PhTae commited on
Commit
a37a30f
·
verified ·
1 Parent(s): 21a0146

Upload folder using huggingface_hub

Browse files
Files changed (3) hide show
  1. config.json +7 -6
  2. generation_config.json +1 -1
  3. model.safetensors +2 -2
config.json CHANGED
@@ -1,11 +1,12 @@
1
  {
 
2
  "architectures": [
3
  "T5ForConditionalGeneration"
4
  ],
5
  "classifier_dropout": 0.0,
6
- "d_ff": 2816,
7
  "d_kv": 64,
8
- "d_model": 1024,
9
  "decoder_start_token_id": 0,
10
  "dense_act_fn": "gelu_new",
11
  "dropout_rate": 0.1,
@@ -16,16 +17,16 @@
16
  "is_gated_act": true,
17
  "layer_norm_epsilon": 1e-06,
18
  "model_type": "t5",
19
- "num_decoder_layers": 24,
20
- "num_heads": 16,
21
- "num_layers": 24,
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": "4.51.3",
29
  "use_cache": true,
30
  "vocab_size": 32128
31
  }
 
1
  {
2
+ "_name_or_path": "outputs_pretrained_truepair/2025-05-01-06-05-26_32_4/30_model/",
3
  "architectures": [
4
  "T5ForConditionalGeneration"
5
  ],
6
  "classifier_dropout": 0.0,
7
+ "d_ff": 2048,
8
  "d_kv": 64,
9
+ "d_model": 768,
10
  "decoder_start_token_id": 0,
11
  "dense_act_fn": "gelu_new",
12
  "dropout_rate": 0.1,
 
17
  "is_gated_act": true,
18
  "layer_norm_epsilon": 1e-06,
19
  "model_type": "t5",
20
+ "num_decoder_layers": 12,
21
+ "num_heads": 12,
22
+ "num_layers": 12,
23
  "output_past": true,
24
  "pad_token_id": 0,
25
  "relative_attention_max_distance": 128,
26
  "relative_attention_num_buckets": 32,
27
  "tie_word_embeddings": false,
28
  "torch_dtype": "float32",
29
+ "transformers_version": "4.46.3",
30
  "use_cache": true,
31
  "vocab_size": 32128
32
  }
generation_config.json CHANGED
@@ -3,5 +3,5 @@
3
  "decoder_start_token_id": 0,
4
  "eos_token_id": 1,
5
  "pad_token_id": 0,
6
- "transformers_version": "4.51.3"
7
  }
 
3
  "decoder_start_token_id": 0,
4
  "eos_token_id": 1,
5
  "pad_token_id": 0,
6
+ "transformers_version": "4.46.3"
7
  }
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:c845f539bb4d222f7d3906b868e124965202c9cdac0de861ec838db854d68218
3
- size 3132668808
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cd78a774daf0e0104df43467b51ebab771e7a2109a68f9c5f3c4d88e50662a4d
3
+ size 990345064