Upload T5ForConditionalGeneration
Browse files- config.json +6 -36
- model.safetensors +2 -2
config.json
CHANGED
@@ -1,12 +1,12 @@
|
|
1 |
{
|
2 |
-
"_name_or_path": "google/
|
3 |
"architectures": [
|
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,
|
@@ -17,44 +17,14 @@
|
|
17 |
"is_gated_act": true,
|
18 |
"layer_norm_epsilon": 1e-06,
|
19 |
"model_type": "t5",
|
20 |
-
"
|
21 |
-
"
|
22 |
-
"
|
23 |
-
"num_layers": 12,
|
24 |
"output_hidden_states": true,
|
25 |
"output_past": false,
|
26 |
"pad_token_id": 0,
|
27 |
"relative_attention_max_distance": 128,
|
28 |
"relative_attention_num_buckets": 32,
|
29 |
-
"task_specific_params": {
|
30 |
-
"summarization": {
|
31 |
-
"early_stopping": true,
|
32 |
-
"length_penalty": 2.0,
|
33 |
-
"max_length": 200,
|
34 |
-
"min_length": 30,
|
35 |
-
"no_repeat_ngram_size": 3,
|
36 |
-
"num_beams": 4,
|
37 |
-
"prefix": "summarize: "
|
38 |
-
},
|
39 |
-
"translation_en_to_de": {
|
40 |
-
"early_stopping": true,
|
41 |
-
"max_length": 300,
|
42 |
-
"num_beams": 4,
|
43 |
-
"prefix": "translate English to German: "
|
44 |
-
},
|
45 |
-
"translation_en_to_fr": {
|
46 |
-
"early_stopping": true,
|
47 |
-
"max_length": 300,
|
48 |
-
"num_beams": 4,
|
49 |
-
"prefix": "translate English to French: "
|
50 |
-
},
|
51 |
-
"translation_en_to_ro": {
|
52 |
-
"early_stopping": true,
|
53 |
-
"max_length": 300,
|
54 |
-
"num_beams": 4,
|
55 |
-
"prefix": "translate English to Romanian: "
|
56 |
-
}
|
57 |
-
},
|
58 |
"tie_word_embeddings": false,
|
59 |
"torch_dtype": "float32",
|
60 |
"transformers_version": "4.39.0",
|
|
|
1 |
{
|
2 |
+
"_name_or_path": "google/t5-large-lm-adapt",
|
3 |
"architectures": [
|
4 |
"T5ForConditionalGeneration"
|
5 |
],
|
6 |
"classifier_dropout": 0.0,
|
7 |
+
"d_ff": 2816,
|
8 |
"d_kv": 64,
|
9 |
+
"d_model": 1024,
|
10 |
"decoder_start_token_id": 0,
|
11 |
"dense_act_fn": "gelu_new",
|
12 |
"dropout_rate": 0.1,
|
|
|
17 |
"is_gated_act": true,
|
18 |
"layer_norm_epsilon": 1e-06,
|
19 |
"model_type": "t5",
|
20 |
+
"num_decoder_layers": 24,
|
21 |
+
"num_heads": 16,
|
22 |
+
"num_layers": 24,
|
|
|
23 |
"output_hidden_states": true,
|
24 |
"output_past": false,
|
25 |
"pad_token_id": 0,
|
26 |
"relative_attention_max_distance": 128,
|
27 |
"relative_attention_num_buckets": 32,
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
28 |
"tie_word_embeddings": false,
|
29 |
"torch_dtype": "float32",
|
30 |
"transformers_version": "4.39.0",
|
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 sha256:8d1a26589f0ee4df1bd5ec2173ed9f37bc0abd19bfbb5dd882ef0f505147d00d
|
3 |
+
size 3132668808
|