lgq12697
commited on
Commit
•
6ebca88
1
Parent(s):
4b005fa
update model
Browse files- README.md +1 -1
- config.json +52 -1
- model.safetensors +3 -0
- test_metrics.json +0 -1
README.md
CHANGED
@@ -18,7 +18,7 @@ All the models have a comparable model size between 90 MB and 150 MB, BPE tokeni
|
|
18 |
### Model Sources
|
19 |
|
20 |
- **Repository:** [Plant DNA LLMs](https://github.com/zhangtaolab/plant_DNA_LLMs)
|
21 |
-
- **Manuscript:** [
|
22 |
|
23 |
### Architecture
|
24 |
|
|
|
18 |
### Model Sources
|
19 |
|
20 |
- **Repository:** [Plant DNA LLMs](https://github.com/zhangtaolab/plant_DNA_LLMs)
|
21 |
+
- **Manuscript:** [PDLLMs: A group of tailored DNA large language models for analyzing plant genomes]()
|
22 |
|
23 |
### Architecture
|
24 |
|
config.json
CHANGED
@@ -1 +1,52 @@
|
|
1 |
-
{
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "Plant_DNAMamba_2mer_open_chromatin",
|
3 |
+
"architectures": [
|
4 |
+
"MambaForSequenceClassification"
|
5 |
+
],
|
6 |
+
"bos_token_id": 0,
|
7 |
+
"conv_kernel": 4,
|
8 |
+
"d_inner": 1536,
|
9 |
+
"d_model": 768,
|
10 |
+
"eos_token_id": 0,
|
11 |
+
"expand": 2,
|
12 |
+
"fused_add_norm": true,
|
13 |
+
"hidden_act": "silu",
|
14 |
+
"hidden_size": 768,
|
15 |
+
"id2label": {
|
16 |
+
"0": "LABEL_0",
|
17 |
+
"1": "LABEL_1",
|
18 |
+
"2": "LABEL_2"
|
19 |
+
},
|
20 |
+
"initializer_range": 0.1,
|
21 |
+
"intermediate_size": 1536,
|
22 |
+
"label2id": {
|
23 |
+
"LABEL_0": 0,
|
24 |
+
"LABEL_1": 1,
|
25 |
+
"LABEL_2": 2
|
26 |
+
},
|
27 |
+
"layer_norm_epsilon": 1e-05,
|
28 |
+
"model_type": "mamba",
|
29 |
+
"n_layer": 24,
|
30 |
+
"num_hidden_layers": 24,
|
31 |
+
"pad_token_id": 0,
|
32 |
+
"pad_vocab_size_multiple": 8,
|
33 |
+
"problem_type": "single_label_classification",
|
34 |
+
"rescale_prenorm_residual": false,
|
35 |
+
"residual_in_fp32": true,
|
36 |
+
"rms_norm": true,
|
37 |
+
"ssm_cfg": {},
|
38 |
+
"state_size": 16,
|
39 |
+
"time_step_floor": 0.0001,
|
40 |
+
"time_step_init_scheme": "random",
|
41 |
+
"time_step_max": 0.1,
|
42 |
+
"time_step_min": 0.001,
|
43 |
+
"time_step_rank": 48,
|
44 |
+
"time_step_scale": 1.0,
|
45 |
+
"torch_dtype": "float32",
|
46 |
+
"transformers_version": "4.45.0.dev0",
|
47 |
+
"use_bias": false,
|
48 |
+
"use_cache": false,
|
49 |
+
"use_conv_bias": true,
|
50 |
+
"use_mambapy": false,
|
51 |
+
"vocab_size": 27
|
52 |
+
}
|
model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:57a96fe472ddbe887997c08ae132665845fb761d66bca44a12fa1c68cacbfea6
|
3 |
+
size 362199580
|
test_metrics.json
DELETED
@@ -1 +0,0 @@
|
|
1 |
-
{'test_loss': 0.9475768804550171, 'test_precision': 0.605993265993266, 'test_recall': 0.605993265993266, 'test_f1': 0.605993265993266, 'test_matthews_correlation': 0.41036008977337035, 'test_AUROC_ovr': 0.789106890453355, 'test_AUROC_ovo': 0.789106890453355, 'test_runtime': 46.9181, 'test_samples_per_second': 316.509, 'test_steps_per_second': 19.8}
|
|
|
|