pszemraj commited on
Commit
fde2b53
1 Parent(s): d54e442

add base model

Browse files
Files changed (3) hide show
  1. config.json +34 -0
  2. pytorch_model.bin +3 -0
  3. training_args.bin +3 -0
config.json ADDED
@@ -0,0 +1,34 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "pszemraj/t5-v1_1-L-semantic-analyzer-14E",
3
+ "architectures": [
4
+ "T5ForConditionalGeneration"
5
+ ],
6
+ "d_ff": 2816,
7
+ "d_kv": 64,
8
+ "d_model": 1024,
9
+ "decoder_start_token_id": 0,
10
+ "dropout_rate": 0.1,
11
+ "early_stopping": true,
12
+ "eos_token_id": 1,
13
+ "feed_forward_proj": "gated-gelu",
14
+ "initializer_factor": 1.0,
15
+ "is_encoder_decoder": true,
16
+ "layer_norm_epsilon": 1e-06,
17
+ "length_penalty": 3.5,
18
+ "max_length": 512,
19
+ "min_length": 32,
20
+ "model_type": "t5",
21
+ "no_repeat_ngram_size": 3,
22
+ "num_beams": 5,
23
+ "num_decoder_layers": 24,
24
+ "num_heads": 16,
25
+ "num_layers": 24,
26
+ "output_past": true,
27
+ "pad_token_id": 0,
28
+ "relative_attention_num_buckets": 32,
29
+ "tie_word_embeddings": false,
30
+ "torch_dtype": "float32",
31
+ "transformers_version": "4.16.2",
32
+ "use_cache": false,
33
+ "vocab_size": 32128
34
+ }
pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:87c946bc47744b6b719856687c2d90524b9e6e761ac4a2c41480d98b3e1ad984
3
+ size 3132743659
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7dc1ff76d444b0b8474c01c33c1344e8380efc63f50e72d4115aa51db16d0156
3
+ size 4207