pszemraj commited on
Commit
600b66e
1 Parent(s): eec6fe7

add base model

Browse files
Files changed (3) hide show
  1. config.json +36 -0
  2. pytorch_model.bin +3 -0
  3. training_args.bin +3 -0
config.json ADDED
@@ -0,0 +1,36 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "pszemraj/grammar-synthesis-small-WIP",
3
+ "architectures": [
4
+ "T5ForConditionalGeneration"
5
+ ],
6
+ "d_ff": 1024,
7
+ "d_kv": 64,
8
+ "d_model": 512,
9
+ "decoder_start_token_id": 0,
10
+ "dense_act_fn": "gelu_new",
11
+ "dropout_rate": 0.1,
12
+ "early_stopping": true,
13
+ "eos_token_id": 1,
14
+ "feed_forward_proj": "gated-gelu",
15
+ "initializer_factor": 1.0,
16
+ "is_encoder_decoder": true,
17
+ "is_gated_act": true,
18
+ "layer_norm_epsilon": 1e-06,
19
+ "max_length": 512,
20
+ "min_length": 8,
21
+ "model_type": "t5",
22
+ "no_repeat_ngram_size": 4,
23
+ "num_beams": 2,
24
+ "num_decoder_layers": 8,
25
+ "num_heads": 6,
26
+ "num_layers": 8,
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": "4.20.1",
34
+ "use_cache": false,
35
+ "vocab_size": 32128
36
+ }
pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:34fe1a08a3fee9281998bcda50786c3204e87f86e462d3306ed58949a3a0cd1c
3
+ size 307871851
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1a2fb1c2d8e00e8ab84642e74fb6a8be3a56cd4bec08a18d225c629ed406a17c
3
+ size 4527