Upload folder using huggingface_hub

config.json

@@ -0,0 +1,98 @@
+{
+  "adamw_betas_for_muon_others": [
+    0.9,
+    0.95
+  ],
+  "adamw_eps_for_muon_others": 1e-10,
+  "adamw_lr": 0.00064,
+  "adamw_lr_for_muon_others": 0.000267,
+  "adamw_max_grad_norm": 0.5,
+  "adamw_weight_decay": 0.01,
+  "adamw_weight_decay_for_muon_others": 0.05,
+  "adjust_learning_rate_for_accumulation": true,
+  "architectures": [
+    "ViralBERTForContrastiveBinning"
+  ],
+  "attention_head_size": 64,
+  "attention_probs_dropout_prob": 0.0,
+  "batch_size": 256,
+  "cls_token_id": 1,
+  "compile_backend": "inductor",
+  "compile_fullgraph": true,
+  "compile_mode": "default",
+  "data_dir": "data/raw",
+  "dtype": "float32",
+  "fasta_file": "meta-1-vg.fna",
+  "feed_forward_activation": "swiglu",
+  "filter_n": false,
+  "fp16": true,
+  "global_attn_every_n_layers": 0,
+  "global_max_grad_norm": 1.0,
+  "gradient_accumulation_steps": 1,
+  "hidden_dropout_prob": 0.0,
+  "hidden_size": 768,
+  "high_lr_multiplier": 1.0,
+  "high_lr_steps_ratio": 0.0,
+  "initializer_range": 0.02,
+  "intermediate_size": 2048,
+  "layer_norm_eps": 1e-12,
+  "logging_steps": 1000,
+  "lr_scheduler_type": "warmup_cosine",
+  "mask_token_id": 3,
+  "masking_strategy": "structural",
+  "max_eval_samples": 2048,
+  "max_steps_for_sweep": null,
+  "min_lr_ratio": 0.05,
+  "mlm_probability": 0.15,
+  "moco_dim": 128,
+  "moco_k": 65536,
+  "moco_m": 0.999,
+  "moco_t": 0.07,
+  "model_type": "viralbert_for_contrastive_binning",
+  "muon_lr": 0.0015,
+  "muon_max_grad_norm": 1.0,
+  "muon_momentum": 0.95,
+  "muon_weight_decay": 0.05,
+  "norm_layer_type": "rmsnorm",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "num_train_epochs": 3,
+  "num_workers": 4,
+  "optimizer_type": "muon_adamw",
+  "p_codon": 0.5,
+  "pad_token_id": 0,
+  "position_embedding_type": "rope",
+  "resume_from_checkpoint": null,
+  "resume_mode": null,
+  "reverse_complement_prob": 0.5,
+  "rope_interpolation_factor": 1.0,
+  "run_name": "",
+  "save_steps": 10000,
+  "save_total_limit": 5,
+  "scale_loss_for_accumulation": true,
+  "seed": 42,
+  "sep_token_id": 2,
+  "seq_length": 512,
+  "sliding_window_size": 0,
+  "stride": 256,
+  "sweep_early_stopping_patience_steps": 1000,
+  "sweep_early_stopping_threshold": 50.0,
+  "tie_word_embeddings": false,
+  "transformers_version": "4.56.1",
+  "unfreeze_last_n_layers": 6,
+  "use_compile": true,
+  "use_per_group_clipping": false,
+  "use_qk_norm": true,
+  "use_xpos": false,
+  "vocab_size": 14,
+  "wandb_enabled": true,
+  "wandb_group": "",
+  "wandb_name": "",
+  "wandb_notes": "",
+  "wandb_project": "",
+  "wandb_tags": [],
+  "wandb_watch_freq": null,
+  "wandb_watch_model": false,
+  "warmup_steps": 4000,
+  "warmup_steps_ratio": 0.1
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0fa2690f463eb30c2dfc10fc36e0ccb0f135e9064053aac113fb9467c7cd0139
+size 718828232

special_tokens_map.json

@@ -0,0 +1,13 @@
+{
+  "additional_special_tokens": [
+    "[M_S]",
+    "[M_B]",
+    "[M_I]",
+    "[M_E]"
+  ],
+  "cls_token": "[CLS]",
+  "mask_token": "[MASK]",
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "unk_token": "[UNK]"
+}

tokenizer.json

@@ -0,0 +1,33 @@
+{
+  "type": "viralbert",
+  "token_to_id": {
+    "[PAD]": 0,
+    "[CLS]": 1,
+    "[SEP]": 2,
+    "[MASK]": 3,
+    "[UNK]": 4,
+    "A": 5,
+    "C": 6,
+    "G": 7,
+    "T": 8,
+    "N": 9,
+    "[M_S]": 10,
+    "[M_B]": 11,
+    "[M_I]": 12,
+    "[M_E]": 13
+  },
+  "standard_bases": [
+    "A",
+    "C",
+    "G",
+    "T"
+  ],
+  "vocab_size": 14,
+  "special_tokens": {
+    "unk_token": "[UNK]",
+    "sep_token": "[SEP]",
+    "pad_token": "[PAD]",
+    "cls_token": "[CLS]",
+    "mask_token": "[MASK]"
+  }
+}

tokenizer_config.json

@@ -0,0 +1,91 @@
+{
+  "added_tokens_decoder": {
+    "0": {
+      "content": "[PAD]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "[CLS]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "[SEP]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "3": {
+      "content": "[MASK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "4": {
+      "content": "[UNK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "10": {
+      "content": "[M_S]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "11": {
+      "content": "[M_B]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "12": {
+      "content": "[M_I]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "13": {
+      "content": "[M_E]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "additional_special_tokens": [
+    "[M_S]",
+    "[M_B]",
+    "[M_I]",
+    "[M_E]"
+  ],
+  "clean_up_tokenization_spaces": false,
+  "cls_token": "[CLS]",
+  "extra_special_tokens": {},
+  "mask_token": "[MASK]",
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "tokenizer_class": "ViralBERTTokenizer",
+  "unk_token": "[UNK]"
+}