Your Name commited on
Commit
1bd6a5f
1 Parent(s): 98c533d

PT and FT models added

Browse files
Files changed (3) hide show
  1. config.json +35 -30
  2. flax_model.msgpack +3 -0
  3. pytorch_model.bin +3 -0
config.json CHANGED
@@ -1,31 +1,36 @@
1
  {
2
- "_name_or_path": "./",
3
- "architectures": [
4
- "T5ForConditionalGeneration"
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
- "eos_token_id": 1,
13
- "feed_forward_proj": "gated-gelu",
14
- "initializer_factor": 1.0,
15
- "is_encoder_decoder": true,
16
- "is_gated_act": true,
17
- "layer_norm_epsilon": 1e-06,
18
- "model_type": "t5",
19
- "num_decoder_layers": 12,
20
- "num_heads": 12,
21
- "num_layers": 12,
22
- "output_past": true,
23
- "pad_token_id": 0,
24
- "relative_attention_max_distance": 128,
25
- "relative_attention_num_buckets": 32,
26
- "tie_word_embeddings": false,
27
- "torch_dtype": "float32",
28
- "transformers_version": "4.23.1",
29
- "use_cache": true,
30
- "vocab_size": 32128
31
- }
 
 
 
 
 
 
1
  {
2
+ "_name_or_path": ".",
3
+ "architectures": [
4
+ "T5ForConditionalGeneration"
5
+ ],
6
+ "classifier_dropout": 0.0,
7
+ "d_ff": 1024,
8
+ "d_kv": 64,
9
+ "d_model": 512,
10
+ "decoder_start_token_id": 0,
11
+ "dense_act_fn": "gelu_new",
12
+ "dropout_rate": 0.1,
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": 64,
20
+ "model_type": "t5",
21
+ "n_positions": 512,
22
+ "num_beams": 4,
23
+ "num_decoder_layers": 8,
24
+ "num_heads": 6,
25
+ "num_layers": 8,
26
+ "output_past": true,
27
+ "pad_token_id": 0,
28
+ "relative_attention_max_distance": 128,
29
+ "relative_attention_num_buckets": 32,
30
+ "tie_word_embeddings": false,
31
+ "torch_dtype": "float32",
32
+ "transformers_version": "4.34.0",
33
+ "use_cache": true,
34
+ "use_fast": false,
35
+ "vocab_size": 32128
36
+ }
flax_model.msgpack ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:673a146bce1ac9c36df4420f82694a985cc48d94c323f8736ace1cac0af38703
3
+ size 307852839
pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:12a7fce4133dcd5246af47244a9cc92a1788a4d88de985e15f418b59c739c6c6
3
+ size 307907906