jungiebeen commited on
Commit
c56f706
·
verified ·
1 Parent(s): 735e716

Upload model

Browse files
Files changed (3) hide show
  1. config.json +25 -39
  2. generation_config.json +2 -5
  3. model.safetensors +2 -2
config.json CHANGED
@@ -1,46 +1,32 @@
1
  {
2
- "_name_or_path": "/workspace/pretraining/local-models/training/2024-02-05_15-45-02",
3
- "activation_dropout": 0.0,
4
- "activation_function": "gelu",
5
  "architectures": [
6
- "BartForCausalLM"
7
  ],
8
- "attention_dropout": 0.0,
9
- "bos_token_id": 0,
10
- "classifier_dropout": 0.0,
11
- "d_model": 768,
12
- "decoder_attention_heads": 12,
13
- "decoder_ffn_dim": 3072,
14
- "decoder_layerdrop": 0.0,
15
- "decoder_layers": 15,
16
- "decoder_start_token_id": 2,
17
- "dropout": 0.1,
18
- "encoder_attention_heads": 12,
19
- "encoder_ffn_dim": 3072,
20
- "encoder_layerdrop": 0.0,
21
- "encoder_layers": 15,
22
- "eos_token_id": 2,
23
- "forced_eos_token_id": 2,
24
- "id2label": {
25
- "0": "LABEL_0",
26
- "1": "LABEL_1",
27
- "2": "LABEL_2"
28
- },
29
- "init_std": 0.02,
30
- "is_decoder": true,
31
- "is_encoder_decoder": false,
32
- "label2id": {
33
- "LABEL_0": 0,
34
- "LABEL_1": 1,
35
- "LABEL_2": 2
36
- },
37
- "max_position_embeddings": 1024,
38
- "model_type": "bart",
39
- "num_hidden_layers": 15,
40
- "pad_token_id": 1,
41
- "scale_embedding": false,
42
  "torch_dtype": "float32",
43
  "transformers_version": "4.34.1",
44
  "use_cache": true,
45
- "vocab_size": 50265
46
  }
 
1
  {
2
+ "_name_or_path": "/workspace/new/pretraining/local-models/training/new",
3
+ "activation_function": "gelu_new",
 
4
  "architectures": [
5
+ "GPT2LMHeadModel"
6
  ],
7
+ "attn_pdrop": 0.1,
8
+ "bos_token_id": 50256,
9
+ "embd_pdrop": 0.1,
10
+ "eos_token_id": 50256,
11
+ "initializer_range": 0.02,
12
+ "layer_norm_epsilon": 1e-05,
13
+ "model_type": "gpt2",
14
+ "n_embd": 1000,
15
+ "n_head": 10,
16
+ "n_inner": null,
17
+ "n_layer": 16,
18
+ "n_positions": 1024,
19
+ "reorder_and_upcast_attn": false,
20
+ "resid_pdrop": 0.1,
21
+ "scale_attn_by_inverse_layer_idx": false,
22
+ "scale_attn_weights": true,
23
+ "summary_activation": null,
24
+ "summary_first_dropout": 0.1,
25
+ "summary_proj_to_labels": true,
26
+ "summary_type": "cls_index",
27
+ "summary_use_proj": true,
 
 
 
 
 
 
 
 
 
 
 
 
 
28
  "torch_dtype": "float32",
29
  "transformers_version": "4.34.1",
30
  "use_cache": true,
31
+ "vocab_size": 50257
32
  }
generation_config.json CHANGED
@@ -1,9 +1,6 @@
1
  {
2
  "_from_model_config": true,
3
- "bos_token_id": 0,
4
- "decoder_start_token_id": 2,
5
- "eos_token_id": 2,
6
- "forced_eos_token_id": 2,
7
- "pad_token_id": 1,
8
  "transformers_version": "4.34.1"
9
  }
 
1
  {
2
  "_from_model_config": true,
3
+ "bos_token_id": 50256,
4
+ "eos_token_id": 50256,
 
 
 
5
  "transformers_version": "4.34.1"
6
  }
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:cb18b56acef83df3ee3316edcba6b91295355cfcccc9c412e51e702c9cffbe96
3
- size 724724784
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:182cb7a86f16722f406c94a7677fc8502fa46caa88e6423d5474ed81a141d647
3
+ size 973984144