add model
Browse files- config.json +5 -2
- pytorch_model.bin +2 -2
config.json
CHANGED
@@ -1,5 +1,5 @@
|
|
1 |
{
|
2 |
-
"_name_or_path": "
|
3 |
"add_prefix": true,
|
4 |
"architectures": [
|
5 |
"MT5ForConditionalGeneration"
|
@@ -8,22 +8,25 @@
|
|
8 |
"d_kv": 64,
|
9 |
"d_model": 512,
|
10 |
"decoder_start_token_id": 0,
|
|
|
11 |
"dropout_rate": 0.1,
|
12 |
"eos_token_id": 1,
|
13 |
"feed_forward_proj": "gated-gelu",
|
14 |
"initializer_factor": 1.0,
|
15 |
"is_encoder_decoder": true,
|
|
|
16 |
"layer_norm_epsilon": 1e-06,
|
17 |
"model_type": "mt5",
|
18 |
"num_decoder_layers": 8,
|
19 |
"num_heads": 6,
|
20 |
"num_layers": 8,
|
21 |
"pad_token_id": 0,
|
|
|
22 |
"relative_attention_num_buckets": 32,
|
23 |
"tie_word_embeddings": false,
|
24 |
"tokenizer_class": "T5Tokenizer",
|
25 |
"torch_dtype": "float32",
|
26 |
-
"transformers_version": "4.
|
27 |
"use_cache": true,
|
28 |
"vocab_size": 250101
|
29 |
}
|
|
|
1 |
{
|
2 |
+
"_name_or_path": "mt5-small-itquad-multitask",
|
3 |
"add_prefix": true,
|
4 |
"architectures": [
|
5 |
"MT5ForConditionalGeneration"
|
|
|
8 |
"d_kv": 64,
|
9 |
"d_model": 512,
|
10 |
"decoder_start_token_id": 0,
|
11 |
+
"dense_act_fn": "gelu_new",
|
12 |
"dropout_rate": 0.1,
|
13 |
"eos_token_id": 1,
|
14 |
"feed_forward_proj": "gated-gelu",
|
15 |
"initializer_factor": 1.0,
|
16 |
"is_encoder_decoder": true,
|
17 |
+
"is_gated_act": true,
|
18 |
"layer_norm_epsilon": 1e-06,
|
19 |
"model_type": "mt5",
|
20 |
"num_decoder_layers": 8,
|
21 |
"num_heads": 6,
|
22 |
"num_layers": 8,
|
23 |
"pad_token_id": 0,
|
24 |
+
"relative_attention_max_distance": 128,
|
25 |
"relative_attention_num_buckets": 32,
|
26 |
"tie_word_embeddings": false,
|
27 |
"tokenizer_class": "T5Tokenizer",
|
28 |
"torch_dtype": "float32",
|
29 |
+
"transformers_version": "4.21.2",
|
30 |
"use_cache": true,
|
31 |
"vocab_size": 250101
|
32 |
}
|
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:bea5e8f132c7403927884f9b89b1e411d38ba2f20fc74e8f92a36849d8d318da
|
3 |
+
size 1200724741
|