RichardErkhov commited on
Commit
4fe0025
1 Parent(s): 407e723

uploaded model

Browse files
Files changed (1) hide show
  1. config.json +70 -0
config.json ADDED
@@ -0,0 +1,70 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "gpt-neo-125M-dutch",
3
+ "activation_function": "gelu_new",
4
+ "architectures": [
5
+ "GPTNeoForCausalLM"
6
+ ],
7
+ "attention_dropout": 0.0,
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
+ "classifier_dropout": 0.1,
33
+ "embed_dropout": 0.0,
34
+ "eos_token_id": 50256,
35
+ "gradient_checkpointing": false,
36
+ "hidden_size": 768,
37
+ "initializer_range": 0.02,
38
+ "intermediate_size": null,
39
+ "layer_norm_epsilon": 1e-05,
40
+ "max_position_embeddings": 2048,
41
+ "model_type": "gpt_neo",
42
+ "num_heads": 12,
43
+ "num_layers": 12,
44
+ "quantization_config": {
45
+ "_load_in_4bit": false,
46
+ "_load_in_8bit": true,
47
+ "bnb_4bit_compute_dtype": "float32",
48
+ "bnb_4bit_quant_storage": "uint8",
49
+ "bnb_4bit_quant_type": "fp4",
50
+ "bnb_4bit_use_double_quant": false,
51
+ "llm_int8_enable_fp32_cpu_offload": false,
52
+ "llm_int8_has_fp16_weight": false,
53
+ "llm_int8_skip_modules": null,
54
+ "llm_int8_threshold": 6.0,
55
+ "load_in_4bit": false,
56
+ "load_in_8bit": true,
57
+ "quant_method": "bitsandbytes"
58
+ },
59
+ "resid_dropout": 0,
60
+ "summary_activation": null,
61
+ "summary_first_dropout": 0.1,
62
+ "summary_proj_to_labels": true,
63
+ "summary_type": "cls_index",
64
+ "summary_use_proj": true,
65
+ "torch_dtype": "float16",
66
+ "transformers_version": "4.42.4",
67
+ "use_cache": true,
68
+ "vocab_size": 50257,
69
+ "window_size": 256
70
+ }