Daniel Stancl
commited on
Commit
•
5261045
1
Parent(s):
00e56fe
Add config and flax ckpt
Browse files- config.json +28 -0
- flax_model.msgpack +3 -0
config.json
ADDED
|
@@ -0,0 +1,28 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"architectures": [
|
| 3 |
+
"LongT5ForConditionalGeneration"
|
| 4 |
+
],
|
| 5 |
+
"d_ff": 2048,
|
| 6 |
+
"d_kv": 64,
|
| 7 |
+
"d_model": 768,
|
| 8 |
+
"decoder_start_token_id": 0,
|
| 9 |
+
"dropout_rate": 0.1,
|
| 10 |
+
"eos_token_id": 1,
|
| 11 |
+
"feed_forward_proj": "gated-gelu",
|
| 12 |
+
"initializer_factor": 1.0,
|
| 13 |
+
"is_encoder_decoder": true,
|
| 14 |
+
"layer_norm_epsilon": 1e-06,
|
| 15 |
+
"local_radius": 127,
|
| 16 |
+
"model_type": "longt5",
|
| 17 |
+
"n_positions": 512,
|
| 18 |
+
"num_decoder_layers": 12,
|
| 19 |
+
"num_heads": 12,
|
| 20 |
+
"num_layers": 12,
|
| 21 |
+
"output_past": true,
|
| 22 |
+
"pad_token_id": 0,
|
| 23 |
+
"relative_attention_max_distance": 128,
|
| 24 |
+
"relative_attention_num_buckets": 32,
|
| 25 |
+
"transformers_version": "4.19.0.dev0",
|
| 26 |
+
"use_cache": true,
|
| 27 |
+
"vocab_size": 32128
|
| 28 |
+
}
|
flax_model.msgpack
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:3f51b0064270aca663a746a4585c24804726e30407d475b2e1be7660ea796081
|
| 3 |
+
size 990323675
|