jungiebeen commited on
Commit
3d337ea
1 Parent(s): 9b871db

Upload BartForCausalLM

Browse files
Files changed (3) hide show
  1. config.json +38 -31
  2. generation_config.json +5 -2
  3. model.safetensors +2 -2
config.json CHANGED
@@ -1,39 +1,46 @@
1
  {
2
- "_name_or_path": "/workspace/pretraining/local-models/training/2024-02-01_15-15-06",
3
- "activation_function": "gelu_new",
 
4
  "architectures": [
5
- "GPT2LMHeadModel"
6
  ],
7
- "attn_pdrop": 0.0,
8
- "bos_token_id": 50256,
9
- "embd_pdrop": 0.0,
10
- "eos_token_id": 50256,
11
- "initializer_range": 0.02,
12
- "layer_norm_epsilon": 1e-05,
13
- "model_type": "gpt2",
14
- "n_ctx": 1024,
15
- "n_embd": 768,
16
- "n_head": 12,
17
- "n_inner": null,
18
- "n_layer": 20,
19
- "n_positions": 1024,
20
- "reorder_and_upcast_attn": false,
21
- "resid_pdrop": 0.0,
22
- "scale_attn_by_inverse_layer_idx": false,
23
- "scale_attn_weights": true,
24
- "summary_activation": null,
25
- "summary_first_dropout": 0.0,
26
- "summary_proj_to_labels": true,
27
- "summary_type": "cls_index",
28
- "summary_use_proj": true,
29
- "task_specific_params": {
30
- "text-generation": {
31
- "do_sample": true,
32
- "max_length": 50
33
- }
34
  },
 
 
 
 
 
 
 
 
 
 
 
 
 
35
  "torch_dtype": "float32",
36
  "transformers_version": "4.34.1",
37
  "use_cache": true,
38
- "vocab_size": 50257
39
  }
 
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
  }
generation_config.json CHANGED
@@ -1,6 +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
  }
 
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
  }
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:86fbefd2dab45a47244c54a712981e73d5d489a38e8c1312a08683921922da66
3
- size 724595976
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cb18b56acef83df3ee3316edcba6b91295355cfcccc9c412e51e702c9cffbe96
3
+ size 724724784