Upload tiny models for PegasusXModel
Browse files- config.json +2 -3
- pytorch_model.bin +2 -2
- spiece.model +3 -0
- tokenizer.json +0 -0
- tokenizer_config.json +0 -1
config.json
CHANGED
|
@@ -7,7 +7,6 @@
|
|
| 7 |
"attention_dropout": 0.1,
|
| 8 |
"block_size": 512,
|
| 9 |
"bos_token_id": 0,
|
| 10 |
-
"classifier_dropout": 0.0,
|
| 11 |
"d_model": 16,
|
| 12 |
"decoder_attention_heads": 4,
|
| 13 |
"decoder_ffn_dim": 4,
|
|
@@ -31,7 +30,7 @@
|
|
| 31 |
"scale_embedding": true,
|
| 32 |
"stagger_local_blocks": false,
|
| 33 |
"torch_dtype": "float32",
|
| 34 |
-
"transformers_version": "4.
|
| 35 |
"use_cache": true,
|
| 36 |
-
"vocab_size":
|
| 37 |
}
|
|
|
|
| 7 |
"attention_dropout": 0.1,
|
| 8 |
"block_size": 512,
|
| 9 |
"bos_token_id": 0,
|
|
|
|
| 10 |
"d_model": 16,
|
| 11 |
"decoder_attention_heads": 4,
|
| 12 |
"decoder_ffn_dim": 4,
|
|
|
|
| 30 |
"scale_embedding": true,
|
| 31 |
"stagger_local_blocks": false,
|
| 32 |
"torch_dtype": "float32",
|
| 33 |
+
"transformers_version": "4.28.0.dev0",
|
| 34 |
"use_cache": true,
|
| 35 |
+
"vocab_size": 96103
|
| 36 |
}
|
pytorch_model.bin
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
-
size
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:76c393d1e6bb3dc9ae20e9de565444ca1be0fba67e6e68372a99cb30d452bd68
|
| 3 |
+
size 6203331
|
spiece.model
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:0015189ef36359283fec8b93cf6d9ce51bca37eb1101defc68a53b394913b96c
|
| 3 |
+
size 1912529
|
tokenizer.json
CHANGED
|
The diff for this file is too large to render.
See raw diff
|
|
|
tokenizer_config.json
CHANGED
|
@@ -108,7 +108,6 @@
|
|
| 108 |
"mask_token": "<mask_2>",
|
| 109 |
"mask_token_sent": "<mask_1>",
|
| 110 |
"model_max_length": 20,
|
| 111 |
-
"name_or_path": "google/pegasus-x-large",
|
| 112 |
"offset": 103,
|
| 113 |
"pad_token": "<pad>",
|
| 114 |
"sp_model_kwargs": {},
|
|
|
|
| 108 |
"mask_token": "<mask_2>",
|
| 109 |
"mask_token_sent": "<mask_1>",
|
| 110 |
"model_max_length": 20,
|
|
|
|
| 111 |
"offset": 103,
|
| 112 |
"pad_token": "<pad>",
|
| 113 |
"sp_model_kwargs": {},
|