sarme
commited on
Commit
·
9fa4c98
1
Parent(s):
3afd123
add model
Browse files- config.json +13 -8
- pytorch_model.bin +2 -2
config.json
CHANGED
|
@@ -1,5 +1,5 @@
|
|
| 1 |
{
|
| 2 |
-
"_name_or_path": "
|
| 3 |
"architectures": [
|
| 4 |
"T5ForConditionalGeneration"
|
| 5 |
],
|
|
@@ -8,19 +8,23 @@
|
|
| 8 |
"d_model": 768,
|
| 9 |
"decoder_start_token_id": 0,
|
| 10 |
"dropout_rate": 0.1,
|
|
|
|
| 11 |
"eos_token_id": 1,
|
| 12 |
"feed_forward_proj": "relu",
|
| 13 |
-
"gradient_checkpointing": false,
|
| 14 |
"initializer_factor": 1.0,
|
| 15 |
"is_encoder_decoder": true,
|
| 16 |
"layer_norm_epsilon": 1e-06,
|
|
|
|
|
|
|
| 17 |
"model_type": "t5",
|
| 18 |
"n_positions": 512,
|
|
|
|
| 19 |
"num_decoder_layers": 12,
|
| 20 |
"num_heads": 12,
|
| 21 |
"num_layers": 12,
|
| 22 |
"output_past": true,
|
| 23 |
"pad_token_id": 0,
|
|
|
|
| 24 |
"relative_attention_num_buckets": 32,
|
| 25 |
"task_specific_params": {
|
| 26 |
"summarization": {
|
|
@@ -52,13 +56,14 @@
|
|
| 52 |
},
|
| 53 |
"translation_en_to_rq": {
|
| 54 |
"early_stopping": true,
|
| 55 |
-
"max_length":
|
| 56 |
-
"min_length":
|
| 57 |
-
"num_beams":
|
| 58 |
-
"prefix": "
|
| 59 |
}
|
| 60 |
},
|
| 61 |
-
"
|
|
|
|
| 62 |
"use_cache": true,
|
| 63 |
-
"vocab_size":
|
| 64 |
}
|
|
|
|
| 1 |
{
|
| 2 |
+
"_name_or_path": "ozcangundes/T5-base-for-BioQA",
|
| 3 |
"architectures": [
|
| 4 |
"T5ForConditionalGeneration"
|
| 5 |
],
|
|
|
|
| 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": "relu",
|
|
|
|
| 14 |
"initializer_factor": 1.0,
|
| 15 |
"is_encoder_decoder": true,
|
| 16 |
"layer_norm_epsilon": 1e-06,
|
| 17 |
+
"max_length": 600,
|
| 18 |
+
"min_length": 500,
|
| 19 |
"model_type": "t5",
|
| 20 |
"n_positions": 512,
|
| 21 |
+
"num_beams": 5,
|
| 22 |
"num_decoder_layers": 12,
|
| 23 |
"num_heads": 12,
|
| 24 |
"num_layers": 12,
|
| 25 |
"output_past": true,
|
| 26 |
"pad_token_id": 0,
|
| 27 |
+
"relative_attention_max_distance": 128,
|
| 28 |
"relative_attention_num_buckets": 32,
|
| 29 |
"task_specific_params": {
|
| 30 |
"summarization": {
|
|
|
|
| 56 |
},
|
| 57 |
"translation_en_to_rq": {
|
| 58 |
"early_stopping": true,
|
| 59 |
+
"max_length": 600,
|
| 60 |
+
"min_length": 500,
|
| 61 |
+
"num_beams": 5,
|
| 62 |
+
"prefix": ""
|
| 63 |
}
|
| 64 |
},
|
| 65 |
+
"torch_dtype": "float32",
|
| 66 |
+
"transformers_version": "4.19.2",
|
| 67 |
"use_cache": true,
|
| 68 |
+
"vocab_size": 32110
|
| 69 |
}
|
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 sha256:3426c0b534f8f4f301938eca2bf43c47e49730a89e5b937011c924150b663677
|
| 3 |
+
size 891645503
|