Upload DemoT5QAPipeline
Browse files- config.json +6 -6
- model.safetensors +2 -2
- tokenizer.json +0 -0
- tokenizer_config.json +0 -4
config.json
CHANGED
|
@@ -1,5 +1,5 @@
|
|
| 1 |
{
|
| 2 |
-
"_name_or_path": "
|
| 3 |
"architectures": [
|
| 4 |
"T5ForConditionalGeneration"
|
| 5 |
],
|
|
@@ -15,9 +15,9 @@
|
|
| 15 |
]
|
| 16 |
}
|
| 17 |
},
|
| 18 |
-
"d_ff":
|
| 19 |
"d_kv": 64,
|
| 20 |
-
"d_model":
|
| 21 |
"decoder_start_token_id": 0,
|
| 22 |
"dense_act_fn": "relu",
|
| 23 |
"dropout_rate": 0.1,
|
|
@@ -29,9 +29,9 @@
|
|
| 29 |
"layer_norm_epsilon": 1e-06,
|
| 30 |
"model_type": "t5",
|
| 31 |
"n_positions": 512,
|
| 32 |
-
"num_decoder_layers":
|
| 33 |
-
"num_heads":
|
| 34 |
-
"num_layers":
|
| 35 |
"output_past": true,
|
| 36 |
"pad_token_id": 0,
|
| 37 |
"relative_attention_max_distance": 128,
|
|
|
|
| 1 |
{
|
| 2 |
+
"_name_or_path": "google-t5/t5-small",
|
| 3 |
"architectures": [
|
| 4 |
"T5ForConditionalGeneration"
|
| 5 |
],
|
|
|
|
| 15 |
]
|
| 16 |
}
|
| 17 |
},
|
| 18 |
+
"d_ff": 2048,
|
| 19 |
"d_kv": 64,
|
| 20 |
+
"d_model": 512,
|
| 21 |
"decoder_start_token_id": 0,
|
| 22 |
"dense_act_fn": "relu",
|
| 23 |
"dropout_rate": 0.1,
|
|
|
|
| 29 |
"layer_norm_epsilon": 1e-06,
|
| 30 |
"model_type": "t5",
|
| 31 |
"n_positions": 512,
|
| 32 |
+
"num_decoder_layers": 6,
|
| 33 |
+
"num_heads": 8,
|
| 34 |
+
"num_layers": 6,
|
| 35 |
"output_past": true,
|
| 36 |
"pad_token_id": 0,
|
| 37 |
"relative_attention_max_distance": 128,
|
model.safetensors
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 sha256:881ecd3d2e20cfb1ddf96ac598ad90a610007dfa4ff04cfc024e4afd118bc686
|
| 3 |
+
size 242041896
|
tokenizer.json
CHANGED
|
The diff for this file is too large to render.
See raw diff
|
|
|
tokenizer_config.json
CHANGED
|
@@ -1,5 +1,4 @@
|
|
| 1 |
{
|
| 2 |
-
"add_prefix_space": true,
|
| 3 |
"added_tokens_decoder": {
|
| 4 |
"0": {
|
| 5 |
"content": "<pad>",
|
|
@@ -931,11 +930,8 @@
|
|
| 931 |
"clean_up_tokenization_spaces": true,
|
| 932 |
"eos_token": "</s>",
|
| 933 |
"extra_ids": 100,
|
| 934 |
-
"from_pt": true,
|
| 935 |
-
"legacy": true,
|
| 936 |
"model_max_length": 512,
|
| 937 |
"pad_token": "<pad>",
|
| 938 |
-
"sp_model_kwargs": {},
|
| 939 |
"tokenizer_class": "T5Tokenizer",
|
| 940 |
"unk_token": "<unk>"
|
| 941 |
}
|
|
|
|
| 1 |
{
|
|
|
|
| 2 |
"added_tokens_decoder": {
|
| 3 |
"0": {
|
| 4 |
"content": "<pad>",
|
|
|
|
| 930 |
"clean_up_tokenization_spaces": true,
|
| 931 |
"eos_token": "</s>",
|
| 932 |
"extra_ids": 100,
|
|
|
|
|
|
|
| 933 |
"model_max_length": 512,
|
| 934 |
"pad_token": "<pad>",
|
|
|
|
| 935 |
"tokenizer_class": "T5Tokenizer",
|
| 936 |
"unk_token": "<unk>"
|
| 937 |
}
|