Upload LongT5ForConditionalGeneration

README.md

@@ -1,6 +1,7 @@
 ---
 library_name: transformers
-tags: []
+tags:
+- Summarization
 ---
 
 # Model Card for Model ID

config.json

@@ -1,44 +1,44 @@
-{
-  "_name_or_path": "./models/pszemraj/long-t5-tglobal-base-16384-book-summary-fine-tuned-v0",
-  "architectures": [
-    "LongT5ForConditionalGeneration"
-  ],
-  "d_ff": 2048,
-  "d_kv": 64,
-  "d_model": 768,
-  "decoder_start_token_id": 0,
-  "dense_act_fn": "gelu_new",
-  "dropout_rate": 0.1,
-  "early_stopping": true,
-  "encoder_attention_type": "transient-global",
-  "encoder_no_repeat_ngram_size": 4,
-  "eos_token_id": 1,
-  "feed_forward_proj": "gated-gelu",
-  "global_block_size": 16,
-  "initializer_factor": 1.0,
-  "is_encoder_decoder": true,
-  "is_gated_act": true,
-  "layer_norm_epsilon": 1e-06,
-  "length_penalty": 0.8,
-  "local_radius": 127,
-  "max_length": 512,
-  "max_position_embeddings": 4096,
-  "min_length": 8,
-  "model_type": "longt5",
-  "n_positions": 4096,
-  "no_repeat_ngram_size": 3,
-  "num_beams": 2,
-  "num_decoder_layers": 12,
-  "num_heads": 12,
-  "num_layers": 12,
-  "output_past": true,
-  "pad_token_id": 0,
-  "relative_attention_max_distance": 128,
-  "relative_attention_num_buckets": 32,
-  "repetition_penalty": 3.5,
-  "tie_word_embeddings": false,
-  "torch_dtype": "float32",
-  "transformers_version": "4.39.1",
-  "use_cache": false,
-  "vocab_size": 32128
-}
+{
+  "_name_or_path": "theekshana/long-t5-tglobal-16k-annual-reports-v0",
+  "architectures": [
+    "LongT5ForConditionalGeneration"
+  ],
+  "d_ff": 2048,
+  "d_kv": 64,
+  "d_model": 768,
+  "decoder_start_token_id": 0,
+  "dense_act_fn": "gelu_new",
+  "dropout_rate": 0.1,
+  "early_stopping": true,
+  "encoder_attention_type": "transient-global",
+  "encoder_no_repeat_ngram_size": 4,
+  "eos_token_id": 1,
+  "feed_forward_proj": "gated-gelu",
+  "global_block_size": 16,
+  "initializer_factor": 1.0,
+  "is_encoder_decoder": true,
+  "is_gated_act": true,
+  "layer_norm_epsilon": 1e-06,
+  "length_penalty": 0.8,
+  "local_radius": 127,
+  "max_length": 512,
+  "max_position_embeddings": 4096,
+  "min_length": 8,
+  "model_type": "longt5",
+  "n_positions": 4096,
+  "no_repeat_ngram_size": 3,
+  "num_beams": 2,
+  "num_decoder_layers": 12,
+  "num_heads": 12,
+  "num_layers": 12,
+  "output_past": true,
+  "pad_token_id": 0,
+  "relative_attention_max_distance": 128,
+  "relative_attention_num_buckets": 32,
+  "repetition_penalty": 3.5,
+  "tie_word_embeddings": false,
+  "torch_dtype": "float32",
+  "transformers_version": "4.41.0.dev0",
+  "use_cache": false,
+  "vocab_size": 32128
+}

generation_config.json

@@ -1,15 +1,15 @@
-{
-  "decoder_start_token_id": 0,
-  "early_stopping": true,
-  "encoder_no_repeat_ngram_size": 4,
-  "eos_token_id": 1,
-  "length_penalty": 0.8,
-  "max_length": 512,
-  "min_length": 8,
-  "no_repeat_ngram_size": 3,
-  "num_beams": 2,
-  "pad_token_id": 0,
-  "repetition_penalty": 3.5,
-  "transformers_version": "4.39.1",
-  "use_cache": false
-}
+{
+  "decoder_start_token_id": 0,
+  "early_stopping": true,
+  "encoder_no_repeat_ngram_size": 4,
+  "eos_token_id": 1,
+  "length_penalty": 0.8,
+  "max_length": 512,
+  "min_length": 8,
+  "no_repeat_ngram_size": 3,
+  "num_beams": 2,
+  "pad_token_id": 0,
+  "repetition_penalty": 3.5,
+  "transformers_version": "4.41.0.dev0",
+  "use_cache": false
+}