mymusise
/

CPM-GPT2-FP16

Text Generation Transformers TensorFlow Chinese gpt2 Inference Endpoints text-generation-inference

Model card Files Files and versions Community

mymusise commited on Feb 24, 2021

Commit

8c1c7cb

•

1 Parent(s): 13c1ec4

update configs

Signed-off-by: mymusise <mymusise1@gmail.com>

Files changed (1) hide show

config.json +6 -5

config.json CHANGED Viewed

@@ -1,11 +1,11 @@
 {
   "architectures": [
     "TFGPT2LMHeadModel"
   ],
-  "activation_function": "gelu_new",
-  "attn_pdrop": 0.1,
   "bos_token_id": 50256,
-  "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "gradient_checkpointing": false,
   "initializer_range": 0.02,
@@ -18,9 +18,9 @@
   "n_layer": 32,
   "n_positions": 1024,
   "pad_token_id": 0,
-  "resid_pdrop": 0.1,
   "summary_activation": null,
-  "summary_first_dropout": 0.1,
   "summary_proj_to_labels": true,
   "summary_type": "cls_index",
   "summary_use_proj": true,
@@ -31,5 +31,6 @@
     }
   },
   "tokenizer_class": "XLNetTokenizer",
   "vocab_size": 30000
 }

 {
+  "activation_function": "gelu",
   "architectures": [
     "TFGPT2LMHeadModel"
   ],
+  "attn_pdrop": 0.0,
   "bos_token_id": 50256,
+  "embd_pdrop": 0.0,
   "eos_token_id": 50256,
   "gradient_checkpointing": false,
   "initializer_range": 0.02,
   "n_layer": 32,
   "n_positions": 1024,
   "pad_token_id": 0,
+  "resid_pdrop": 0.0,
   "summary_activation": null,
+  "summary_first_dropout": 0.0,
   "summary_proj_to_labels": true,
   "summary_type": "cls_index",
   "summary_use_proj": true,
     }
   },
   "tokenizer_class": "XLNetTokenizer",
+  "use_cache": true,
   "vocab_size": 30000
 }