Mainak Manna
commited on
Commit
•
ed73d7f
1
Parent(s):
d5b4e10
First version of the model
Browse files- config.json +36 -0
- pytorch_model.bin +3 -0
- spiece.model +3 -0
config.json
ADDED
@@ -0,0 +1,36 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"architectures": [
|
3 |
+
"T5ForConditionalGeneration"
|
4 |
+
],
|
5 |
+
"d_ff": 2048,
|
6 |
+
"d_kv": 64,
|
7 |
+
"d_model": 512,
|
8 |
+
"decoder_start_token_id": 0,
|
9 |
+
"dropout_rate": 0.1,
|
10 |
+
"eos_token_id": 1,
|
11 |
+
"feed_forward_proj": "relu",
|
12 |
+
"initializer_factor": 1.0,
|
13 |
+
"is_encoder_decoder": true,
|
14 |
+
"layer_norm_epsilon": 1e-06,
|
15 |
+
"model_type": "t5",
|
16 |
+
"n_positions": 512,
|
17 |
+
"num_decoder_layers": 6,
|
18 |
+
"num_heads": 8,
|
19 |
+
"num_layers": 6,
|
20 |
+
"output_past": true,
|
21 |
+
"pad_token_id": 0,
|
22 |
+
"relative_attention_num_buckets": 32,
|
23 |
+
"task_specific_params": {
|
24 |
+
"translation_cs_to_es": {
|
25 |
+
"early_stopping": true,
|
26 |
+
"length_penalty": 2.0,
|
27 |
+
"max_length": 512,
|
28 |
+
"min_length": 1,
|
29 |
+
"no_repeat_ngram_size": 3,
|
30 |
+
"num_beams": 4,
|
31 |
+
"prefix": "translate Cszech to Spanish : "
|
32 |
+
}
|
33 |
+
},
|
34 |
+
"use_cache": true,
|
35 |
+
"vocab_size": 32128
|
36 |
+
}
|
pytorch_model.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:1e016c0d5b35152b0ba42347994b2f17fdb86ed4d51b4939b666848fe489cf36
|
3 |
+
size 242087498
|
spiece.model
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:53b3c9b1becca02342bbf2c8b00abe9154fb0fc8dbe8c71ad506537b2222523a
|
3 |
+
size 840425
|