Upload Model

model/config.json

@@ -0,0 +1,37 @@
+{
+  "_name_or_path": "pszemraj/flan-t5-large-grammar-synthesis",
+  "architectures": [
+    "T5ForConditionalGeneration"
+  ],
+  "classifier_dropout": 0.0,
+  "d_ff": 2816,
+  "d_kv": 64,
+  "d_model": 1024,
+  "decoder_start_token_id": 0,
+  "dense_act_fn": "gelu",
+  "dropout_rate": 0.1,
+  "eos_token_id": 1,
+  "feed_forward_proj": "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",
+  "n_positions": 512,
+  "no_repeat_ngram_size": 4,
+  "num_beams": 2,
+  "num_decoder_layers": 24,
+  "num_heads": 16,
+  "num_layers": 24,
+  "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": "4.41.2",
+  "use_cache": true,
+  "vocab_size": 32128
+}

model/generation_config.json

@@ -0,0 +1,11 @@
+{
+  "_from_model_config": true,
+  "decoder_start_token_id": 0,
+  "eos_token_id": 1,
+  "max_length": 512,
+  "min_length": 8,
+  "no_repeat_ngram_size": 4,
+  "num_beams": 2,
+  "pad_token_id": 0,
+  "transformers_version": "4.41.2"
+}

model/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:eb2a429f3af36ee5d91f13966cf62dbb650f88e3fec023eb6d0c05e7500f0130
+size 3132668808