antphb commited on
Commit
3f07230
1 Parent(s): cecfc56

Training in progress, step 200

Browse files
.gitattributes CHANGED
@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
33
  *.zip filter=lfs diff=lfs merge=lfs -text
34
  *.zst filter=lfs diff=lfs merge=lfs -text
35
  *tfevents* filter=lfs diff=lfs merge=lfs -text
 
 
33
  *.zip filter=lfs diff=lfs merge=lfs -text
34
  *.zst filter=lfs diff=lfs merge=lfs -text
35
  *tfevents* filter=lfs diff=lfs merge=lfs -text
36
+ tokenizer.json filter=lfs diff=lfs merge=lfs -text
.gitignore ADDED
@@ -0,0 +1 @@
 
 
1
+ checkpoint-*/
config.json ADDED
@@ -0,0 +1,27 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "antphb/DS-Chatbox-facebook-xglm-564M-V3",
3
+ "activation_dropout": 0,
4
+ "activation_function": "gelu",
5
+ "architectures": [
6
+ "XGLMForCausalLM"
7
+ ],
8
+ "attention_dropout": 0.1,
9
+ "attention_heads": 16,
10
+ "bos_token_id": 0,
11
+ "d_model": 1024,
12
+ "decoder_start_token_id": 2,
13
+ "dropout": 0.1,
14
+ "eos_token_id": 2,
15
+ "ffn_dim": 4096,
16
+ "init_std": 0.02,
17
+ "layerdrop": 0.0,
18
+ "max_position_embeddings": 2048,
19
+ "model_type": "xglm",
20
+ "num_layers": 24,
21
+ "pad_token_id": 1,
22
+ "scale_embedding": true,
23
+ "torch_dtype": "float32",
24
+ "transformers_version": "4.30.2",
25
+ "use_cache": false,
26
+ "vocab_size": 256008
27
+ }
pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ae98e83cd805dd82896e7689b21dcb09b646bde2af0d69c14076340810e42237
3
+ size 2257982617
special_tokens_map.json ADDED
@@ -0,0 +1,17 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "additional_special_tokens": [
3
+ "<madeupword0>",
4
+ "<madeupword1>",
5
+ "<madeupword2>",
6
+ "<madeupword3>",
7
+ "<madeupword4>",
8
+ "<madeupword5>",
9
+ "<madeupword6>"
10
+ ],
11
+ "bos_token": "<s>",
12
+ "cls_token": "<s>",
13
+ "eos_token": "</s>",
14
+ "pad_token": "</s>",
15
+ "sep_token": "</s>",
16
+ "unk_token": "<unk>"
17
+ }
tokenizer.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:00d163342a36b3ad1ea2f5f608e6bb2b2ff29bd453a41c4f52525a7ebc7c4b6a
3
+ size 17210041
tokenizer_config.json ADDED
@@ -0,0 +1,21 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "additional_special_tokens": [
3
+ "<madeupword0>",
4
+ "<madeupword1>",
5
+ "<madeupword2>",
6
+ "<madeupword3>",
7
+ "<madeupword4>",
8
+ "<madeupword5>",
9
+ "<madeupword6>"
10
+ ],
11
+ "bos_token": "<s>",
12
+ "clean_up_tokenization_spaces": true,
13
+ "cls_token": "<s>",
14
+ "eos_token": "</s>",
15
+ "model_max_length": 2048,
16
+ "pad_token": "<pad>",
17
+ "sep_token": "</s>",
18
+ "sp_model_kwargs": {},
19
+ "tokenizer_class": "XGLMTokenizer",
20
+ "unk_token": "<unk>"
21
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:439b7946d0af1594330e4354ee4ae3530100b57bbe96d67842ff9507539649f3
3
+ size 3963