afg1 commited on
Commit
c8c74c9
·
verified ·
1 Parent(s): a1d596e

Model save

Browse files
Files changed (3) hide show
  1. README.md +8 -16
  2. model.safetensors +1 -1
  3. training_args.bin +1 -1
README.md CHANGED
@@ -1,28 +1,21 @@
1
  ---
 
 
2
  model-index:
3
  - name: RNAMamba-14M
4
  results: []
5
- license: apache-2.0
6
- datasets:
7
- - afg1/rnacentral_subset
8
- pipeline_tag: fill-mask
9
- inference: false
10
  ---
11
 
 
 
12
 
13
  # RNAMamba-14M
14
 
15
- 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).
16
 
17
- This is intended to be a sequence embedding model for downstream processing of ncRNA sequences.
18
- It is trained with a masked language modelling objective, and a context size of 8,192 nucleotides.
19
- 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.
20
- 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.
21
-
22
-
23
- <!--## Model description
24
- I'll fill this in later...
25
 
 
26
 
27
  ## Intended uses & limitations
28
 
@@ -33,7 +26,6 @@ More information needed
33
  More information needed
34
 
35
  ## Training procedure
36
- -->
37
 
38
  ### Training hyperparameters
39
 
@@ -51,4 +43,4 @@ The following hyperparameters were used during training:
51
  - Transformers 4.39.3
52
  - Pytorch 2.2.2+cu118
53
  - Datasets 2.18.0
54
- - Tokenizers 0.15.2
 
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 fine-tuned version of [](https://huggingface.co/) on an unknown dataset.
15
 
16
+ ## Model description
 
 
 
 
 
 
 
17
 
18
+ More information needed
19
 
20
  ## Intended uses & limitations
21
 
 
26
  More information needed
27
 
28
  ## Training procedure
 
29
 
30
  ### Training hyperparameters
31
 
 
43
  - Transformers 4.39.3
44
  - Pytorch 2.2.2+cu118
45
  - Datasets 2.18.0
46
+ - Tokenizers 0.15.2
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:ad6184c990246aa1ec418cdb4be417990a57c548487463855a2c07fee3de32d1
3
  size 56398500
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a238e0813bbfb570b18ff89c92cd63f03935cbb8c9282a250c533df673dca66d
3
  size 56398500
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:761a44663ae5eeea6c7af0dd949641cb77ee38b0a5cde871ed4a6fa638def7f5
3
  size 4920
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d62db5204d4bd6d9c7f84466a6ad35588667099a445a3b5d547f96a5373c5955
3
  size 4920