khangnguyen2907 commited on
Commit
d3816a6
·
1 Parent(s): 79592a7

Upload MT5LSAAlibiForConditionalGeneration

Browse files
Files changed (3) hide show
  1. config.json +33 -0
  2. generation_config.json +7 -0
  3. model.safetensors +3 -0
config.json ADDED
@@ -0,0 +1,33 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "artifacts/model_trainer/mt5_large_lsa_alibi/v1/checkpoint-190500",
3
+ "alibi_type": "sym",
4
+ "architectures": [
5
+ "MT5LSAAlibiForConditionalGeneration"
6
+ ],
7
+ "classifier_dropout": 0.0,
8
+ "d_ff": 2816,
9
+ "d_kv": 64,
10
+ "d_model": 512,
11
+ "decoder_start_token_id": 0,
12
+ "dense_act_fn": "gelu_new",
13
+ "dropout_rate": 0.0,
14
+ "eos_token_id": 1,
15
+ "feed_forward_proj": "gated-gelu",
16
+ "initializer_factor": 1.0,
17
+ "is_encoder_decoder": true,
18
+ "is_gated_act": true,
19
+ "layer_norm_epsilon": 1e-06,
20
+ "lsa_sparsity": 6,
21
+ "model_type": "mt5",
22
+ "num_decoder_layers": 24,
23
+ "num_heads": 16,
24
+ "num_layers": 24,
25
+ "output_past": true,
26
+ "pad_token_id": 0,
27
+ "tie_word_embeddings": false,
28
+ "tokenizer_class": "T5Tokenizer",
29
+ "torch_dtype": "float32",
30
+ "transformers_version": "4.35.0",
31
+ "use_cache": true,
32
+ "vocab_size": 250112
33
+ }
generation_config.json ADDED
@@ -0,0 +1,7 @@
 
 
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "decoder_start_token_id": 0,
4
+ "eos_token_id": 1,
5
+ "pad_token_id": 0,
6
+ "transformers_version": "4.35.0"
7
+ }
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:492aa17196f370b69563b5ed4a757172ee5c9514d6942d1b7cce7d037d14e661
3
+ size 2291402448