Jumtra commited on
Commit
4991616
1 Parent(s): bb653b2

Upload folder using huggingface_hub

Browse files
config.json ADDED
@@ -0,0 +1,26 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "GPTNeoXForCausalLM"
4
+ ],
5
+ "bos_token_id": 2,
6
+ "classifier_dropout": 0.1,
7
+ "eos_token_id": 3,
8
+ "hidden_act": "gelu",
9
+ "hidden_size": 2816,
10
+ "init_device": "cpu",
11
+ "initializer_range": 0.02,
12
+ "intermediate_size": 11264,
13
+ "layer_norm_eps": 1e-05,
14
+ "max_position_embeddings": 2048,
15
+ "model_type": "gpt_neox",
16
+ "num_attention_heads": 22,
17
+ "num_hidden_layers": 36,
18
+ "rotary_emb_base": 10000,
19
+ "rotary_pct": 1.0,
20
+ "tie_word_embeddings": false,
21
+ "torch_dtype": "bfloat16",
22
+ "transformers_version": "4.30.2",
23
+ "use_cache": true,
24
+ "use_parallel_residual": false,
25
+ "vocab_size": 32000
26
+ }
generation_config.json ADDED
@@ -0,0 +1,6 @@
 
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "bos_token_id": 2,
4
+ "eos_token_id": 3,
5
+ "transformers_version": "4.30.2"
6
+ }
pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:38a927b65e0a917d34da12148fcad24501741898fbc849ccca34be2164a3e165
3
+ size 7365674005
special_tokens_map.json ADDED
@@ -0,0 +1,9 @@
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": "<s>",
3
+ "cls_token": "[CLS]",
4
+ "eos_token": "</s>",
5
+ "mask_token": "[MASK]",
6
+ "pad_token": "[PAD]",
7
+ "sep_token": "[SEP]",
8
+ "unk_token": "[UNK]"
9
+ }
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1,16 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "additional_special_tokens": [],
3
+ "bos_token": "<s>",
4
+ "clean_up_tokenization_spaces": true,
5
+ "cls_token": "[CLS]",
6
+ "do_lower_case": false,
7
+ "eos_token": "</s>",
8
+ "extra_ids": 0,
9
+ "mask_token": "[MASK]",
10
+ "model_max_length": 2048,
11
+ "pad_token": "[PAD]",
12
+ "sep_token": "[SEP]",
13
+ "sp_model_kwargs": {},
14
+ "tokenizer_class": "T5Tokenizer",
15
+ "unk_token": "[UNK]"
16
+ }