Move MLM readme into this repo.
Browse files
README.md
ADDED
@@ -0,0 +1,52 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
tags:
|
3 |
+
- generated_from_trainer
|
4 |
+
model-index:
|
5 |
+
- name: RNAMamba-14M
|
6 |
+
results: []
|
7 |
+
---
|
8 |
+
|
9 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
10 |
+
should probably proofread and complete it, then remove this comment. -->
|
11 |
+
|
12 |
+
# RNAMamba-14M
|
13 |
+
|
14 |
+
This model is a small Mamba based model trained from scratch on 1.96 million sequences (1.56 billion bases) extracted from RNAcentral's active sequences FASTA file for release 24 (March 2024).
|
15 |
+
|
16 |
+
This is intended to be a sequence embedding model for downstream processing of ncRNA sequences.
|
17 |
+
It is trained with a masked language modelling objective, and a context size of 8,192 nucleotides. This particular model has the MLM head stripped off and so should be almost ready to use for embedding.
|
18 |
+
The [dataset](https://huggingface.co/datasets/afg1/rnacentral_subset) has sequences ranging in length from 10 to 8192, so the model should be pretty good at handling sequences in that range.
|
19 |
+
This is a deliberately small model with only 14.1 million parameters (8 hidden layers, hidden dim 512, intermediate size 1024) such that it will run fast without a GPU. We may train something bigger if it looks like these embeddings are not good enough.
|
20 |
+
|
21 |
+
|
22 |
+
<!--## Model description
|
23 |
+
|
24 |
+
More information needed
|
25 |
+
|
26 |
+
## Intended uses & limitations
|
27 |
+
|
28 |
+
More information needed
|
29 |
+
|
30 |
+
## Training and evaluation data
|
31 |
+
|
32 |
+
More information needed
|
33 |
+
|
34 |
+
## Training procedure
|
35 |
+
-->
|
36 |
+
### Training hyperparameters
|
37 |
+
|
38 |
+
The following hyperparameters were used during training:
|
39 |
+
- learning_rate: 2e-05
|
40 |
+
- train_batch_size: 32
|
41 |
+
- eval_batch_size: 8
|
42 |
+
- seed: 42
|
43 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
44 |
+
- lr_scheduler_type: linear
|
45 |
+
- num_epochs: 1.0
|
46 |
+
|
47 |
+
### Framework versions
|
48 |
+
|
49 |
+
- Transformers 4.39.3
|
50 |
+
- Pytorch 2.2.2+cu118
|
51 |
+
- Datasets 2.18.0
|
52 |
+
- Tokenizers 0.15.2
|