Jingjing Zhai
commited on
Commit
•
ab83746
1
Parent(s):
6f1841a
PlantCaduceus_l32
Browse files- config.json +57 -0
- pytorch_model.bin +3 -0
- special_tokens_map.json +23 -0
- tokenizer.json +61 -0
- tokenizer_config.json +34 -0
config.json
ADDED
@@ -0,0 +1,57 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "yairschiff/caduceus_base",
|
3 |
+
"architectures": [
|
4 |
+
"Caduceus"
|
5 |
+
],
|
6 |
+
"auto_map": {
|
7 |
+
"AutoConfig": "yairschiff/caduceus_base--configuration_caduceus.CaduceusConfig",
|
8 |
+
"AutoModel": "yairschiff/caduceus_base--modeling_caduceus.Caduceus",
|
9 |
+
"AutoModelForMaskedLM": "yairschiff/caduceus_base--modeling_caduceus.CaduceusForMaskedLM",
|
10 |
+
"AutoModelForSequenceClassification": "yairschiff/caduceus_base--modeling_caduceus.CaduceusForSequenceClassification"
|
11 |
+
},
|
12 |
+
"bidirectional": true,
|
13 |
+
"bidirectional_strategy": "add",
|
14 |
+
"bidirectional_weight_tie": true,
|
15 |
+
"complement_map": {
|
16 |
+
"0": 0,
|
17 |
+
"1": 1,
|
18 |
+
"2": 2,
|
19 |
+
"3": 6,
|
20 |
+
"4": 5,
|
21 |
+
"5": 4,
|
22 |
+
"6": 3,
|
23 |
+
"7": 7
|
24 |
+
},
|
25 |
+
"d_model": 1024,
|
26 |
+
"fused_add_norm": true,
|
27 |
+
"initializer_cfg": {
|
28 |
+
"initializer_range": 0.02,
|
29 |
+
"n_residuals_per_layer": 1,
|
30 |
+
"rescale_prenorm_residual": true
|
31 |
+
},
|
32 |
+
"model_type": "caduceus",
|
33 |
+
"n_layer": 32,
|
34 |
+
"norm_epsilon": 1e-05,
|
35 |
+
"pad_token_id": -100,
|
36 |
+
"pad_vocab_size_multiple": 8,
|
37 |
+
"rcps": true,
|
38 |
+
"residual_in_fp32": true,
|
39 |
+
"rms_norm": true,
|
40 |
+
"ssm_cfg": {
|
41 |
+
"bias": false,
|
42 |
+
"conv_bias": true,
|
43 |
+
"d_conv": 4,
|
44 |
+
"d_state": 16,
|
45 |
+
"dt_init": "random",
|
46 |
+
"dt_init_floor": 0.0001,
|
47 |
+
"dt_max": 0.1,
|
48 |
+
"dt_min": 0.001,
|
49 |
+
"dt_rank": "auto",
|
50 |
+
"dt_scale": 1.0,
|
51 |
+
"expand": 2,
|
52 |
+
"use_fast_path": true
|
53 |
+
},
|
54 |
+
"torch_dtype": "float32",
|
55 |
+
"transformers_version": "4.37.2",
|
56 |
+
"vocab_size": 8
|
57 |
+
}
|
pytorch_model.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:308d9125a0e2a350252c902c27c308bbcf56a1d8198f399f9e7c26d9b552ec10
|
3 |
+
size 901671450
|
special_tokens_map.json
ADDED
@@ -0,0 +1,23 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"mask_token": {
|
3 |
+
"content": "[MASK]",
|
4 |
+
"lstrip": false,
|
5 |
+
"normalized": false,
|
6 |
+
"rstrip": false,
|
7 |
+
"single_word": false
|
8 |
+
},
|
9 |
+
"pad_token": {
|
10 |
+
"content": "[PAD]",
|
11 |
+
"lstrip": false,
|
12 |
+
"normalized": false,
|
13 |
+
"rstrip": false,
|
14 |
+
"single_word": false
|
15 |
+
},
|
16 |
+
"unk_token": {
|
17 |
+
"content": "[UNK]",
|
18 |
+
"lstrip": false,
|
19 |
+
"normalized": false,
|
20 |
+
"rstrip": false,
|
21 |
+
"single_word": false
|
22 |
+
}
|
23 |
+
}
|
tokenizer.json
ADDED
@@ -0,0 +1,61 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"version": "1.0",
|
3 |
+
"truncation": null,
|
4 |
+
"padding": null,
|
5 |
+
"added_tokens": [
|
6 |
+
{
|
7 |
+
"id": 0,
|
8 |
+
"content": "[PAD]",
|
9 |
+
"single_word": false,
|
10 |
+
"lstrip": false,
|
11 |
+
"rstrip": false,
|
12 |
+
"normalized": false,
|
13 |
+
"special": true
|
14 |
+
},
|
15 |
+
{
|
16 |
+
"id": 1,
|
17 |
+
"content": "[MASK]",
|
18 |
+
"single_word": false,
|
19 |
+
"lstrip": false,
|
20 |
+
"rstrip": false,
|
21 |
+
"normalized": false,
|
22 |
+
"special": true
|
23 |
+
},
|
24 |
+
{
|
25 |
+
"id": 2,
|
26 |
+
"content": "[UNK]",
|
27 |
+
"single_word": false,
|
28 |
+
"lstrip": false,
|
29 |
+
"rstrip": false,
|
30 |
+
"normalized": false,
|
31 |
+
"special": true
|
32 |
+
}
|
33 |
+
],
|
34 |
+
"normalizer": {
|
35 |
+
"type": "Lowercase"
|
36 |
+
},
|
37 |
+
"pre_tokenizer": {
|
38 |
+
"type": "Whitespace"
|
39 |
+
},
|
40 |
+
"post_processor": null,
|
41 |
+
"decoder": null,
|
42 |
+
"model": {
|
43 |
+
"type": "BPE",
|
44 |
+
"dropout": null,
|
45 |
+
"unk_token": "[UNK]",
|
46 |
+
"continuing_subword_prefix": null,
|
47 |
+
"end_of_word_suffix": null,
|
48 |
+
"fuse_unk": false,
|
49 |
+
"byte_fallback": false,
|
50 |
+
"vocab": {
|
51 |
+
"[PAD]": 0,
|
52 |
+
"[MASK]": 1,
|
53 |
+
"[UNK]": 2,
|
54 |
+
"a": 3,
|
55 |
+
"c": 4,
|
56 |
+
"g": 5,
|
57 |
+
"t": 6
|
58 |
+
},
|
59 |
+
"merges": []
|
60 |
+
}
|
61 |
+
}
|
tokenizer_config.json
ADDED
@@ -0,0 +1,34 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"added_tokens_decoder": {
|
3 |
+
"0": {
|
4 |
+
"content": "[PAD]",
|
5 |
+
"lstrip": false,
|
6 |
+
"normalized": false,
|
7 |
+
"rstrip": false,
|
8 |
+
"single_word": false,
|
9 |
+
"special": true
|
10 |
+
},
|
11 |
+
"1": {
|
12 |
+
"content": "[MASK]",
|
13 |
+
"lstrip": false,
|
14 |
+
"normalized": false,
|
15 |
+
"rstrip": false,
|
16 |
+
"single_word": false,
|
17 |
+
"special": true
|
18 |
+
},
|
19 |
+
"2": {
|
20 |
+
"content": "[UNK]",
|
21 |
+
"lstrip": false,
|
22 |
+
"normalized": false,
|
23 |
+
"rstrip": false,
|
24 |
+
"single_word": false,
|
25 |
+
"special": true
|
26 |
+
}
|
27 |
+
},
|
28 |
+
"clean_up_tokenization_spaces": true,
|
29 |
+
"mask_token": "[MASK]",
|
30 |
+
"model_max_length": 1000000000000000019884624838656,
|
31 |
+
"pad_token": "[PAD]",
|
32 |
+
"tokenizer_class": "PreTrainedTokenizerFast",
|
33 |
+
"unk_token": "[UNK]"
|
34 |
+
}
|