Upload T5ForConditionalGeneration
Browse files- config.json +5 -5
- generation_config.json +1 -0
- model.safetensors +2 -2
config.json
CHANGED
@@ -4,9 +4,9 @@
|
|
4 |
"T5ForConditionalGeneration"
|
5 |
],
|
6 |
"classifier_dropout": 0.0,
|
7 |
-
"d_ff":
|
8 |
"d_kv": 64,
|
9 |
-
"d_model":
|
10 |
"decoder_start_token_id": 0,
|
11 |
"dense_act_fn": "gelu_new",
|
12 |
"dropout_rate": 0.1,
|
@@ -18,9 +18,9 @@
|
|
18 |
"layer_norm_epsilon": 1e-06,
|
19 |
"model_type": "t5",
|
20 |
"n_positions": 512,
|
21 |
-
"num_decoder_layers":
|
22 |
-
"num_heads":
|
23 |
-
"num_layers":
|
24 |
"output_past": true,
|
25 |
"pad_token_id": 0,
|
26 |
"relative_attention_max_distance": 128,
|
|
|
4 |
"T5ForConditionalGeneration"
|
5 |
],
|
6 |
"classifier_dropout": 0.0,
|
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,
|
|
|
18 |
"layer_norm_epsilon": 1e-06,
|
19 |
"model_type": "t5",
|
20 |
"n_positions": 512,
|
21 |
+
"num_decoder_layers": 8,
|
22 |
+
"num_heads": 6,
|
23 |
+
"num_layers": 8,
|
24 |
"output_past": true,
|
25 |
"pad_token_id": 0,
|
26 |
"relative_attention_max_distance": 128,
|
generation_config.json
CHANGED
@@ -1,4 +1,5 @@
|
|
1 |
{
|
|
|
2 |
"decoder_start_token_id": 0,
|
3 |
"eos_token_id": 1,
|
4 |
"pad_token_id": 0,
|
|
|
1 |
{
|
2 |
+
"_from_model_config": true,
|
3 |
"decoder_start_token_id": 0,
|
4 |
"eos_token_id": 1,
|
5 |
"pad_token_id": 0,
|
model.safetensors
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 sha256:7c6451ce60a6cb391e25edfb82d5c068a020b143e5fbfbbb4a864b08da40f0a1
|
3 |
+
size 307764648
|