_prefix": null, + "end_of_word_suffix": null, + "fuse_unk": false, + "byte_fallback": false, + "vocab": { + "[PAD]": 0, + "[MASK]": 1, + "[UNK]": 2, + "a": 3, + "c": 4, + "g": 5, + "t": 6 + }, + "merges": [] + } +} \ No newline at end of file diff --git a/prom_300_notata/tokenizer_config.json b/prom_300_notata/tokenizer_config.json new file mode 100644 index 0000000000000000000000000000000000000000..5b4598766946a32e9172f7d704564217f5293196 --- /dev/null +++ b/prom_300_notata/tokenizer_config.json @@ -0,0 +1,34 @@ +{ + "added_tokens_decoder": { + "0": { + "content": "[PAD]", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "1": { + "content": "[MASK]", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "2": { + "content": "[UNK]", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + } + }, + "clean_up_tokenization_spaces": true, + "mask_token": "[MASK]", + "model_max_length": 300, + "pad_token": "[PAD]", + "tokenizer_class": "PreTrainedTokenizerFast", + "unk_token": "[UNK]" +} diff --git a/prom_300_tata/config.json b/prom_300_tata/config.json new file mode 100644 index 0000000000000000000000000000000000000000..9d321b56dac4fc440968591bca13ad558673ae67 --- /dev/null +++ b/prom_300_tata/config.json @@ -0,0 +1,66 @@ +{ + "_name_or_path": "/nvme0/wb_ssd0/FishCaduceus/pretrained_model/FishCaduceus_train_l28_512/checkpoint-40000", + "architectures": [ + "CaduceusForSequenceClassification" + ], + "auto_map": { + "AutoConfig": "configuration_caduceus.CaduceusConfig", + "AutoModel": "modeling_caduceus.Caduceus", + "AutoModelForMaskedLM": "modeling_caduceus.CaduceusForMaskedLM", + "AutoModelForSequenceClassification": "modeling_caduceus.CaduceusForSequenceClassification" + }, + "bidirectional": true, + "bidirectional_strategy": "add", + "bidirectional_weight_tie": true, + "complement_map": { + "0": 0, + "1": 1, + "2": 2, + "3": 6, + "4": 5, + "5": 4, + "6": 3, + "7": 7 + }, + "d_model": 768, + "fused_add_norm": true, + "id2label": { + "0": "Not", + "1": "Yes" + }, + "initializer_cfg": { + "initializer_range": 0.02, + "n_residuals_per_layer": 1, + "rescale_prenorm_residual": true + }, + "label2id": { + "Not": 0, + "Yes": 1 + }, + "model_type": "caduceus", + "n_layer": 28, + "norm_epsilon": 1e-05, + "pad_token_id": 0, + "pad_vocab_size_multiple": 8, + "problem_type": "single_label_classification", + "rcps": true, + "residual_in_fp32": true, + "rms_norm": true, + "ssm_cfg": { + "bias": false, + "conv_bias": true, + "d_conv": 4, + "d_state": 16, + "dt_init": "random", + "dt_init_floor": 0.0001, + "dt_max": 0.1, + "dt_min": 0.001, + "dt_rank": "auto", + "dt_scale": 1.0, + "expand": 2, + "use_fast_path": true + }, + "torch_dtype": "float32", + "transformers_version": "4.30.2", + "vocab_size": 8 +} diff --git a/prom_300_tata/pytorch_model.bin b/prom_300_tata/pytorch_model.bin new file mode 100644 index 0000000000000000000000000000000000000000..3b6aef67f070e4128b9ca3e25ea723d38e98b884 --- /dev/null +++ b/prom_300_tata/pytorch_model.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cd755b1aa0e15ec7e296096a2b1542a9514107b1167f3e9ead5fc94079dc1ce9 +size 448617482 diff --git a/prom_300_tata/special_tokens_map.json b/prom_300_tata/special_tokens_map.json new file mode 100644 index 0000000000000000000000000000000000000000..962961477153a31b5606b5dc1cd6c37a2a290f5a --- /dev/null +++ b/prom_300_tata/special_tokens_map.json @@ -0,0 +1,23 @@ +{ + "mask_token": { + "content": "[MASK]", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false + }, + "pad_token": { + "content": "[PAD]", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false + }, + "unk_token": { + "content": "[UNK]", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false + } +} diff --git a/prom_300_tata/tokenizer.json b/prom_300_tata/tokenizer.json new file mode 100644 index 0000000000000000000000000000000000000000..7119d0e651854dc119609c139a0babbd2cc55e9a --- /dev/null +++ b/prom_300_tata/tokenizer.json @@ -0,0 +1,75 @@ +{ + "version": "1.0", + "truncation": { + "direction": "Right", + "max_length": 300, + "strategy": "LongestFirst", + "stride": 0 + }, + "padding": { + "strategy": { + "Fixed": 300 + }, + "direction": "Right", + "pad_to_multiple_of": null, + "pad_id": 0, + "pad_type_id": 0, + "pad_token": "[PAD]" + }, + "added_tokens": [ + { + "id": 0, + "content": "[PAD]", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false, + "special": true + }, + { + "id": 1, + "content": "[MASK]", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false, + "special": true + }, + { + "id": 2, + "content": "[UNK]", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false, + "special": true + } + ], + "normalizer": { + "type": "Lowercase" + }, + "pre_tokenizer": { + "type": "Whitespace" + }, + "post_processor": null, + "decoder": null, + "model": { + "type": "BPE", + "dropout": null, + "unk_token": "[UNK]", + "continuing_subword_prefix": null, + "end_of_word_suffix": null, + "fuse_unk": false, + "byte_fallback": false, + "vocab": { + "[PAD]": 0, + "[MASK]": 1, + "[UNK]": 2, + "a": 3, + "c": 4, + "g": 5, + "t": 6 + }, + "merges": [] + } +} \ No newline at end of file diff --git a/prom_300_tata/tokenizer_config.json b/prom_300_tata/tokenizer_config.json new file mode 100644 index 0000000000000000000000000000000000000000..5b4598766946a32e9172f7d704564217f5293196 --- /dev/null +++ b/prom_300_tata/tokenizer_config.json @@ -0,0 +1,34 @@ +{ + "added_tokens_decoder": { + "0": { + "content": "[PAD]", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "1": { + "content": "[MASK]", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "2": { + "content": "[UNK]", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + } + }, + "clean_up_tokenization_spaces": true, + "mask_token": "[MASK]", + "model_max_length": 300, + "pad_token": "[PAD]", + "tokenizer_class": "PreTrainedTokenizerFast", + "unk_token": "[UNK]" +} diff --git a/splice_acceptor/config.json b/splice_acceptor/config.json new file mode 100644 index 0000000000000000000000000000000000000000..9d321b56dac4fc440968591bca13ad558673ae67 --- /dev/null +++ b/splice_acceptor/config.json @@ -0,0 +1,66 @@ +{ + "_name_or_path": "/nvme0/wb_ssd0/FishCaduceus/pretrained_model/FishCaduceus_train_l28_512/checkpoint-40000", + "architectures": [ + "CaduceusForSequenceClassification" + ], + "auto_map": { + "AutoConfig": "configuration_caduceus.CaduceusConfig", + "AutoModel": "modeling_caduceus.Caduceus", + "AutoModelForMaskedLM": "modeling_caduceus.CaduceusForMaskedLM", + "AutoModelForSequenceClassification": "modeling_caduceus.CaduceusForSequenceClassification" + }, + "bidirectional": true, + "bidirectional_strategy": "add", + "bidirectional_weight_tie": true, + "complement_map": { + "0": 0, + "1": 1, + "2": 2, + "3": 6, + "4": 5, + "5": 4, + "6": 3, + "7": 7 + }, + "d_model": 768, + "fused_add_norm": true, + "id2label": { + "0": "Not", + "1": "Yes" + }, + "initializer_cfg": { + "initializer_range": 0.02, + "n_residuals_per_layer": 1, + "rescale_prenorm_residual": true + }, + "label2id": { + "Not": 0, + "Yes": 1 + }, + "model_type": "caduceus", + "n_layer": 28, + "norm_epsilon": 1e-05, + "pad_token_id": 0, + "pad_vocab_size_multiple": 8, + "problem_type": "single_label_classification", + "rcps": true, + "residual_in_fp32": true, + "rms_norm": true, + "ssm_cfg": { + "bias": false, + "conv_bias": true, + "d_conv": 4, + "d_state": 16, + "dt_init": "random", + "dt_init_floor": 0.0001, + "dt_max": 0.1, + "dt_min": 0.001, + "dt_rank": "auto", + "dt_scale": 1.0, + "expand": 2, + "use_fast_path": true + }, + "torch_dtype": "float32", + "transformers_version": "4.30.2", + "vocab_size": 8 +} diff --git a/splice_acceptor/pytorch_model.bin b/splice_acceptor/pytorch_model.bin new file mode 100644 index 0000000000000000000000000000000000000000..fc93117c1c3b07a7c5390a0676c9607a4985be1c --- /dev/null +++ b/splice_acceptor/pytorch_model.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2e8968149e6bfb6b1b57354b98c4578e09294ad1b53a33a589ef6009e8641ce2 +size 448617482 diff --git a/splice_acceptor/special_tokens_map.json b/splice_acceptor/special_tokens_map.json new file mode 100644 index 0000000000000000000000000000000000000000..962961477153a31b5606b5dc1cd6c37a2a290f5a --- /dev/null +++ b/splice_acceptor/special_tokens_map.json @@ -0,0 +1,23 @@ +{ + "mask_token": { + "content": "[MASK]", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false + }, + "pad_token": { + "content": "[PAD]", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false + }, + "unk_token": { + "content": "[UNK]", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false + } +} diff --git a/splice_acceptor/tokenizer.json b/splice_acceptor/tokenizer.json new file mode 100644 index 0000000000000000000000000000000000000000..18b5b86306dd6d97ecc39f63de7e1c693b847182 --- /dev/null +++ b/splice_acceptor/tokenizer.json @@ -0,0 +1,75 @@ +{ + "version": "1.0", + "truncation": { + "direction": "Right", + "max_length": 600, + "strategy": "LongestFirst", + "stride": 0 + }, + "padding": { + "strategy": { + "Fixed": 600 + }, + "direction": "Right", + "pad_to_multiple_of": null, + "pad_id": 0, + "pad_type_id": 0, + "pad_token": "[PAD]" + }, + "added_tokens": [ + { + "id": 0, + "content": "[PAD]", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false, + "special": true + }, + { + "id": 1, + "content": "[MASK]", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false, + "special": true + }, + { + "id": 2, + "content": "[UNK]", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false, + "special": true + } + ], + "normalizer": { + "type": "Lowercase" + }, + "pre_tokenizer": { + "type": "Whitespace" + }, + "post_processor": null, + "decoder": null, + "model": { + "type": "BPE", + "dropout": null, + "unk_token": "[UNK]", + "continuing_subword_prefix": null, + "end_of_word_suffix": null, + "fuse_unk": false, + "byte_fallback": false, + "vocab": { + "[PAD]": 0, + "[MASK]": 1, + "[UNK]": 2, + "a": 3, + "c": 4, + "g": 5, + "t": 6 + }, + "merges": [] + } +} \ No newline at end of file diff --git a/splice_acceptor/tokenizer_config.json b/splice_acceptor/tokenizer_config.json new file mode 100644 index 0000000000000000000000000000000000000000..48f683595edc797448c853a5ffa65e8e4f3c98fb --- /dev/null +++ b/splice_acceptor/tokenizer_config.json @@ -0,0 +1,34 @@ +{ + "added_tokens_decoder": { + "0": { + "content": "[PAD]", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "1": { + "content": "[MASK]", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "2": { + "content": "[UNK]", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + } + }, + "clean_up_tokenization_spaces": true, + "mask_token": "[MASK]", + "model_max_length": 600, + "pad_token": "[PAD]", + "tokenizer_class": "PreTrainedTokenizerFast", + "unk_token": "[UNK]" +} diff --git a/splice_all/config.json b/splice_all/config.json new file mode 100644 index 0000000000000000000000000000000000000000..bcc507332bf6f1b0855b3d1609a330bcbb054452 --- /dev/null +++ b/splice_all/config.json @@ -0,0 +1,68 @@ +{ + "_name_or_path": "/nvme0/wb_ssd0/FishCaduceus/pretrained_model/FishCaduceus_train_l28_512/checkpoint-40000", + "architectures": [ + "CaduceusForSequenceClassification" + ], + "auto_map": { + "AutoConfig": "configuration_caduceus.CaduceusConfig", + "AutoModel": "modeling_caduceus.Caduceus", + "AutoModelForMaskedLM": "modeling_caduceus.CaduceusForMaskedLM", + "AutoModelForSequenceClassification": "modeling_caduceus.CaduceusForSequenceClassification" + }, + "bidirectional": true, + "bidirectional_strategy": "add", + "bidirectional_weight_tie": true, + "complement_map": { + "0": 0, + "1": 1, + "2": 2, + "3": 6, + "4": 5, + "5": 4, + "6": 3, + "7": 7 + }, + "d_model": 768, + "fused_add_norm": true, + "id2label": { + "0": "Not", + "1": "Acceptor", + "2": "Donor" + }, + "initializer_cfg": { + "initializer_range": 0.02, + "n_residuals_per_layer": 1, + "rescale_prenorm_residual": true + }, + "label2id": { + "Acceptor": 1, + "Donor": 2, + "Not": 0 + }, + "model_type": "caduceus", + "n_layer": 28, + "norm_epsilon": 1e-05, + "pad_token_id": 0, + "pad_vocab_size_multiple": 8, + "problem_type": "single_label_classification", + "rcps": true, + "residual_in_fp32": true, + "rms_norm": true, + "ssm_cfg": { + "bias": false, + "conv_bias": true, + "d_conv": 4, + "d_state": 16, + "dt_init": "random", + "dt_init_floor": 0.0001, + "dt_max": 0.1, + "dt_min": 0.001, + "dt_rank": "auto", + "dt_scale": 1.0, + "expand": 2, + "use_fast_path": true + }, + "torch_dtype": "float32", + "transformers_version": "4.30.2", + "vocab_size": 8 +} diff --git a/splice_all/pytorch_model.bin b/splice_all/pytorch_model.bin new file mode 100644 index 0000000000000000000000000000000000000000..c9d4aedd26187f46527a957466a5c6bad2fc2122 --- /dev/null +++ b/splice_all/pytorch_model.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:766de7da6bf3ecf873ab99e3e5ab652316ffff72a817d66804a55e8b3668a225 +size 448620554 diff --git a/splice_all/special_tokens_map.json b/splice_all/special_tokens_map.json new file mode 100644 index 0000000000000000000000000000000000000000..962961477153a31b5606b5dc1cd6c37a2a290f5a --- /dev/null +++ b/splice_all/special_tokens_map.json @@ -0,0 +1,23 @@ +{ + "mask_token": { + "content": "[MASK]", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false + }, + "pad_token": { + "content": "[PAD]", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false + }, + "unk_token": { + "content": "[UNK]", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false + } +} diff --git a/splice_all/tokenizer.json b/splice_all/tokenizer.json new file mode 100644 index 0000000000000000000000000000000000000000..18b5b86306dd6d97ecc39f63de7e1c693b847182 --- /dev/null +++ b/splice_all/tokenizer.json @@ -0,0 +1,75 @@ +{ + "version": "1.0", + "truncation": { + "direction": "Right", + "max_length": 600, + "strategy": "LongestFirst", + "stride": 0 + }, + "padding": { + "strategy": { + "Fixed": 600 + }, + "direction": "Right", + "pad_to_multiple_of": null, + "pad_id": 0, + "pad_type_id": 0, + "pad_token": "[PAD]" + }, + "added_tokens": [ + { + "id": 0, + "content": "[PAD]", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false, + "special": true + }, + { + "id": 1, + "content": "[MASK]", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false, + "special": true + }, + { + "id": 2, + "content": "[UNK]", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false, + "special": true + } + ], + "normalizer": { + "type": "Lowercase" + }, + "pre_tokenizer": { + "type": "Whitespace" + }, + "post_processor": null, + "decoder": null, + "model": { + "type": "BPE", + "dropout": null, + "unk_token": "[UNK]", + "continuing_subword_prefix": null, + "end_of_word_suffix": null, + "fuse_unk": false, + "byte_fallback": false, + "vocab": { + "[PAD]": 0, + "[MASK]": 1, + "[UNK]": 2, + "a": 3, + "c": 4, + "g": 5, + "t": 6 + }, + "merges": [] + } +} \ No newline at end of file diff --git a/splice_all/tokenizer_config.json b/splice_all/tokenizer_config.json new file mode 100644 index 0000000000000000000000000000000000000000..48f683595edc797448c853a5ffa65e8e4f3c98fb --- /dev/null +++ b/splice_all/tokenizer_config.json @@ -0,0 +1,34 @@ +{ + "added_tokens_decoder": { + "0": { + "content": "[PAD]", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "1": { + "content": "[MASK]", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "2": { + "content": "[UNK]", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + } + }, + "clean_up_tokenization_spaces": true, + "mask_token": "[MASK]", + "model_max_length": 600, + "pad_token": "[PAD]", + "tokenizer_class": "PreTrainedTokenizerFast", + "unk_token": "[UNK]" +} diff --git a/splice_donor/config.json b/splice_donor/config.json new file mode 100644 index 0000000000000000000000000000000000000000..9d321b56dac4fc440968591bca13ad558673ae67 --- /dev/null +++ b/splice_donor/config.json @@ -0,0 +1,66 @@ +{ + "_name_or_path": "/nvme0/wb_ssd0/FishCaduceus/pretrained_model/FishCaduceus_train_l28_512/checkpoint-40000", + "architectures": [ + "CaduceusForSequenceClassification" + ], + "auto_map": { + "AutoConfig": "configuration_caduceus.CaduceusConfig", + "AutoModel": "modeling_caduceus.Caduceus", + "AutoModelForMaskedLM": "modeling_caduceus.CaduceusForMaskedLM", + "AutoModelForSequenceClassification": "modeling_caduceus.CaduceusForSequenceClassification" + }, + "bidirectional": true, + "bidirectional_strategy": "add", + "bidirectional_weight_tie": true, + "complement_map": { + "0": 0, + "1": 1, + "2": 2, + "3": 6, + "4": 5, + "5": 4, + "6": 3, + "7": 7 + }, + "d_model": 768, + "fused_add_norm": true, + "id2label": { + "0": "Not", + "1": "Yes" + }, + "initializer_cfg": { + "initializer_range": 0.02, + "n_residuals_per_layer": 1, + "rescale_prenorm_residual": true + }, + "label2id": { + "Not": 0, + "Yes": 1 + }, + "model_type": "caduceus", + "n_layer": 28, + "norm_epsilon": 1e-05, + "pad_token_id": 0, + "pad_vocab_size_multiple": 8, + "problem_type": "single_label_classification", + "rcps": true, + "residual_in_fp32": true, + "rms_norm": true, + "ssm_cfg": { + "bias": false, + "conv_bias": true, + "d_conv": 4, + "d_state": 16, + "dt_init": "random", + "dt_init_floor": 0.0001, + "dt_max": 0.1, + "dt_min": 0.001, + "dt_rank": "auto", + "dt_scale": 1.0, + "expand": 2, + "use_fast_path": true + }, + "torch_dtype": "float32", + "transformers_version": "4.30.2", + "vocab_size": 8 +} diff --git a/splice_donor/pytorch_model.bin b/splice_donor/pytorch_model.bin new file mode 100644 index 0000000000000000000000000000000000000000..783106fa95eff242f80cfc8943bce8378bcf463a --- /dev/null +++ b/splice_donor/pytorch_model.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d6a88bbaeabda5b35474a067d7c3ba09f6b017f16b3024b38d8610b3aee4fd43 +size 448617482 diff --git a/splice_donor/special_tokens_map.json b/splice_donor/special_tokens_map.json new file mode 100644 index 0000000000000000000000000000000000000000..962961477153a31b5606b5dc1cd6c37a2a290f5a --- /dev/null +++ b/splice_donor/special_tokens_map.json @@ -0,0 +1,23 @@ +{ + "mask_token": { + "content": "[MASK]", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false + }, + "pad_token": { + "content": "[PAD]", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false + }, + "unk_token": { + "content": "[UNK]", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false + } +} diff --git a/splice_donor/tokenizer.json b/splice_donor/tokenizer.json new file mode 100644 index 0000000000000000000000000000000000000000..18b5b86306dd6d97ecc39f63de7e1c693b847182 --- /dev/null +++ b/splice_donor/tokenizer.json @@ -0,0 +1,75 @@ +{ + "version": "1.0", + "truncation": { + "direction": "Right", + "max_length": 600, + "strategy": "LongestFirst", + "stride": 0 + }, + "padding": { + "strategy": { + "Fixed": 600 + }, + "direction": "Right", + "pad_to_multiple_of": null, + "pad_id": 0, + "pad_type_id": 0, + "pad_token": "[PAD]" + }, + "added_tokens": [ + { + "id": 0, + "content": "[PAD]", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false, + "special": true + }, + { + "id": 1, + "content": "[MASK]", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false, + "special": true + }, + { + "id": 2, + "content": "[UNK]", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false, + "special": true + } + ], + "normalizer": { + "type": "Lowercase" + }, + "pre_tokenizer": { + "type": "Whitespace" + }, + "post_processor": null, + "decoder": null, + "model": { + "type": "BPE", + "dropout": null, + "unk_token": "[UNK]", + "continuing_subword_prefix": null, + "end_of_word_suffix": null, + "fuse_unk": false, + "byte_fallback": false, + "vocab": { + "[PAD]": 0, + "[MASK]": 1, + "[UNK]": 2, + "a": 3, + "c": 4, + "g": 5, + "t": 6 + }, + "merges": [] + } +} \ No newline at end of file diff --git a/splice_donor/tokenizer_config.json b/splice_donor/tokenizer_config.json new file mode 100644 index 0000000000000000000000000000000000000000..48f683595edc797448c853a5ffa65e8e4f3c98fb --- /dev/null +++ b/splice_donor/tokenizer_config.json @@ -0,0 +1,34 @@ +{ + "added_tokens_decoder": { + "0": { + "content": "[PAD]", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "1": { + "content": "[MASK]", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "2": { + "content": "[UNK]", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + } + }, + "clean_up_tokenization_spaces": true, + "mask_token": "[MASK]", + "model_max_length": 600, + "pad_token": "[PAD]", + "tokenizer_class": "PreTrainedTokenizerFast", + "unk_token": "[UNK]" +}