docs: update readme

README.md

@@ -4,48 +4,47 @@ tags:
 - human_genome
 ---
 
-# GENA-LM
+# GENA-LM (BigBird-base T2T)
 
-GENA-LM is a transformer masked language model trained on human DNA sequence.
+GENA-LM (BigBird-base T2T) is a transformer masked language model trained on human DNA sequence. GENA-LM (BigBird-base T2T) follows BigBird architecture.
 
-Differences between GENA-LM and DNABERT:
+Differences between GENA-LM (BigBird-base T2T) and DNABERT:
 - BPE tokenization instead of k-mers;
-- input sequence size is about 3000 nucleotides (512 BPE tokens) compared to 510 nucleotides of DNABERT
+- input sequence size is about 24000 nucleotides (4096 BPE tokens) compared to 510 nucleotides of DNABERT;
 - pre-training on T2T vs. GRCh38.p13 human genome assembly.
 
 Source code and data: https://github.com/AIRI-Institute/GENA_LM
 
 ## Examples
+
+### Load pre-trained model
+```python
+from transformers import AutoTokenizer, BigBirdForMaskedLM
+
+tokenizer = AutoTokenizer.from_pretrained('AIRI-Institute/gena-lm-bigbird-base-t2t')
+model = BigBirdForMaskedLM.from_pretrained('AIRI-Institute/gena-lm-bigbird-base-t2t')
+```
+
+
 ### How to load the model to fine-tune it on classification task
 ```python
-from src.gena_lm.modeling_bert import BertForSequenceClassification
-from transformers import AutoTokenizer
+from transformers import AutoTokenizer, BigBirdForSequenceClassification
 
-tokenizer = AutoTokenizer.from_pretrained('AIRI-Institute/gena-lm-bert-base')
-model = BertForSequenceClassification.from_pretrained('AIRI-Institute/gena-lm-bert-base')
+tokenizer = AutoTokenizer.from_pretrained('AIRI-Institute/gena-lm-bigbird-base-t2t')
+model = BigBirdForSequenceClassification.from_pretrained('AIRI-Institute/gena-lm-bigbird-base-t2t')
 ```
 
 ## Model description
-GENA-LM model is trained in a masked language model (MLM) fashion, following the methods proposed in the BigBird paper by masking 85% of tokens. Model config for `gena-lm-bert-base` is similar to the bert-base:
+GENA-LM (BigBird-base T2T) model is trained in a masked language model (MLM) fashion, following the methods proposed in the BigBird paper by masking 15% of tokens. Model config for `gena-lm-bigbird-base-t2t` is similar to the `google/bigbird-roberta-base`:
 
-- 512 Maximum sequence length
+- 4096 Maximum sequence length
 - 12 Layers, 12 Attention heads
 - 768 Hidden size
-- 32k Vocabulary size
-
-We pre-trained `gena-lm-bert-base` using the latest T2T human genome assembly (https://www.ncbi.nlm.nih.gov/assembly/GCA_009914755.3/). Pre-training was performed for 500,000 iterations with the same parameters as in BigBird, except sequence length was equal to 512 tokens and we used pre-layer normalization in Transformer.
-
-## Downstream tasks
-Currently, gena-lm-bert-base model has been finetuned  and tested on promoter prediction task.  Its' performance is comparable to previous SOTA results. We plan to fine-tune and make available models for other downstream tasks in the near future.
-
-### Fine-tuning GENA-LM on our data and scoring
-After fine-tuning gena-lm-bert-base on promoter prediction dataset, following results were achieved: 
-
-| model                    | seq_len (bp) | F1    |
-|--------------------------|--------------|-------|
-| DeePromoter              | 300          | 95.60 |
-| GENA-LM bert-base (ours) | 2000         | 95.72 |
-| BigBird                  | 16000        | 99.90 |
-
-We can conclude that our model achieves comparable performance to the previously published results for promoter prediction task.
-
+- sparse config:
+    - block size: 64
+    - random blocks: 3
+    - global blocks: 2
+    - sliding window blocks: 3
+- 32k Vocabulary size, tokenizer trained on DNA data.
+
+We pre-trained `gena-lm-bigbird-base-t2t` using the latest T2T human genome assembly (https://www.ncbi.nlm.nih.gov/assembly/GCA_009914755.3/). The data was augmented by sampling SNPs human mutations.  Pre-training was performed for 1,070,000 iterations with batch size 256.