lgq12697 commited on
Commit
8b400bc
·
1 Parent(s): 5928db6

update model

Browse files
Files changed (4) hide show
  1. config.json +42 -1
  2. model.safetensors +3 -0
  3. tokenizer.json +25 -4
  4. tokenizer_config.json +2 -0
config.json CHANGED
@@ -1 +1,42 @@
1
- {"d_model": 768, "n_layer": 24, "vocab_size": 8000, "ssm_cfg": {}, "rms_norm": true, "residual_in_fp32": true, "fused_add_norm": true, "pad_vocab_size_multiple": 8, "tie_embeddings": true}
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "Plant_DNAMamba_BPE_H3K27me3",
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
+ "initializer_range": 0.1,
16
+ "intermediate_size": 1536,
17
+ "layer_norm_epsilon": 1e-05,
18
+ "model_type": "mamba",
19
+ "n_layer": 24,
20
+ "num_hidden_layers": 24,
21
+ "pad_token_id": 0,
22
+ "pad_vocab_size_multiple": 8,
23
+ "problem_type": "single_label_classification",
24
+ "rescale_prenorm_residual": false,
25
+ "residual_in_fp32": true,
26
+ "rms_norm": true,
27
+ "ssm_cfg": {},
28
+ "state_size": 16,
29
+ "time_step_floor": 0.0001,
30
+ "time_step_init_scheme": "random",
31
+ "time_step_max": 0.1,
32
+ "time_step_min": 0.001,
33
+ "time_step_rank": 48,
34
+ "time_step_scale": 1.0,
35
+ "torch_dtype": "float32",
36
+ "transformers_version": "4.45.0.dev0",
37
+ "use_bias": false,
38
+ "use_cache": false,
39
+ "use_conv_bias": true,
40
+ "use_mambapy": false,
41
+ "vocab_size": 8000
42
+ }
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5c9bba99797274a63da85f1d7751d0459e3b7e59cc2d9e5484881e7fd87904bb
3
+ size 386689624
tokenizer.json CHANGED
@@ -46,10 +46,30 @@
46
  "use_regex": true
47
  },
48
  "post_processor": {
49
- "type": "ByteLevel",
50
- "add_prefix_space": false,
51
- "trim_offsets": true,
52
- "use_regex": true
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
53
  },
54
  "decoder": {
55
  "type": "ByteLevel",
@@ -65,6 +85,7 @@
65
  "end_of_word_suffix": null,
66
  "fuse_unk": false,
67
  "byte_fallback": false,
 
68
  "vocab": {
69
  "<|endoftext|>": 0,
70
  "<|padding|>": 1,
 
46
  "use_regex": true
47
  },
48
  "post_processor": {
49
+ "type": "TemplateProcessing",
50
+ "single": [
51
+ {
52
+ "Sequence": {
53
+ "id": "A",
54
+ "type_id": 0
55
+ }
56
+ }
57
+ ],
58
+ "pair": [
59
+ {
60
+ "Sequence": {
61
+ "id": "A",
62
+ "type_id": 0
63
+ }
64
+ },
65
+ {
66
+ "Sequence": {
67
+ "id": "B",
68
+ "type_id": 1
69
+ }
70
+ }
71
+ ],
72
+ "special_tokens": {}
73
  },
74
  "decoder": {
75
  "type": "ByteLevel",
 
85
  "end_of_word_suffix": null,
86
  "fuse_unk": false,
87
  "byte_fallback": false,
88
+ "ignore_merges": false,
89
  "vocab": {
90
  "<|endoftext|>": 0,
91
  "<|padding|>": 1,
tokenizer_config.json CHANGED
@@ -1,4 +1,6 @@
1
  {
 
 
2
  "add_prefix_space": false,
3
  "added_tokens_decoder": {
4
  "0": {
 
1
  {
2
+ "add_bos_token": false,
3
+ "add_eos_token": false,
4
  "add_prefix_space": false,
5
  "added_tokens_decoder": {
6
  "0": {