Test V1
Browse files- config.json +24 -59
- pytorch_model.bin +2 -2
- special_tokens_map.json +1 -1
- model.safetensors → spiece.model +2 -2
- tokenizer_config.json +1 -1
config.json
CHANGED
@@ -1,66 +1,31 @@
|
|
1 |
{
|
2 |
-
"_name_or_path": "
|
3 |
-
"_num_labels": 3,
|
4 |
-
"activation_dropout": 0.0,
|
5 |
-
"activation_function": "gelu",
|
6 |
-
"add_bias_logits": false,
|
7 |
-
"add_final_layer_norm": false,
|
8 |
"architectures": [
|
9 |
-
"
|
10 |
],
|
11 |
-
"
|
12 |
-
"
|
13 |
-
"
|
14 |
-
"
|
15 |
-
"
|
16 |
-
"
|
17 |
-
"
|
18 |
-
"
|
19 |
-
"decoder_layers": 12,
|
20 |
-
"decoder_start_token_id": 2,
|
21 |
-
"dropout": 0.1,
|
22 |
-
"early_stopping": true,
|
23 |
-
"encoder_attention_heads": 16,
|
24 |
-
"encoder_ffn_dim": 4096,
|
25 |
-
"encoder_layerdrop": 0.0,
|
26 |
-
"encoder_layers": 12,
|
27 |
-
"eos_token_id": 2,
|
28 |
-
"eos_token_ids": [
|
29 |
-
2
|
30 |
-
],
|
31 |
-
"forced_eos_token_id": 2,
|
32 |
-
"gradient_checkpointing": false,
|
33 |
-
"id2label": {
|
34 |
-
"0": "LABEL_0",
|
35 |
-
"1": "LABEL_1",
|
36 |
-
"2": "LABEL_2"
|
37 |
-
},
|
38 |
-
"init_std": 0.02,
|
39 |
"is_encoder_decoder": true,
|
40 |
-
"
|
41 |
-
|
42 |
-
|
43 |
-
|
44 |
-
|
45 |
-
"
|
46 |
-
"
|
47 |
-
"
|
48 |
-
"
|
49 |
-
"no_repeat_ngram_size": 3,
|
50 |
-
"normalize_before": false,
|
51 |
-
"normalize_embedding": true,
|
52 |
-
"num_beams": 6,
|
53 |
-
"num_hidden_layers": 12,
|
54 |
"output_past": true,
|
55 |
-
"pad_token_id":
|
56 |
-
"
|
57 |
-
"
|
58 |
-
"
|
59 |
-
"static_position_embeddings": false,
|
60 |
-
"student_decoder_layers": null,
|
61 |
-
"student_encoder_layers": null,
|
62 |
-
"task_specific_params": {},
|
63 |
-
"transformers_version": "4.6.1",
|
64 |
"use_cache": true,
|
65 |
-
"vocab_size":
|
66 |
}
|
|
|
1 |
{
|
2 |
+
"_name_or_path": "google/mt5-base",
|
|
|
|
|
|
|
|
|
|
|
3 |
"architectures": [
|
4 |
+
"MT5ForConditionalGeneration"
|
5 |
],
|
6 |
+
"d_ff": 2048,
|
7 |
+
"d_kv": 64,
|
8 |
+
"d_model": 768,
|
9 |
+
"decoder_start_token_id": 0,
|
10 |
+
"dropout_rate": 0.1,
|
11 |
+
"eos_token_id": 1,
|
12 |
+
"feed_forward_proj": "gated-gelu",
|
13 |
+
"initializer_factor": 1.0,
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
14 |
"is_encoder_decoder": true,
|
15 |
+
"layer_norm_epsilon": 1e-06,
|
16 |
+
"length_penalty": 0.6,
|
17 |
+
"max_length": 84,
|
18 |
+
"model_type": "mt5",
|
19 |
+
"no_repeat_ngram_size": 2,
|
20 |
+
"num_beams": 4,
|
21 |
+
"num_decoder_layers": 12,
|
22 |
+
"num_heads": 12,
|
23 |
+
"num_layers": 12,
|
|
|
|
|
|
|
|
|
|
|
24 |
"output_past": true,
|
25 |
+
"pad_token_id": 0,
|
26 |
+
"relative_attention_num_buckets": 32,
|
27 |
+
"tie_word_embeddings": false,
|
28 |
+
"tokenizer_class": "T5Tokenizer",
|
|
|
|
|
|
|
|
|
|
|
29 |
"use_cache": true,
|
30 |
+
"vocab_size": 250112
|
31 |
}
|
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 sha256:1899a041aceedfd0c9c67e87f2597bc597ce6f4c1f21b5d35a6325322608a898
|
3 |
+
size 2329707353
|
special_tokens_map.json
CHANGED
@@ -1 +1 @@
|
|
1 |
-
{"
|
|
|
1 |
+
{"eos_token": "</s>", "unk_token": "<unk>", "pad_token": "<pad>"}
|
model.safetensors → spiece.model
RENAMED
@@ -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:ef78f86560d809067d12bac6c09f19a462cb3af3f54d2b8acbba26e1433125d6
|
3 |
+
size 4309802
|
tokenizer_config.json
CHANGED
@@ -1 +1 @@
|
|
1 |
-
{"
|
|
|
1 |
+
{"eos_token": "</s>", "unk_token": "<unk>", "pad_token": "<pad>", "extra_ids": 0, "additional_special_tokens": null, "special_tokens_map_file": "/home/patrick/.cache/torch/transformers/685ac0ca8568ec593a48b61b0a3c272beee9bc194a3c7241d15dcadb5f875e53.f76030f3ec1b96a8199b2593390c610e76ca8028ef3d24680000619ffb646276", "tokenizer_file": null, "name_or_path": "google/mt5-base"}
|