add base model
Browse files- config.json +34 -0
- pytorch_model.bin +3 -0
- training_args.bin +3 -0
config.json
ADDED
@@ -0,0 +1,34 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "google/t5-v1_1-base",
|
3 |
+
"architectures": [
|
4 |
+
"T5ForConditionalGeneration"
|
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 |
+
"early_stopping": true,
|
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 |
+
"length_penalty": 3.5,
|
18 |
+
"max_length": 512,
|
19 |
+
"min_length": 16,
|
20 |
+
"model_type": "t5",
|
21 |
+
"no_repeat_ngram_size": 3,
|
22 |
+
"num_beams": 5,
|
23 |
+
"num_decoder_layers": 12,
|
24 |
+
"num_heads": 12,
|
25 |
+
"num_layers": 12,
|
26 |
+
"output_past": true,
|
27 |
+
"pad_token_id": 0,
|
28 |
+
"relative_attention_num_buckets": 32,
|
29 |
+
"tie_word_embeddings": false,
|
30 |
+
"torch_dtype": "float32",
|
31 |
+
"transformers_version": "4.16.2",
|
32 |
+
"use_cache": false,
|
33 |
+
"vocab_size": 32128
|
34 |
+
}
|
pytorch_model.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:6e37d0ff2b1c1c6b6bd1eb96e7c017f8575328e7f8ffe0fd763d0c78071e72ef
|
3 |
+
size 990383595
|
training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:0f7d4a138032663ec751b249c00b14ae6d7b51b0f0ff193b363e1b68b69cb66a
|
3 |
+
size 4207
|