masked-sentence-generation

config.json

@@ -1,59 +1,37 @@
 {
-  "_name_or_path": "t5-base",
+  "_name_or_path": "google/flan-t5-large",
   "architectures": [
     "T5ForConditionalGeneration"
   ],
-  "d_ff": 3072,
+  "d_ff": 2816,
   "d_kv": 64,
-  "d_model": 768,
+  "d_model": 1024,
   "decoder_start_token_id": 0,
-  "dense_act_fn": "relu",
+  "dense_act_fn": "gelu_new",
   "dropout_rate": 0.1,
   "eos_token_id": 1,
-  "feed_forward_proj": "relu",
+  "feed_forward_proj": "gated-gelu",
   "initializer_factor": 1.0,
   "is_encoder_decoder": true,
-  "is_gated_act": false,
+  "is_gated_act": true,
   "layer_norm_epsilon": 1e-06,
   "model_type": "t5",
   "n_positions": 512,
-  "num_decoder_layers": 12,
-  "num_heads": 12,
-  "num_layers": 12,
+  "num_decoder_layers": 24,
+  "num_heads": 16,
+  "num_layers": 24,
   "output_past": true,
   "pad_token_id": 0,
+  "quantization_config": {
+    "llm_int8_enable_fp32_cpu_offload": false,
+    "llm_int8_skip_modules": null,
+    "llm_int8_threshold": 6.0,
+    "load_in_8bit": true
+  },
   "relative_attention_max_distance": 128,
   "relative_attention_num_buckets": 32,
-  "task_specific_params": {
-    "summarization": {
-      "early_stopping": true,
-      "length_penalty": 2.0,
-      "max_length": 200,
-      "min_length": 30,
-      "no_repeat_ngram_size": 3,
-      "num_beams": 4,
-      "prefix": "summarize: "
-    },
-    "translation_en_to_de": {
-      "early_stopping": true,
-      "max_length": 300,
-      "num_beams": 4,
-      "prefix": "translate English to German: "
-    },
-    "translation_en_to_fr": {
-      "early_stopping": true,
-      "max_length": 300,
-      "num_beams": 4,
-      "prefix": "translate English to French: "
-    },
-    "translation_en_to_ro": {
-      "early_stopping": true,
-      "max_length": 300,
-      "num_beams": 4,
-      "prefix": "translate English to Romanian: "
-    }
-  },
-  "torch_dtype": "float32",
+  "tie_word_embeddings": false,
+  "torch_dtype": "float16",
   "transformers_version": "4.28.1",
   "use_cache": true,
   "vocab_size": 32128

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:56f3d4c63c39d73a428a55938073a0674e506a244e587a4ac384f1786357b123
-size 891702929
+oid sha256:6e2e65a60a357b044f8254ec72a926c8fa14e4c2237035d39941ac75af52fee4
+size 1266894853

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5524932a2a37f894c5804719a694277f6504c5ae28fd197dc041744bf5be0c13
+oid sha256:6359a27e6dbfa5865af9d08f7773f5504beebc21957ecdb85370ebd03dc60bb4
 size 3707