Hugging Face's logo

breadlicker45
/
MusePy

Text Generation
Transformers
PyTorch
gpt_neox
text-generation-inference
Model card Files
xet
 Community
2
breadlicker45 commited on
Commit
f34c08a
·
1 Parent(s): dc09d65

Upload 4 files

Browse files
Files changed (3) hide show
  1. config.json +17 -46
  2. tokenizer.json +0 -0
  3. tokenizer_config.json +1 -1
config.json CHANGED
@@ -1,55 +1,26 @@
1
  {
2
- "_name_or_path": "breadlicker45/MuseNeo",
3
- "activation_function": "gelu_new",
4
  "architectures": [
5
- "GPTNeoForCausalLM"
6
  ],
7
- "attention_dropout": 0,
8
- "attention_layers": [
9
- "global",
10
- "local",
11
- "global",
12
- "local",
13
- "global",
14
- "local",
15
- "global",
16
- "local",
17
- "global",
18
- "local",
19
- "global",
20
- "local"
21
- ],
22
- "attention_types": [
23
- [
24
- [
25
- "global",
26
- "local"
27
- ],
28
- 6
29
- ]
30
- ],
31
- "bos_token_id": 50256,
32
- "embed_dropout": 0,
33
- "eos_token_id": 50256,
34
- "gradient_checkpointing": false,
35
- "hidden_size": 768,
36
  "initializer_range": 0.02,
37
- "intermediate_size": null,
38
- "layer_norm_epsilon": 1e-05,
39
  "line_by_line": true,
40
  "max_position_embeddings": 2048,
41
- "model_type": "pythia",
42
- "num_heads": 12,
43
- "num_layers": 12,
44
- "resid_dropout": 0,
45
- "summary_activation": null,
46
- "summary_first_dropout": 0.1,
47
- "summary_proj_to_labels": true,
48
- "summary_type": "cls_index",
49
- "summary_use_proj": true,
50
  "torch_dtype": "float32",
51
- "transformers_version": "4.20.1",
52
  "use_cache": true,
53
- "vocab_size": 50257,
54
- "window_size": 256
55
  }
 
1
  {
2
+ "_name_or_path": "EleutherAI/pythia-19m",
 
3
  "architectures": [
4
+ "GPTNeoXForCausalLM"
5
  ],
6
+ "bos_token_id": 0,
7
+ "eos_token_id": 0,
8
+ "hidden_act": "gelu",
9
+ "hidden_size": 512,
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
10
  "initializer_range": 0.02,
11
+ "intermediate_size": 2048,
12
+ "layer_norm_eps": 1e-05,
13
  "line_by_line": true,
14
  "max_position_embeddings": 2048,
15
+ "model_type": "gpt_neox",
16
+ "num_attention_heads": 8,
17
+ "num_hidden_layers": 6,
18
+ "rotary_emb_base": 10000,
19
+ "rotary_pct": 0.25,
20
+ "tie_word_embeddings": false,
 
 
 
21
  "torch_dtype": "float32",
22
+ "transformers_version": "4.25.1",
23
  "use_cache": true,
24
+ "use_parallel_residual": true,
25
+ "vocab_size": 50304
26
  }
tokenizer.json CHANGED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json CHANGED
@@ -1,5 +1,5 @@
1
  {
2
- "name_or_path": "EleutherAI/pythia-19m",
3
  "eos_token": "<|endoftext|>",
4
  "pad_token": "<|endoftext|>",
5
  "tokenizer_class": "PreTrainedTokenizerFast"
 
1
  {
2
+ "name_or_path": "EleutherAI/polyglot-ko-1.3b",
3
  "eos_token": "<|endoftext|>",
4
  "pad_token": "<|endoftext|>",
5
  "tokenizer_class": "PreTrainedTokenizerFast"