PrekshaJoon
/

flan-t5-finetuned-summarization

text2text-generation

text-generation-inference

Inference Endpoints

Model card Files Files and versions Community

PrekshaJoon commited on Oct 7, 2024

Commit

6e6107e

·

verified ·

1 Parent(s): 2f24180

Upload T5ForConditionalGeneration

Files changed (3) hide show

README.md +4 -4
config.json +5 -5
model.safetensors +2 -2

README.md CHANGED Viewed

@@ -1,12 +1,12 @@
 ---
-library_name: transformers
-license: mit
 datasets:
 - abisee/cnn_dailymail
 language:
 - en
-base_model:
-- google/flan-t5-large
 pipeline_tag: summarization
 ---

 ---
+base_model:
+- google/flan-t5-large
 datasets:
 - abisee/cnn_dailymail
 language:
 - en
+library_name: transformers
+license: mit
 pipeline_tag: summarization
 ---

config.json CHANGED Viewed

@@ -4,9 +4,9 @@
     "T5ForConditionalGeneration"
   ],
   "classifier_dropout": 0.0,
-  "d_ff": 2048,
   "d_kv": 64,
-  "d_model": 768,
   "decoder_start_token_id": 0,
   "dense_act_fn": "gelu_new",
   "dropout_rate": 0.1,
@@ -18,9 +18,9 @@
   "layer_norm_epsilon": 1e-06,
   "model_type": "t5",
   "n_positions": 512,
-  "num_decoder_layers": 12,
-  "num_heads": 12,
-  "num_layers": 12,
   "output_past": true,
   "pad_token_id": 0,
   "relative_attention_max_distance": 128,

     "T5ForConditionalGeneration"
   ],
   "classifier_dropout": 0.0,
+  "d_ff": 1024,
   "d_kv": 64,
+  "d_model": 512,
   "decoder_start_token_id": 0,
   "dense_act_fn": "gelu_new",
   "dropout_rate": 0.1,
   "layer_norm_epsilon": 1e-06,
   "model_type": "t5",
   "n_positions": 512,
+  "num_decoder_layers": 8,
+  "num_heads": 6,
+  "num_layers": 8,
   "output_past": true,
   "pad_token_id": 0,
   "relative_attention_max_distance": 128,

model.safetensors CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:197b346658905cda50c1a71fe0eb77a4d79306adaeb5d7a3c0e9208c91022d45
-size 990345064

 version https://git-lfs.github.com/spec/v1
+oid sha256:495fa51e204676f1a857a9fc13c4c89f3f5ba9f480b898cebca02add25e6d749
+size 307867048