Development Build

Commits

• d549ad4: fix inplace modification error in rare cases (Zhiyuan Chen)
• 9536254: improve dataset saving (Zhiyuan Chen)
• eef18ef: add RYOS dataset (Zhiyuan Chen)
• bc7cede: add EternaBench dataset (Zhiyuan Chen)

v0.0.5

Commits

• c776a5d: add citation (Zhiyuan Chen)
• e02c90e: fix output type of rna ernie (Zhiyuan Chen)
• d7120dc: fix criterion when labels is NestedTensor (Zhiyuan Chen)
• 047faa8: Tokenizers won't add special token if passed None (Zhiyuan Chen)
• 6c15493: fix docs format (Zhiyuan Chen)
• bf820cd: update conversion_utils (Zhiyuan Chen)
• 10741ba: prediction heads accept NestedTensor as input_ids (Zhiyuan Chen)
• 0acee22: add DotBracketTokenizer (Zhiyuan Chen)
• 2150c76: add data (Zhiyuan Chen)
• 8d138a9: add datasets (Zhiyuan Chen)
• 2d070e0: add badges to readme (Zhiyuan Chen)

v0.0.4

Commits

• b28bfe5: improve code quality (Zhiyuan Chen)
• 8ed0f1a: add modules.RotaryEmbedding (Zhiyuan Chen)
• bf1f65e: make RnaBert supports gradient checkpoint (Zhiyuan Chen)
• 561be58: make RnaMsm supports gradient checkpoint (Zhiyuan Chen)
• 1ded797: expose token_ids in PretrainedConfig (Zhiyuan Chen)
• a5031b4: rename Pretrain -> PreTrain for consistency (Zhiyuan Chen)
• 81c8936: fix type hints (Zhiyuan Chen)
• 25a443a: support count_parameters (Zhiyuan Chen)
• c632a77: add README (Zhiyuan Chen)
• 1c9514b: register models to AutoBackbone (Zhiyuan Chen)
• b48af26: fix token is not recognised (Zhiyuan Chen)
• fef7fcb: add README of RNA-FM (Zhiyuan Chen)
• a483660: add README of RNABERT (Zhiyuan Chen)
• 881a7d0: add README of RNA-MSM (Zhiyuan Chen)
• 59ee118: add README of SpliceBERT (Zhiyuan Chen)
• 7554a94: add README of 3UTRBERT (Zhiyuan Chen)
• 5ee24bd: add README of UTR-LM (Zhiyuan Chen)
• 2bddca3: add document site (Zhiyuan Chen)
• 47b8a96: improve tokenizer design (Zhiyuan Chen)
• 0ace669: add mrna-fm (Zhiyuan Chen)
• 1dd1e65: fix lm_head weight (Zhiyuan Chen)
• 7ea36b9: improve docs (Zhiyuan Chen)
• cc288bd: add dna and protein tokenizer (Zhiyuan Chen)
• c9bc441: add sinusoidal position embedding (Zhiyuan Chen)
• 1b81880: add CaLm (Zhiyuan Chen)
• d85c4bb: add Inosine token in RNA vocab (Zhiyuan Chen)
• 303e8a3: add RiNALMo (Zhiyuan Chen)
• d19bd2a: add ERNIE-RNA (Zhiyuan Chen)
• f7d3ab5: remove downstream (Zhiyuan Chen)
• 4915e6f: rename Classification to Prediction (Zhiyuan Chen)
• fed720d: add corresponding AutoModelForPrediction (Zhiyuan Chen)
• 4b716ce: add modeling_output (Zhiyuan Chen)
• 52eed9f: improve doctest (Zhiyuan Chen)
• 2718a32: fix ContactPredictionHead (Zhiyuan Chen)
• ffa0213: rewrite RnaBertForPreTraining (Zhiyuan Chen)
• e18cf00: rewrite RnaFmForPretraining (Zhiyuan Chen)
• 9fedd52: rewrite RnaMsmForPretraining (Zhiyuan Chen)
• 8fb3ad4: rewrite UtrLmForPretraining (Zhiyuan Chen)
• 74f283a: improve SpliceBert & UtrBert for pretraining (Zhiyuan Chen)
• ac76344: add contact prediction models (Zhiyuan Chen)
• 369513c: add module docment (Zhiyuan Chen)
• 61c5687: improve head design (Zhiyuan Chen)
• 650edb8: update models doc (Zhiyuan Chen)
• e180f39: improve Tokenizer design (Zhiyuan Chen)
• 6fa7283: add RNAErnie (Zhiyuan Chen)
• 5a08afe: clean up docs and utils (Zhiyuan Chen)
• 0ef34df: add model widgets (Zhiyuan Chen)

v0.0.3

Commits

• d99eeb5: run tests before publishing (Zhiyuan Chen)
• 89d52ae: fix rotary embedding in UtrLm and RnaFm (Zhiyuan Chen)
• 461ba05: fix attention mask of RnaMsm (Zhiyuan Chen)
• 3fcb921: fix head for utrlm and utrbert (Zhiyuan Chen)
• 2968292: unify classification head (Zhiyuan Chen)
• 9f8b2a7: rename Outputs of RnaMsm (Zhiyuan Chen)
• bde2098: add support of CrisprOffTarget tasks (Zhiyuan Chen)
• 83572c7: set default value of head in code (Zhiyuan Chen)
• 3747c05: improve token initialisation (Zhiyuan Chen)
• 9a41985: support delete_existing in convert_checkpoint (Zhiyuan Chen)
• 8011687: ensure pooler consistency (Zhiyuan Chen)
• 57039f7: rename tokenizers -> tokenisers to avoid conflicts (Zhiyuan Chen)
• e06fb22: relax the input_ids in ContactPredictionHead (Zhiyuan Chen)
• e2702d3: use strameline vocab by default if nmers > 1 (Zhiyuan Chen)
• 4b1cd97: add KMerTokenHead (Zhiyuan Chen)
• 3f9ec11: add head for nucleotide-level tasks (Zhiyuan Chen)
• 91b0201: add support of Nucleotide level tasks (Zhiyuan Chen)
• 449b56e: pytest now fails under 50 (Zhiyuan Chen)
• cb98098: set default transform_act to gelu (Zhiyuan Chen)
• 8e31573: fix type hints (Zhiyuan Chen)
• f74b91f: inspect if input_ids is NestedTensor (Zhiyuan Chen)
• 4ff51f9: ignore convert_checkpoint.py in testing (Zhiyuan Chen)
• c7cebc7: unify typehints (Zhiyuan Chen)
• 6c53582: unify criterion & build criterion into head (Zhiyuan Chen)
• f8c825b: make multimolecule.module for shared modulet diff develop (Zhiyuan Chen)
• 5dfc33c: fix token & nucleodite head (Zhiyuan Chen)
• b0c2b63: use mcrmse for multi regression tasks (Zhiyuan Chen)
• ce325f0: allow additional kwargs in Nucleotide-level tasks (Zhiyuan Chen)
• b61796b: add AutoModelForNucleotideClassification & AutoModelForCrisprOffTarget (Zhiyuan Chen)
• b981919: set model_max_length in covert_checkpoint (Zhiyuan Chen)
• 0c850cb: fix rnamsm output (Zhiyuan Chen)
• c229a7d: add copyright header (Zhiyuan Chen)
• c47578c: fix head config (Zhiyuan Chen)
• 6856ad8: fix model_max_length of RnaFm Tokenizer (Zhiyuan Chen)

v0.0.2

Commits

• 0f62c93: fix imports (Zhiyuan Chen)
• 573deee: update gitignore (Zhiyuan Chen)
• cd27502: improve RnaTokenizer (Zhiyuan Chen)
• 2bea376: rewrite heads (Zhiyuan Chen)
• 5fd3353: support kmer in tokenizer (Zhiyuan Chen)
• 9c96615: reorganise rnabert (Zhiyuan Chen)
• 061a554: add support of RnaMsm (Zhiyuan Chen)
• 0273c7b: add support of SpliceBert (Zhiyuan Chen)
• d831fbd: add support of RnaFm (Zhiyuan Chen)
• 5b22b8e: add support of UtrLm (Zhiyuan Chen)
• 3ff3d2f: add support of 3UTR-BERT (Zhiyuan Chen)
• ce31a79: add strameline vocab to avoid excessive mem in kmer (Zhiyuan Chen)

v0.0.1

Commits

• 3188088: Unify RNA Tokenizer (Zhiyuan Chen)

v0.0.0

Supports RNABERT

Signed-off-by: Zhiyuan Chen <[email protected]>