update model
Browse files- config.json +6 -6
- generation_config.json +1 -1
- model.safetensors +2 -2
- spiece.model +3 -0
- tokenizer_config.json +0 -4
- training_args.bin +2 -2
config.json
CHANGED
@@ -1,12 +1,12 @@
|
|
1 |
{
|
2 |
-
"_name_or_path": "/
|
3 |
"architectures": [
|
4 |
"T5ForConditionalGeneration"
|
5 |
],
|
6 |
"classifier_dropout": 0.0,
|
7 |
-
"d_ff":
|
8 |
"d_kv": 64,
|
9 |
-
"d_model":
|
10 |
"decoder_start_token_id": 0,
|
11 |
"dense_act_fn": "relu",
|
12 |
"dropout_rate": 0.1,
|
@@ -18,9 +18,9 @@
|
|
18 |
"layer_norm_epsilon": 1e-06,
|
19 |
"model_type": "t5",
|
20 |
"n_positions": 512,
|
21 |
-
"num_decoder_layers":
|
22 |
-
"num_heads":
|
23 |
-
"num_layers":
|
24 |
"output_past": true,
|
25 |
"pad_token_id": 0,
|
26 |
"relative_attention_max_distance": 128,
|
|
|
1 |
{
|
2 |
+
"_name_or_path": "google-t5/t5-small",
|
3 |
"architectures": [
|
4 |
"T5ForConditionalGeneration"
|
5 |
],
|
6 |
"classifier_dropout": 0.0,
|
7 |
+
"d_ff": 2048,
|
8 |
"d_kv": 64,
|
9 |
+
"d_model": 512,
|
10 |
"decoder_start_token_id": 0,
|
11 |
"dense_act_fn": "relu",
|
12 |
"dropout_rate": 0.1,
|
|
|
18 |
"layer_norm_epsilon": 1e-06,
|
19 |
"model_type": "t5",
|
20 |
"n_positions": 512,
|
21 |
+
"num_decoder_layers": 6,
|
22 |
+
"num_heads": 8,
|
23 |
+
"num_layers": 6,
|
24 |
"output_past": true,
|
25 |
"pad_token_id": 0,
|
26 |
"relative_attention_max_distance": 128,
|
generation_config.json
CHANGED
@@ -3,7 +3,7 @@
|
|
3 |
"early_stopping": true,
|
4 |
"eos_token_id": 1,
|
5 |
"max_new_tokens": 32,
|
6 |
-
"min_new_tokens":
|
7 |
"num_beams": 2,
|
8 |
"pad_token_id": 0,
|
9 |
"transformers_version": "4.39.0"
|
|
|
3 |
"early_stopping": true,
|
4 |
"eos_token_id": 1,
|
5 |
"max_new_tokens": 32,
|
6 |
+
"min_new_tokens": 2,
|
7 |
"num_beams": 2,
|
8 |
"pad_token_id": 0,
|
9 |
"transformers_version": "4.39.0"
|
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:da1a681c6910fcf9624d64ea3d93dea8b57d1f21432c064e40987fe289c264b7
|
3 |
+
size 242041896
|
spiece.model
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:d60acb128cf7b7f2536e8f38a5b18a05535c9e14c7a355904270e15b0945ea86
|
3 |
+
size 791656
|
tokenizer_config.json
CHANGED
@@ -930,12 +930,8 @@
|
|
930 |
"clean_up_tokenization_spaces": true,
|
931 |
"eos_token": "</s>",
|
932 |
"extra_ids": 100,
|
933 |
-
"max_length": 32,
|
934 |
"model_max_length": 512,
|
935 |
"pad_token": "<pad>",
|
936 |
-
"stride": 0,
|
937 |
"tokenizer_class": "T5Tokenizer",
|
938 |
-
"truncation_side": "right",
|
939 |
-
"truncation_strategy": "longest_first",
|
940 |
"unk_token": "<unk>"
|
941 |
}
|
|
|
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 |
}
|
training_args.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 sha256:3d724b3b5ce66aa92dfa1552b1696860da1ef1ee9b6cfbe7985ef4cb3d74dcac
|
3 |
+
size 6712
|