Aobangaming commited on
Commit
fb71a37
·
verified ·
1 Parent(s): c7b961e

Upload folder using huggingface_hub

Browse files
config.json ADDED
@@ -0,0 +1,13 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "model_type": "lightning",
3
+ "vocab_size": 65830,
4
+ "d_model": 256,
5
+ "nhead": 4,
6
+ "num_layers": 4,
7
+ "dropout": 0.1,
8
+ "max_seq_len": 160,
9
+ "auto_map": {
10
+ "AutoConfig": "configuration_lightning.LightningConfig",
11
+ "AutoModelForCausalLM": "modeling_lightning.LightningForCausalLM"
12
+ }
13
+ }
configuration_luna copy.py ADDED
@@ -0,0 +1,29 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ from transformers import PretrainedConfig
2
+
3
+
4
+ class LightningConfig(PretrainedConfig):
5
+ model_type = "lightning"
6
+
7
+ def __init__(
8
+ self,
9
+ vocab_size=75000,
10
+ d_model=256,
11
+ nhead=4,
12
+ num_layers=6,
13
+ dropout=0.1,
14
+ max_seq_len=200,
15
+ **kwargs
16
+ ):
17
+ kwargs.setdefault("tie_word_embeddings", False)
18
+ super().__init__(**kwargs)
19
+
20
+ self.vocab_size = vocab_size
21
+ self.d_model = d_model
22
+ self.nhead = nhead
23
+ self.num_layers = num_layers
24
+ self.dropout = dropout
25
+ self.max_seq_len = max_seq_len
26
+
27
+ self.num_hidden_layers = num_layers
28
+ self.num_attention_heads = nhead
29
+ self.hidden_size = d_model
configuration_luna.py ADDED
@@ -0,0 +1,29 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ from transformers import PretrainedConfig
2
+
3
+
4
+ class LightningConfig(PretrainedConfig):
5
+ model_type = "lightning"
6
+
7
+ def __init__(
8
+ self,
9
+ vocab_size=75000,
10
+ d_model=256,
11
+ nhead=4,
12
+ num_layers=6,
13
+ dropout=0.1,
14
+ max_seq_len=200,
15
+ **kwargs
16
+ ):
17
+ kwargs.setdefault("tie_word_embeddings", False)
18
+ super().__init__(**kwargs)
19
+
20
+ self.vocab_size = vocab_size
21
+ self.d_model = d_model
22
+ self.nhead = nhead
23
+ self.num_layers = num_layers
24
+ self.dropout = dropout
25
+ self.max_seq_len = max_seq_len
26
+
27
+ self.num_hidden_layers = num_layers
28
+ self.num_attention_heads = nhead
29
+ self.hidden_size = d_model
luna_tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8ee65b783e97db03f9167748c7f4e636eed773aa48474aabdbef45dece730893
3
+ size 172775680