phueb commited on
Commit
6fa1048
1 Parent(s): 9c4be6e

Update from ph

Browse files
Files changed (4) hide show
  1. README.md +4 -0
  2. config.json +25 -0
  3. pytorch_model.bin +3 -0
  4. tokenizer.json +0 -0
README.md ADDED
@@ -0,0 +1,4 @@
 
 
 
 
 
1
+ ## BabyBERTA
2
+
3
+ BabyBERTA is a slightly-modified and much smaller RoBERTa model trained on 5M words of American-English child-directed input.
4
+ It is intended for language acquisition research, on a single desktop with a single GPU - no high-performance computing infrastructure needed.
config.json ADDED
@@ -0,0 +1,25 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "RobertaForMaskedLM"
4
+ ],
5
+ "attention_probs_dropout_prob": 0.1,
6
+ "bos_token_id": 3,
7
+ "eos_token_id": 4,
8
+ "gradient_checkpointing": false,
9
+ "hidden_act": "gelu",
10
+ "hidden_dropout_prob": 0.1,
11
+ "hidden_size": 256,
12
+ "initializer_range": 0.02,
13
+ "intermediate_size": 1024,
14
+ "layer_norm_eps": 1e-05,
15
+ "max_position_embeddings": 130,
16
+ "model_type": "roberta",
17
+ "num_attention_heads": 8,
18
+ "num_hidden_layers": 8,
19
+ "pad_token_id": 1,
20
+ "position_embedding_type": "absolute",
21
+ "transformers_version": "4.3.3",
22
+ "type_vocab_size": 2,
23
+ "use_cache": true,
24
+ "vocab_size": 8192
25
+ }
pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:70f1cbe5ab289d59e1c6205cd2b754227d04df8e1c7e2ebdd34c6d98487287a6
3
+ size 34154962
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff