model: add original and converted T5 checkpoints
Browse files- .gitattributes +4 -0
- config.json +30 -0
- model.ckpt-524288.data-00000-of-00004 +0 -0
- model.ckpt-524288.data-00001-of-00004 +3 -0
- model.ckpt-524288.data-00002-of-00004 +3 -0
- model.ckpt-524288.data-00003-of-00004 +3 -0
- model.ckpt-524288.index +0 -0
- model.ckpt-524288.meta +3 -0
- pytorch_model.bin +3 -0
.gitattributes
CHANGED
@@ -32,3 +32,7 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
|
|
32 |
*.zip filter=lfs diff=lfs merge=lfs -text
|
33 |
*.zst filter=lfs diff=lfs merge=lfs -text
|
34 |
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
|
|
|
|
|
|
|
|
|
32 |
*.zip filter=lfs diff=lfs merge=lfs -text
|
33 |
*.zst filter=lfs diff=lfs merge=lfs -text
|
34 |
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
35 |
+
model.ckpt-524288.data-00001-of-00004 filter=lfs diff=lfs merge=lfs -text
|
36 |
+
model.ckpt-524288.data-00002-of-00004 filter=lfs diff=lfs merge=lfs -text
|
37 |
+
model.ckpt-524288.data-00003-of-00004 filter=lfs diff=lfs merge=lfs -text
|
38 |
+
model.ckpt-524288.meta filter=lfs diff=lfs merge=lfs -text
|
config.json
ADDED
@@ -0,0 +1,30 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
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 |
+
"dense_act_fn": "relu",
|
10 |
+
"dropout_rate": 0.1,
|
11 |
+
"eos_token_id": 1,
|
12 |
+
"feed_forward_proj": "relu",
|
13 |
+
"initializer_factor": 1.0,
|
14 |
+
"is_encoder_decoder": true,
|
15 |
+
"is_gated_act": false,
|
16 |
+
"layer_norm_epsilon": 1e-06,
|
17 |
+
"model_type": "t5",
|
18 |
+
"n_positions": 512,
|
19 |
+
"num_decoder_layers": 6,
|
20 |
+
"num_heads": 8,
|
21 |
+
"num_layers": 32,
|
22 |
+
"output_past": true,
|
23 |
+
"pad_token_id": 0,
|
24 |
+
"relative_attention_max_distance": 128,
|
25 |
+
"relative_attention_num_buckets": 32,
|
26 |
+
"torch_dtype": "float32",
|
27 |
+
"transformers_version": "4.26.0.dev0",
|
28 |
+
"use_cache": true,
|
29 |
+
"vocab_size": 32128
|
30 |
+
}
|
model.ckpt-524288.data-00000-of-00004
ADDED
Binary file (8 Bytes). View file
|
|
model.ckpt-524288.data-00001-of-00004
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:a73b0985e901644ff3aee06603f2767dc670b4dd9280deeb85c4732f0f67d099
|
3 |
+
size 95480320
|
model.ckpt-524288.data-00002-of-00004
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:d572beb863c467810b0029c0dbc09a550f65ed187a116154231eaf01b253d25b
|
3 |
+
size 95484928
|
model.ckpt-524288.data-00003-of-00004
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:0ca1261215eaeba247e0371cfc38bdbf61fb518fb4f0390dbd5ed1d93767e161
|
3 |
+
size 95482880
|
model.ckpt-524288.index
ADDED
Binary file (13.9 kB). View file
|
|
model.ckpt-524288.meta
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:475805e5b5e0e9c0b1648fdde50a7e10add2bdb676c305d479b01fefe5bcad2c
|
3 |
+
size 48313899
|
pytorch_model.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:3314a22d752968ec202463620cad026df22bace259b9bfd73166de45b8d79492
|
3 |
+
size 569398427
|