Hugging Face's logo

Kooltek68
/
sn9_153

Text Generation
Transformers
Safetensors
bart
Inference Endpoints
Model card Files Community
Kooltek68 commited on
Commit
ac16043
•
1 Parent(s): a2b41f6

Upload BartForCausalLM

Browse files
Files changed (3) hide show
  1. config.json +36 -19
  2. generation_config.json +4 -1
  3. model.safetensors +2 -2
config.json CHANGED
@@ -1,29 +1,46 @@
1
  {
2
- "_name_or_path": "/dev/shm/checkpoints-pythia/checkpoint-500",
 
 
3
  "architectures": [
4
- "GPTNeoXForCausalLM"
5
  ],
6
  "attention_dropout": 0.0,
7
  "bos_token_id": 0,
8
- "classifier_dropout": 0.1,
9
- "eos_token_id": 0,
10
- "hidden_act": "gelu",
11
- "hidden_dropout": 0.0,
12
- "hidden_size": 768,
13
- "initializer_range": 0.02,
14
- "intermediate_size": 3072,
15
- "layer_norm_eps": 1e-05,
16
- "max_position_embeddings": 2048,
17
- "model_type": "gpt_neox",
18
- "num_attention_heads": 12,
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
19
  "num_hidden_layers": 15,
20
- "rope_scaling": null,
21
- "rotary_emb_base": 10000,
22
- "rotary_pct": 0.25,
23
- "tie_word_embeddings": false,
24
  "torch_dtype": "float32",
25
  "transformers_version": "4.34.1",
26
  "use_cache": true,
27
- "use_parallel_residual": true,
28
- "vocab_size": 50304
29
  }
 
1
  {
2
+ "_name_or_path": "/dev/shm/checkpoints-bart/checkpoint-7000",
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": 0,
4
- "eos_token_id": 0,
 
 
 
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:b60cfc2abed97a1fec53b9c9940ae1924433d64b624c98b017db17e561243f12
3
- size 734369568
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b524d5be9ce6779f855ac8d8fb75004847cd7c5a76bc45608196aebfef7bb730
3
+ size 724724784