add base model
Browse files- config.json +36 -0
- pytorch_model.bin +3 -0
- training_args.bin +3 -0
config.json
ADDED
@@ -0,0 +1,36 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "pszemraj/t5-base-kw2email-v3.5",
|
3 |
+
"architectures": [
|
4 |
+
"T5ForConditionalGeneration"
|
5 |
+
],
|
6 |
+
"d_ff": 2048,
|
7 |
+
"d_kv": 64,
|
8 |
+
"d_model": 768,
|
9 |
+
"decoder_start_token_id": 0,
|
10 |
+
"dense_act_fn": "gelu_new",
|
11 |
+
"dropout_rate": 0.1,
|
12 |
+
"early_stopping": true,
|
13 |
+
"eos_token_id": 1,
|
14 |
+
"feed_forward_proj": "gated-gelu",
|
15 |
+
"initializer_factor": 1.0,
|
16 |
+
"is_encoder_decoder": true,
|
17 |
+
"is_gated_act": true,
|
18 |
+
"layer_norm_epsilon": 1e-06,
|
19 |
+
"max_length": 1024,
|
20 |
+
"min_length": 8,
|
21 |
+
"model_type": "t5",
|
22 |
+
"no_repeat_ngram_size": 4,
|
23 |
+
"num_beams": 2,
|
24 |
+
"num_decoder_layers": 12,
|
25 |
+
"num_heads": 12,
|
26 |
+
"num_layers": 12,
|
27 |
+
"output_past": true,
|
28 |
+
"pad_token_id": 0,
|
29 |
+
"relative_attention_max_distance": 128,
|
30 |
+
"relative_attention_num_buckets": 32,
|
31 |
+
"tie_word_embeddings": false,
|
32 |
+
"torch_dtype": "float32",
|
33 |
+
"transformers_version": "4.21.2",
|
34 |
+
"use_cache": false,
|
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:cff9ef3f8fad8c94d2edd08493463109bf74e996d9d0ca997470d96987d9a46c
|
3 |
+
size 990351851
|
training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:bc29c279b2ccbed713b99bc7eaa7fb0d930fd7cce1fba718b8a35a721d8f5782
|
3 |
+
size 4527
|