Remove early prototype kmer1-decoder (not used in the paper)

kmer1-decoder/config.json

@@ -1,32 +0,0 @@
-{
-  "activation_function": "gelu_new",
-  "architectures": [
-    "GPT2LMHeadModel"
-  ],
-  "attn_pdrop": 0.1,
-  "bos_token_id": 2,
-  "embd_pdrop": 0.1,
-  "eos_token_id": 3,
-  "initializer_range": 0.02,
-  "layer_norm_epsilon": 1e-05,
-  "model_type": "gpt2",
-  "n_embd": 256,
-  "n_head": 4,
-  "n_inner": 1024,
-  "n_layer": 6,
-  "n_positions": 512,
-  "pad_token_id": 0,
-  "reorder_and_upcast_attn": false,
-  "resid_pdrop": 0.1,
-  "scale_attn_by_inverse_layer_idx": false,
-  "scale_attn_weights": true,
-  "summary_activation": null,
-  "summary_first_dropout": 0.1,
-  "summary_proj_to_labels": true,
-  "summary_type": "cls_index",
-  "summary_use_proj": true,
-  "torch_dtype": "float32",
-  "transformers_version": "4.46.3",
-  "use_cache": true,
-  "vocab_size": 10
-}

kmer1-decoder/eval_results.json

@@ -1,10 +0,0 @@
-{
-  "eval_loss": 0.5514755845069885,
-  "eval_masked_accuracy": 0.7674719289606015,
-  "eval_next_token_count": 509689,
-  "eval_runtime": 0.5524,
-  "eval_samples_per_second": 3620.738,
-  "eval_steps_per_second": 7.241,
-  "epoch": 1.0,
-  "eval_perplexity": 1.7358124670446264
-}

kmer1-decoder/generation_config.json

@@ -1,7 +0,0 @@
-{
-  "_from_model_config": true,
-  "bos_token_id": 2,
-  "eos_token_id": 3,
-  "pad_token_id": 0,
-  "transformers_version": "4.46.3"
-}

kmer1-decoder/model.safetensors

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:a817544c9b4285d173c52016910918351165598075403df76160bab33a7e6bc9
-size 19498304

kmer1-decoder/model_config.json

@@ -1,88 +0,0 @@
-{
-  "vocab_size": 10,
-  "n_positions": 512,
-  "n_embd": 256,
-  "n_layer": 6,
-  "n_head": 4,
-  "n_inner": 1024,
-  "activation_function": "gelu_new",
-  "resid_pdrop": 0.1,
-  "embd_pdrop": 0.1,
-  "attn_pdrop": 0.1,
-  "layer_norm_epsilon": 1e-05,
-  "initializer_range": 0.02,
-  "summary_type": "cls_index",
-  "summary_use_proj": true,
-  "summary_activation": null,
-  "summary_first_dropout": 0.1,
-  "summary_proj_to_labels": true,
-  "scale_attn_weights": true,
-  "use_cache": true,
-  "scale_attn_by_inverse_layer_idx": false,
-  "reorder_and_upcast_attn": false,
-  "bos_token_id": 2,
-  "eos_token_id": 3,
-  "return_dict": true,
-  "output_hidden_states": false,
-  "output_attentions": false,
-  "torchscript": false,
-  "torch_dtype": "float32",
-  "use_bfloat16": false,
-  "tf_legacy_loss": false,
-  "pruned_heads": {},
-  "tie_word_embeddings": true,
-  "chunk_size_feed_forward": 0,
-  "is_encoder_decoder": false,
-  "is_decoder": false,
-  "cross_attention_hidden_size": null,
-  "add_cross_attention": false,
-  "tie_encoder_decoder": false,
-  "max_length": 20,
-  "min_length": 0,
-  "do_sample": false,
-  "early_stopping": false,
-  "num_beams": 1,
-  "num_beam_groups": 1,
-  "diversity_penalty": 0.0,
-  "temperature": 1.0,
-  "top_k": 50,
-  "top_p": 1.0,
-  "typical_p": 1.0,
-  "repetition_penalty": 1.0,
-  "length_penalty": 1.0,
-  "no_repeat_ngram_size": 0,
-  "encoder_no_repeat_ngram_size": 0,
-  "bad_words_ids": null,
-  "num_return_sequences": 1,
-  "output_scores": false,
-  "return_dict_in_generate": false,
-  "forced_bos_token_id": null,
-  "forced_eos_token_id": null,
-  "remove_invalid_values": false,
-  "exponential_decay_length_penalty": null,
-  "suppress_tokens": null,
-  "begin_suppress_tokens": null,
-  "architectures": [
-    "GPT2LMHeadModel"
-  ],
-  "finetuning_task": null,
-  "id2label": {
-    "0": "LABEL_0",
-    "1": "LABEL_1"
-  },
-  "label2id": {
-    "LABEL_0": 0,
-    "LABEL_1": 1
-  },
-  "tokenizer_class": null,
-  "prefix": null,
-  "pad_token_id": 0,
-  "sep_token_id": null,
-  "decoder_start_token_id": null,
-  "task_specific_params": null,
-  "problem_type": null,
-  "_name_or_path": "",
-  "_attn_implementation_autoset": false,
-  "transformers_version": "4.46.3",
-  "model_type": "gpt2"
-}

kmer1-decoder/special_tokens_map.json

@@ -1,7 +0,0 @@
-{
-  "cls_token": "[CLS]",
-  "mask_token": "[MASK]",
-  "pad_token": "[PAD]",
-  "sep_token": "[SEP]",
-  "unk_token": "[UNK]"
-}

kmer1-decoder/tokenizer.json

@@ -1,165 +0,0 @@
-{
-  "version": "1.0",
-  "truncation": {
-    "direction": "Right",
-    "max_length": 512,
-    "strategy": "LongestFirst",
-    "stride": 0
-  },
-  "padding": null,
-  "added_tokens": [
-    {
-      "id": 0,
-      "content": "[PAD]",
-      "single_word": false,
-      "lstrip": false,
-      "rstrip": false,
-      "normalized": false,
-      "special": true
-    },
-    {
-      "id": 1,
-      "content": "[UNK]",
-      "single_word": false,
-      "lstrip": false,
-      "rstrip": false,
-      "normalized": false,
-      "special": true
-    },
-    {
-      "id": 2,
-      "content": "[CLS]",
-      "single_word": false,
-      "lstrip": false,
-      "rstrip": false,
-      "normalized": false,
-      "special": true
-    },
-    {
-      "id": 3,
-      "content": "[SEP]",
-      "single_word": false,
-      "lstrip": false,
-      "rstrip": false,
-      "normalized": false,
-      "special": true
-    },
-    {
-      "id": 4,
-      "content": "[MASK]",
-      "single_word": false,
-      "lstrip": false,
-      "rstrip": false,
-      "normalized": false,
-      "special": true
-    }
-  ],
-  "normalizer": {
-    "type": "BertNormalizer",
-    "clean_text": true,
-    "handle_chinese_chars": false,
-    "strip_accents": false,
-    "lowercase": false
-  },
-  "pre_tokenizer": {
-    "type": "BertPreTokenizer"
-  },
-  "post_processor": {
-    "type": "TemplateProcessing",
-    "single": [
-      {
-        "SpecialToken": {
-          "id": "[CLS]",
-          "type_id": 0
-        }
-      },
-      {
-        "Sequence": {
-          "id": "A",
-          "type_id": 0
-        }
-      },
-      {
-        "SpecialToken": {
-          "id": "[SEP]",
-          "type_id": 0
-        }
-      }
-    ],
-    "pair": [
-      {
-        "SpecialToken": {
-          "id": "[CLS]",
-          "type_id": 0
-        }
-      },
-      {
-        "Sequence": {
-          "id": "A",
-          "type_id": 0
-        }
-      },
-      {
-        "SpecialToken": {
-          "id": "[SEP]",
-          "type_id": 0
-        }
-      },
-      {
-        "Sequence": {
-          "id": "B",
-          "type_id": 1
-        }
-      },
-      {
-        "SpecialToken": {
-          "id": "[SEP]",
-          "type_id": 1
-        }
-      }
-    ],
-    "special_tokens": {
-      "[CLS]": {
-        "id": "[CLS]",
-        "ids": [
-          2
-        ],
-        "tokens": [
-          "[CLS]"
-        ]
-      },
-      "[SEP]": {
-        "id": "[SEP]",
-        "ids": [
-          3
-        ],
-        "tokens": [
-          "[SEP]"
-        ]
-      }
-    }
-  },
-  "decoder": {
-    "type": "WordPiece",
-    "prefix": "##",
-    "cleanup": true
-  },
-  "model": {
-    "type": "WordPiece",
-    "unk_token": "[UNK]",
-    "continuing_subword_prefix": "##",
-    "max_input_chars_per_word": 100,
-    "vocab": {
-      "[PAD]": 0,
-      "[UNK]": 1,
-      "[CLS]": 2,
-      "[SEP]": 3,
-      "[MASK]": 4,
-      "A": 5,
-      "U": 6,
-      "C": 7,
-      "G": 8,
-      "N": 9
-    }
-  }
-}

kmer1-decoder/tokenizer_config.json

@@ -1,57 +0,0 @@
-{
-  "added_tokens_decoder": {
-    "0": {
-      "content": "[PAD]",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "1": {
-      "content": "[UNK]",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "2": {
-      "content": "[CLS]",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "3": {
-      "content": "[SEP]",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "4": {
-      "content": "[MASK]",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    }
-  },
-  "clean_up_tokenization_spaces": true,
-  "cls_token": "[CLS]",
-  "do_basic_tokenize": true,
-  "do_lower_case": false,
-  "mask_token": "[MASK]",
-  "model_max_length": 1000000000000000019884624838656,
-  "never_split": null,
-  "pad_token": "[PAD]",
-  "sep_token": "[SEP]",
-  "strip_accents": false,
-  "tokenize_chinese_chars": false,
-  "tokenizer_class": "BertTokenizer",
-  "unk_token": "[UNK]"
-}

kmer1-decoder/vocab.txt

@@ -1,10 +0,0 @@
-[PAD]
-[UNK]
-[CLS]
-[SEP]
-[MASK]
-A
-U
-C
-G
-N