Upload MT5ForConditionalGeneration
Browse files- config.json +53 -0
- generation_config.json +7 -0
- pytorch_model.bin +3 -0
config.json
ADDED
@@ -0,0 +1,53 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "lmqg_output/trimmed_qa/mt5-small-trimmed-ru-5000-ruquad-qa/best_model",
|
3 |
+
"add_prefix": false,
|
4 |
+
"architectures": [
|
5 |
+
"MT5ForConditionalGeneration"
|
6 |
+
],
|
7 |
+
"d_ff": 1024,
|
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": "4.26.1",
|
30 |
+
"use_cache": true,
|
31 |
+
"vocab_size": 5003,
|
32 |
+
"vocabtrimmer": {
|
33 |
+
"mining_config": {
|
34 |
+
"dataset": "vocabtrimmer/mc4_validation",
|
35 |
+
"dataset_column": "text",
|
36 |
+
"dataset_name": "ru",
|
37 |
+
"dataset_split": "validation",
|
38 |
+
"language": "ru",
|
39 |
+
"min_frequency": 2,
|
40 |
+
"target_vocab_size": 5000
|
41 |
+
},
|
42 |
+
"stats": {
|
43 |
+
"compression_rate_embedding": 1.999904042988741,
|
44 |
+
"compression_rate_full": 16.38505482209736,
|
45 |
+
"parameter_size_embedding/raw": 256114688,
|
46 |
+
"parameter_size_embedding/trimmed": 5122048,
|
47 |
+
"parameter_size_full/raw": 300176768,
|
48 |
+
"parameter_size_full/trimmed": 49184128,
|
49 |
+
"vocab_size/raw": 250112,
|
50 |
+
"vocab_size/trimmed": 5002
|
51 |
+
}
|
52 |
+
}
|
53 |
+
}
|
generation_config.json
ADDED
@@ -0,0 +1,7 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_from_model_config": true,
|
3 |
+
"decoder_start_token_id": 0,
|
4 |
+
"eos_token_id": 1,
|
5 |
+
"pad_token_id": 0,
|
6 |
+
"transformers_version": "4.26.1"
|
7 |
+
}
|
pytorch_model.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:aac4644372148a69318c8df5bf502646e059de51f81d2366a1e351a4d85acf83
|
3 |
+
size 196806021
|