Update from ph

README.md

@@ -0,0 +1,4 @@
+## BabyBERTA
+
+BabyBERTA is a slightly-modified and much smaller RoBERTa model trained on 5M words of American-English child-directed input.
+It is intended for language acquisition research, on a single desktop with a single GPU - no high-performance computing infrastructure needed. 

config.json

@@ -0,0 +1,25 @@
+{
+  "architectures": [
+    "RobertaForMaskedLM"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "bos_token_id": 3,
+  "eos_token_id": 4,
+  "gradient_checkpointing": false,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 256,
+  "initializer_range": 0.02,
+  "intermediate_size": 1024,
+  "layer_norm_eps": 1e-05,
+  "max_position_embeddings": 130,
+  "model_type": "roberta",
+  "num_attention_heads": 8,
+  "num_hidden_layers": 8,
+  "pad_token_id": 1,
+  "position_embedding_type": "absolute",
+  "transformers_version": "4.3.3",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 8192
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:70f1cbe5ab289d59e1c6205cd2b754227d04df8e1c7e2ebdd34c6d98487287a6
+size 34154962