Kooltek68 commited on
Commit
85ace4d
1 Parent(s): 31ded56

Upload BartForCausalLM

Browse files
Files changed (3) hide show
  1. config.json +36 -18
  2. generation_config.json +4 -1
  3. model.safetensors +2 -2
config.json CHANGED
@@ -1,28 +1,46 @@
1
  {
2
- "_name_or_path": "/dev/shm/falcon-refinedweb/checkpoints-gpt2-best4-180M/checkpoint-1000",
 
 
3
  "architectures": [
4
- "LlamaForCausalLM"
5
  ],
6
- "attention_bias": false,
7
  "attention_dropout": 0.0,
8
- "bos_token_id": 1,
 
 
 
 
 
 
 
 
 
 
 
 
9
  "eos_token_id": 2,
10
- "hidden_act": "silu",
11
- "hidden_size": 768,
12
- "initializer_range": 0.02,
13
- "intermediate_size": 2000,
 
 
 
 
 
 
 
 
 
 
14
  "max_position_embeddings": 1024,
15
- "model_type": "llama",
16
- "num_attention_heads": 12,
17
- "num_hidden_layers": 20,
18
- "num_key_value_heads": 12,
19
- "pretraining_tp": 1,
20
- "rms_norm_eps": 1e-06,
21
- "rope_scaling": null,
22
- "rope_theta": 10000.0,
23
- "tie_word_embeddings": true,
24
  "torch_dtype": "float32",
25
  "transformers_version": "4.34.1",
26
  "use_cache": true,
27
- "vocab_size": 50257
28
  }
 
1
  {
2
+ "_name_or_path": "/dev/shm/checkpoints-bart/checkpoint-4500",
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": 1,
 
4
  "eos_token_id": 2,
 
 
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 sha256:8a8f04ee1ee53861c6803e33af97651627309da60c4b1aab6d1bcd4c28c0eae7
3
- size 711919432
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6f4fce4a50576cbe2c1ea3ee5029f8776446e1f4a4d8f35a5077c1151ee42bc3
3
+ size 724724784