model: add original and converted 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 |
+
"_name_or_path": "t5-efficient-large-nl36",
|
3 |
+
"architectures": [
|
4 |
+
"T5ForConditionalGeneration"
|
5 |
+
],
|
6 |
+
"d_ff": 4096,
|
7 |
+
"d_kv": 64,
|
8 |
+
"d_model": 1024,
|
9 |
+
"decoder_start_token_id": 0,
|
10 |
+
"dense_act_fn": "relu",
|
11 |
+
"dropout_rate": 0.1,
|
12 |
+
"eos_token_id": 1,
|
13 |
+
"feed_forward_proj": "relu",
|
14 |
+
"initializer_factor": 1.0,
|
15 |
+
"is_encoder_decoder": true,
|
16 |
+
"is_gated_act": false,
|
17 |
+
"layer_norm_epsilon": 1e-06,
|
18 |
+
"model_type": "t5",
|
19 |
+
"n_positions": 512,
|
20 |
+
"num_decoder_layers": 36,
|
21 |
+
"num_heads": 16,
|
22 |
+
"num_layers": 36,
|
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:bb35a30755ee39972d569bb1baabbea8a9bec54dc9f15220b8571dacc625ffbd
|
3 |
+
size 728787968
|
model.ckpt-524288.data-00002-of-00004
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:3c9298ee11249ba074506e7cf44b284a5f0271442461965efac3a94167fefc9b
|
3 |
+
size 728790528
|
model.ckpt-524288.data-00003-of-00004
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:9b1fb96509255e0a351750b47650b7e95a447041547bcc47f55835bcb270367e
|
3 |
+
size 729893888
|
model.ckpt-524288.index
ADDED
Binary file (30.9 kB). View file
|
|
model.ckpt-524288.meta
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:dea3bf95a0342b126a2c227bf17eabc5eaa6539fae411044ef5e1e9a72b9d2fb
|
3 |
+
size 39267483
|
pytorch_model.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:57e5b3525479da68a39f4c016460a05fd4e66a360eee231c8b0a5e3862c59f48
|
3 |
+
size 4360452147
|