Hugging Face's logo

Saeed
/
TissueGPT

Text Generation
Safetensors
English
biogpt
biomedical
BioGPT
fine-tuning
Model card Files
xet
Community
Saeed commited on
Commit
9379127
·
1 Parent(s): 18a136c

new TissueGPT model

Browse files
Files changed (7) hide show
  1. config.json +27 -27
  2. generation_config.json +7 -0
  3. merges.txt +0 -0
  4. model.safetensors +1 -1
  5. special_tokens_map.json +37 -7
  6. tokenizer_config.json +44 -44
  7. vocab.json +0 -0
config.json CHANGED
@@ -1,27 +1,27 @@
1
- {
2
- "_name_or_path": "microsoft/BioGPT",
3
- "activation_dropout": 0.0,
4
- "architectures": [
5
- "BioGptForCausalLM"
6
- ],
7
- "attention_probs_dropout_prob": 0.1,
8
- "bos_token_id": 0,
9
- "eos_token_id": 2,
10
- "hidden_act": "gelu",
11
- "hidden_dropout_prob": 0.1,
12
- "hidden_size": 1024,
13
- "initializer_range": 0.02,
14
- "intermediate_size": 4096,
15
- "layer_norm_eps": 1e-12,
16
- "layerdrop": 0.0,
17
- "max_position_embeddings": 1024,
18
- "model_type": "biogpt",
19
- "num_attention_heads": 16,
20
- "num_hidden_layers": 24,
21
- "pad_token_id": 1,
22
- "scale_embedding": true,
23
- "torch_dtype": "float32",
24
- "transformers_version": "4.46.1",
25
- "use_cache": true,
26
- "vocab_size": 42384
27
- }
 
1
+ {
2
+ "_name_or_path": "./biogpt_finetuned",
3
+ "activation_dropout": 0.0,
4
+ "architectures": [
5
+ "BioGptForCausalLM"
6
+ ],
7
+ "attention_probs_dropout_prob": 0.1,
8
+ "bos_token_id": 0,
9
+ "eos_token_id": 2,
10
+ "hidden_act": "gelu",
11
+ "hidden_dropout_prob": 0.1,
12
+ "hidden_size": 1024,
13
+ "initializer_range": 0.02,
14
+ "intermediate_size": 4096,
15
+ "layer_norm_eps": 1e-12,
16
+ "layerdrop": 0.0,
17
+ "max_position_embeddings": 1024,
18
+ "model_type": "biogpt",
19
+ "num_attention_heads": 16,
20
+ "num_hidden_layers": 24,
21
+ "pad_token_id": 1,
22
+ "scale_embedding": true,
23
+ "torch_dtype": "float32",
24
+ "transformers_version": "4.46.1",
25
+ "use_cache": true,
26
+ "vocab_size": 42384
27
+ }
generation_config.json ADDED
@@ -0,0 +1,7 @@
 
 
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "bos_token_id": 0,
4
+ "eos_token_id": 2,
5
+ "pad_token_id": 1,
6
+ "transformers_version": "4.46.1"
7
+ }
merges.txt CHANGED
The diff for this file is too large to render. See raw diff
 
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:d3e474ce8b1a6d05ec72997fe6ed9739e1cf75c93bb2020175fe5223da217015
3
  size 1387095576
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4430f32416b64f68bdc73e3ddbadf7b3dc2f9760f71e5308ee9a652da09b1752
3
  size 1387095576
special_tokens_map.json CHANGED
@@ -1,7 +1,37 @@
1
- {
2
- "bos_token": "<s>",
3
- "eos_token": "</s>",
4
- "pad_token": "<pad>",
5
- "sep_token": "</s>",
6
- "unk_token": "<unk>"
7
- }
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": {
3
+ "content": "<s>",
4
+ "lstrip": false,
5
+ "normalized": false,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "eos_token": {
10
+ "content": "</s>",
11
+ "lstrip": false,
12
+ "normalized": false,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "pad_token": {
17
+ "content": "<pad>",
18
+ "lstrip": false,
19
+ "normalized": false,
20
+ "rstrip": false,
21
+ "single_word": false
22
+ },
23
+ "sep_token": {
24
+ "content": "</s>",
25
+ "lstrip": false,
26
+ "normalized": false,
27
+ "rstrip": false,
28
+ "single_word": false
29
+ },
30
+ "unk_token": {
31
+ "content": "<unk>",
32
+ "lstrip": false,
33
+ "normalized": false,
34
+ "rstrip": false,
35
+ "single_word": false
36
+ }
37
+ }
tokenizer_config.json CHANGED
@@ -1,44 +1,44 @@
1
- {
2
- "added_tokens_decoder": {
3
- "0": {
4
- "content": "<s>",
5
- "lstrip": false,
6
- "normalized": false,
7
- "rstrip": false,
8
- "single_word": false,
9
- "special": true
10
- },
11
- "1": {
12
- "content": "<pad>",
13
- "lstrip": false,
14
- "normalized": false,
15
- "rstrip": false,
16
- "single_word": false,
17
- "special": true
18
- },
19
- "2": {
20
- "content": "</s>",
21
- "lstrip": false,
22
- "normalized": false,
23
- "rstrip": false,
24
- "single_word": false,
25
- "special": true
26
- },
27
- "3": {
28
- "content": "<unk>",
29
- "lstrip": false,
30
- "normalized": false,
31
- "rstrip": false,
32
- "single_word": false,
33
- "special": true
34
- }
35
- },
36
- "bos_token": "<s>",
37
- "clean_up_tokenization_spaces": false,
38
- "eos_token": "</s>",
39
- "model_max_length": 1000000000000000019884624838656,
40
- "pad_token": "<pad>",
41
- "sep_token": "</s>",
42
- "tokenizer_class": "BioGptTokenizer",
43
- "unk_token": "<unk>"
44
- }
 
1
+ {
2
+ "added_tokens_decoder": {
3
+ "0": {
4
+ "content": "<s>",
5
+ "lstrip": false,
6
+ "normalized": false,
7
+ "rstrip": false,
8
+ "single_word": false,
9
+ "special": true
10
+ },
11
+ "1": {
12
+ "content": "<pad>",
13
+ "lstrip": false,
14
+ "normalized": false,
15
+ "rstrip": false,
16
+ "single_word": false,
17
+ "special": true
18
+ },
19
+ "2": {
20
+ "content": "</s>",
21
+ "lstrip": false,
22
+ "normalized": false,
23
+ "rstrip": false,
24
+ "single_word": false,
25
+ "special": true
26
+ },
27
+ "3": {
28
+ "content": "<unk>",
29
+ "lstrip": false,
30
+ "normalized": false,
31
+ "rstrip": false,
32
+ "single_word": false,
33
+ "special": true
34
+ }
35
+ },
36
+ "bos_token": "<s>",
37
+ "clean_up_tokenization_spaces": false,
38
+ "eos_token": "</s>",
39
+ "model_max_length": 1000000000000000019884624838656,
40
+ "pad_token": "<pad>",
41
+ "sep_token": "</s>",
42
+ "tokenizer_class": "BioGptTokenizer",
43
+ "unk_token": "<unk>"
44
+ }
vocab.json CHANGED
The diff for this file is too large to render. See raw diff