Hugging Face's logo

RichardErkhov
/
NexaAIDev_-_octo-net-4bits

Safetensors
phi3
custom_code
4-bit precision
bitsandbytes
Model card Files Community
RichardErkhov commited on
Commit
36d8f24
·
verified ·
1 Parent(s): 4dd10d1

uploaded model

Browse files
Files changed (1) hide show
  1. config.json +152 -0
config.json ADDED
@@ -0,0 +1,152 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "octo-net",
3
+ "architectures": [
4
+ "Phi3ForCausalLM"
5
+ ],
6
+ "attention_dropout": 0.0,
7
+ "auto_map": {
8
+ "AutoConfig": "configuration_phi3.Phi3Config",
9
+ "AutoModelForCausalLM": "modeling_phi3.Phi3ForCausalLM"
10
+ },
11
+ "bos_token_id": 1,
12
+ "embd_pdrop": 0.0,
13
+ "eos_token_id": 32000,
14
+ "hidden_act": "silu",
15
+ "hidden_size": 3072,
16
+ "initializer_range": 0.02,
17
+ "intermediate_size": 8192,
18
+ "max_position_embeddings": 131072,
19
+ "model_type": "phi3",
20
+ "num_attention_heads": 32,
21
+ "num_hidden_layers": 32,
22
+ "num_key_value_heads": 32,
23
+ "original_max_position_embeddings": 4096,
24
+ "pad_token_id": 32000,
25
+ "quantization_config": {
26
+ "_load_in_4bit": true,
27
+ "_load_in_8bit": false,
28
+ "bnb_4bit_compute_dtype": "float32",
29
+ "bnb_4bit_quant_storage": "uint8",
30
+ "bnb_4bit_quant_type": "fp4",
31
+ "bnb_4bit_use_double_quant": false,
32
+ "llm_int8_enable_fp32_cpu_offload": false,
33
+ "llm_int8_has_fp16_weight": false,
34
+ "llm_int8_skip_modules": null,
35
+ "llm_int8_threshold": 6.0,
36
+ "load_in_4bit": true,
37
+ "load_in_8bit": false,
38
+ "quant_method": "bitsandbytes"
39
+ },
40
+ "resid_pdrop": 0.0,
41
+ "rms_norm_eps": 1e-05,
42
+ "rope_scaling": {
43
+ "long_factor": [
44
+ 1.0299999713897705,
45
+ 1.0499999523162842,
46
+ 1.0499999523162842,
47
+ 1.0799999237060547,
48
+ 1.2299998998641968,
49
+ 1.2299998998641968,
50
+ 1.2999999523162842,
51
+ 1.4499999284744263,
52
+ 1.5999999046325684,
53
+ 1.6499998569488525,
54
+ 1.8999998569488525,
55
+ 2.859999895095825,
56
+ 3.68999981880188,
57
+ 5.419999599456787,
58
+ 5.489999771118164,
59
+ 5.489999771118164,
60
+ 9.09000015258789,
61
+ 11.579999923706055,
62
+ 15.65999984741211,
63
+ 15.769999504089355,
64
+ 15.789999961853027,
65
+ 18.360000610351562,
66
+ 21.989999771118164,
67
+ 23.079999923706055,
68
+ 30.009998321533203,
69
+ 32.35000228881836,
70
+ 32.590003967285156,
71
+ 35.56000518798828,
72
+ 39.95000457763672,
73
+ 53.840003967285156,
74
+ 56.20000457763672,
75
+ 57.95000457763672,
76
+ 59.29000473022461,
77
+ 59.77000427246094,
78
+ 59.920005798339844,
79
+ 61.190006256103516,
80
+ 61.96000671386719,
81
+ 62.50000762939453,
82
+ 63.3700065612793,
83
+ 63.48000717163086,
84
+ 63.48000717163086,
85
+ 63.66000747680664,
86
+ 63.850006103515625,
87
+ 64.08000946044922,
88
+ 64.760009765625,
89
+ 64.80001068115234,
90
+ 64.81001281738281,
91
+ 64.81001281738281
92
+ ],
93
+ "short_factor": [
94
+ 1.05,
95
+ 1.05,
96
+ 1.05,
97
+ 1.1,
98
+ 1.1,
99
+ 1.1500000000000001,
100
+ 1.2000000000000002,
101
+ 1.2500000000000002,
102
+ 1.3000000000000003,
103
+ 1.3500000000000003,
104
+ 1.5000000000000004,
105
+ 2.000000000000001,
106
+ 2.000000000000001,
107
+ 2.000000000000001,
108
+ 2.000000000000001,
109
+ 2.000000000000001,
110
+ 2.000000000000001,
111
+ 2.000000000000001,
112
+ 2.000000000000001,
113
+ 2.000000000000001,
114
+ 2.000000000000001,
115
+ 2.000000000000001,
116
+ 2.000000000000001,
117
+ 2.000000000000001,
118
+ 2.000000000000001,
119
+ 2.000000000000001,
120
+ 2.000000000000001,
121
+ 2.000000000000001,
122
+ 2.000000000000001,
123
+ 2.000000000000001,
124
+ 2.000000000000001,
125
+ 2.000000000000001,
126
+ 2.0500000000000007,
127
+ 2.0500000000000007,
128
+ 2.0500000000000007,
129
+ 2.1000000000000005,
130
+ 2.1000000000000005,
131
+ 2.1000000000000005,
132
+ 2.1500000000000004,
133
+ 2.1500000000000004,
134
+ 2.3499999999999996,
135
+ 2.549999999999999,
136
+ 2.5999999999999988,
137
+ 2.5999999999999988,
138
+ 2.7499999999999982,
139
+ 2.849999999999998,
140
+ 2.849999999999998,
141
+ 2.9499999999999975
142
+ ],
143
+ "type": "longrope"
144
+ },
145
+ "rope_theta": 10000.0,
146
+ "sliding_window": 262144,
147
+ "tie_word_embeddings": false,
148
+ "torch_dtype": "float16",
149
+ "transformers_version": "4.47.1",
150
+ "use_cache": true,
151
+ "vocab_size": 32064
152
+ }