rristo commited on
Commit
96f7451
1 Parent(s): 54edc2a

Upload LongT5ForConditionalGeneration

Browse files
Files changed (3) hide show
  1. config.json +36 -0
  2. generation_config.json +7 -0
  3. model.safetensors +3 -0
config.json ADDED
@@ -0,0 +1,36 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "mlong-t5-tglobal-base-et-riigikogu/",
3
+ "architectures": [
4
+ "LongT5ForConditionalGeneration"
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
+ "encoder_attention_type": "transient-global",
13
+ "eos_token_id": 1,
14
+ "feed_forward_proj": "gated-gelu",
15
+ "global_block_size": 16,
16
+ "initializer_factor": 1.0,
17
+ "is_encoder_decoder": true,
18
+ "is_gated_act": true,
19
+ "layer_norm_epsilon": 1e-06,
20
+ "local_radius": 127,
21
+ "max_length": 2048,
22
+ "model_type": "longt5",
23
+ "n_positions": 4096,
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": "4.39.3",
34
+ "use_cache": true,
35
+ "vocab_size": 18171
36
+ }
generation_config.json ADDED
@@ -0,0 +1,7 @@
 
 
 
 
 
 
 
 
1
+ {
2
+ "decoder_start_token_id": 0,
3
+ "eos_token_id": 1,
4
+ "max_length": 2048,
5
+ "pad_token_id": 0,
6
+ "transformers_version": "4.39.3"
7
+ }
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:83936b239164ffdd3ffb81da526a3c3632b868c9199d35bd0a746c9e12681a9b
3
+ size 904634392