loiccabannes commited on
Commit
1564d21
1 Parent(s): a0c0d9d

model upload

Browse files
config.json ADDED
@@ -0,0 +1,10 @@
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "d_model": 1024,
3
+ "fused_add_norm": true,
4
+ "n_layer": 48,
5
+ "pad_vocab_size_multiple": 8,
6
+ "residual_in_fp32": true,
7
+ "rms_norm": true,
8
+ "ssm_cfg": {},
9
+ "vocab_size": 32000
10
+ }
pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:706f57b750567786c5bfd07753f1a499ca68a4d7a64a518bd30fc739ab29bc8d
3
+ size 709121042
special_tokens_map.json ADDED
@@ -0,0 +1,24 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": {
3
+ "content": "<|startoftext|>",
4
+ "lstrip": false,
5
+ "normalized": false,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "eos_token": {
10
+ "content": "<|endoftext|>",
11
+ "lstrip": false,
12
+ "normalized": false,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "pad_token": "<|endoftext|>",
17
+ "unk_token": {
18
+ "content": "<|endoftext|>",
19
+ "lstrip": false,
20
+ "normalized": false,
21
+ "rstrip": false,
22
+ "single_word": false
23
+ }
24
+ }
tokenizer_config.json ADDED
@@ -0,0 +1,28 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "added_tokens_decoder": {
3
+ "31996": {
4
+ "content": "<|startoftext|>",
5
+ "lstrip": false,
6
+ "normalized": false,
7
+ "rstrip": false,
8
+ "single_word": false,
9
+ "special": true
10
+ },
11
+ "31999": {
12
+ "content": "<|endoftext|>",
13
+ "lstrip": false,
14
+ "normalized": false,
15
+ "rstrip": false,
16
+ "single_word": false,
17
+ "special": true
18
+ }
19
+ },
20
+ "bos_token": "<|startoftext|>",
21
+ "clean_up_tokenization_spaces": true,
22
+ "do_clean_text": false,
23
+ "eos_token": "<|endoftext|>",
24
+ "model_max_length": 2048,
25
+ "pad_token": "<|endoftext|>",
26
+ "tokenizer_class": "GPTNeoXJapaneseTokenizer",
27
+ "unk_token": "<|endoftext|>"
28
+ }
vocab.txt ADDED
The diff for this file is too large to render. See raw diff