RichardErkhov commited on
Commit
c2a6853
1 Parent(s): afbf394

uploaded model

Browse files
Files changed (1) hide show
  1. config.json +62 -0
config.json ADDED
@@ -0,0 +1,62 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "MagicPrompt-tinystories-33M-epoch10-merged",
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
+ ],
14
+ "attention_types": [
15
+ [
16
+ [
17
+ "global",
18
+ "local"
19
+ ],
20
+ 2
21
+ ]
22
+ ],
23
+ "bos_token_id": 50256,
24
+ "classifier_dropout": 0.1,
25
+ "embed_dropout": 0,
26
+ "eos_token_id": 50256,
27
+ "gradient_checkpointing": false,
28
+ "hidden_size": 768,
29
+ "initializer_range": 0.02,
30
+ "intermediate_size": null,
31
+ "layer_norm_epsilon": 1e-05,
32
+ "max_position_embeddings": 2048,
33
+ "model_type": "gpt_neo",
34
+ "num_heads": 16,
35
+ "num_layers": 4,
36
+ "quantization_config": {
37
+ "_load_in_4bit": true,
38
+ "_load_in_8bit": false,
39
+ "bnb_4bit_compute_dtype": "float32",
40
+ "bnb_4bit_quant_storage": "uint8",
41
+ "bnb_4bit_quant_type": "fp4",
42
+ "bnb_4bit_use_double_quant": false,
43
+ "llm_int8_enable_fp32_cpu_offload": false,
44
+ "llm_int8_has_fp16_weight": false,
45
+ "llm_int8_skip_modules": null,
46
+ "llm_int8_threshold": 6.0,
47
+ "load_in_4bit": true,
48
+ "load_in_8bit": false,
49
+ "quant_method": "bitsandbytes"
50
+ },
51
+ "resid_dropout": 0,
52
+ "summary_activation": null,
53
+ "summary_first_dropout": 0.1,
54
+ "summary_proj_to_labels": true,
55
+ "summary_type": "cls_index",
56
+ "summary_use_proj": true,
57
+ "torch_dtype": "float16",
58
+ "transformers_version": "4.42.4",
59
+ "use_cache": true,
60
+ "vocab_size": 50257,
61
+ "window_size": 256
62
+ }