add base model

config.json

@@ -0,0 +1,36 @@
+{
+  "_name_or_path": "pszemraj/grammar-synthesis-small-WIP",
+  "architectures": [
+    "T5ForConditionalGeneration"
+  ],
+  "d_ff": 1024,
+  "d_kv": 64,
+  "d_model": 512,
+  "decoder_start_token_id": 0,
+  "dense_act_fn": "gelu_new",
+  "dropout_rate": 0.1,
+  "early_stopping": true,
+  "eos_token_id": 1,
+  "feed_forward_proj": "gated-gelu",
+  "initializer_factor": 1.0,
+  "is_encoder_decoder": true,
+  "is_gated_act": true,
+  "layer_norm_epsilon": 1e-06,
+  "max_length": 512,
+  "min_length": 8,
+  "model_type": "t5",
+  "no_repeat_ngram_size": 4,
+  "num_beams": 2,
+  "num_decoder_layers": 8,
+  "num_heads": 6,
+  "num_layers": 8,
+  "output_past": true,
+  "pad_token_id": 0,
+  "relative_attention_max_distance": 128,
+  "relative_attention_num_buckets": 32,
+  "tie_word_embeddings": false,
+  "torch_dtype": "float32",
+  "transformers_version": "4.20.1",
+  "use_cache": false,
+  "vocab_size": 32128
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:34fe1a08a3fee9281998bcda50786c3204e87f86e462d3306ed58949a3a0cd1c
+size 307871851

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1a2fb1c2d8e00e8ab84642e74fb6a8be3a56cd4bec08a18d225c629ed406a17c
+size 4527