hf-transformers-bot commited on
Commit
ed58edf
·
1 Parent(s): b22e56c

Upload tiny models for BioGptForCausalLM

Browse files
config.json ADDED
@@ -0,0 +1,28 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "activation_dropout": 0.0,
3
+ "architectures": [
4
+ "BioGptForCausalLM"
5
+ ],
6
+ "attention_probs_dropout_prob": 0.1,
7
+ "bos_token_id": 0,
8
+ "eos_token_id": 2,
9
+ "hidden_act": "gelu",
10
+ "hidden_dropout_prob": 0.1,
11
+ "hidden_size": 32,
12
+ "initializer_range": 0.02,
13
+ "intermediate_size": 37,
14
+ "is_decoder": true,
15
+ "layer_norm_eps": 1e-12,
16
+ "layerdrop": 0.0,
17
+ "max_position_embeddings": 512,
18
+ "model_type": "biogpt",
19
+ "num_attention_heads": 4,
20
+ "num_hidden_layers": 5,
21
+ "pad_token_id": 1,
22
+ "scale_embedding": true,
23
+ "torch_dtype": "float32",
24
+ "transformers_version": "4.28.0.dev0",
25
+ "type_vocab_size": 16,
26
+ "use_cache": true,
27
+ "vocab_size": 42384
28
+ }
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": "4.28.0.dev0"
7
+ }
merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4679c805f44086d7e5179a1881ced0b32452ee7d7f0fc188a0c858dc528bfb23
3
+ size 5653037
special_tokens_map.json ADDED
@@ -0,0 +1,7 @@
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": "<s>",
3
+ "eos_token": "</s>",
4
+ "pad_token": "<pad>",
5
+ "sep_token": "</s>",
6
+ "unk_token": "<unk>"
7
+ }
tokenizer_config.json ADDED
@@ -0,0 +1,11 @@
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": "<s>",
3
+ "clean_up_tokenization_spaces": true,
4
+ "eos_token": "</s>",
5
+ "model_max_length": 512,
6
+ "pad_token": "<pad>",
7
+ "sep_token": "</s>",
8
+ "special_tokens_map_file": null,
9
+ "tokenizer_class": "BioGptTokenizer",
10
+ "unk_token": "<unk>"
11
+ }
vocab.json ADDED
The diff for this file is too large to render. See raw diff