Stancld commited on
Commit
8308524
1 Parent(s): e4efd5c
Files changed (2) hide show
  1. config.json +29 -0
  2. flax_model.msgpack +3 -0
config.json ADDED
@@ -0,0 +1,29 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "LongT5ForConditionalGeneration"
4
+ ],
5
+ "d_ff": 2816,
6
+ "d_kv": 64,
7
+ "d_model": 1024,
8
+ "decoder_start_token_id": 0,
9
+ "dropout_rate": 0.1,
10
+ "encoder_attention_type": "local",
11
+ "eos_token_id": 1,
12
+ "feed_forward_proj": "gated-gelu",
13
+ "initializer_factor": 1.0,
14
+ "is_encoder_decoder": true,
15
+ "layer_norm_epsilon": 1e-06,
16
+ "local_radius": 127,
17
+ "model_type": "longt5",
18
+ "n_positions": 4096,
19
+ "num_decoder_layers": 24,
20
+ "num_heads": 16,
21
+ "num_layers": 24,
22
+ "output_past": true,
23
+ "pad_token_id": 0,
24
+ "relative_attention_max_distance": 128,
25
+ "relative_attention_num_buckets": 32,
26
+ "transformers_version": "4.19.0.dev0",
27
+ "use_cache": true,
28
+ "vocab_size": 32128
29
+ }
flax_model.msgpack ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7fcb80c51a31d99c56780a4af0bb289da89831ff233b85237e1621cf81a5257c
3
+ size 3001028196