kevin510 commited on
Commit
ad849ba
·
verified ·
1 Parent(s): 482b5e0

upload model

Browse files
Files changed (3) hide show
  1. config.json +180 -0
  2. generation_config.json +10 -0
  3. model.safetensors +3 -0
config.json ADDED
@@ -0,0 +1,180 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_cfg_special_tokens": {
3
+ "image_end_token_id": 200031,
4
+ "image_start_token_id": 200030,
5
+ "image_token_id": 200029
6
+ },
7
+ "_cfg_vision_adapter": {
8
+ "activation": "gelu",
9
+ "hidden_dim": 3072,
10
+ "input_dim": 6144,
11
+ "num_layers": 2,
12
+ "output_dim": 3072
13
+ },
14
+ "_cfg_vision_tower": {
15
+ "model_params": {
16
+ "trust_remote_code": true
17
+ },
18
+ "pad_to_square": true,
19
+ "pretrained_model_name_or_path": "kevin510/fast-vit-hd",
20
+ "s2_scales": "512,1024",
21
+ "type": "fastvit",
22
+ "use_s2": true
23
+ },
24
+ "architectures": [
25
+ "FridayForCausalLM"
26
+ ],
27
+ "attention_bias": false,
28
+ "attention_dropout": 0.0,
29
+ "auto_map": {
30
+ "AutoConfig": "microsoft/Phi-4-mini-instruct--configuration_phi3.Phi3Config",
31
+ "AutoModelForCausalLM": "microsoft/Phi-4-mini-instruct--modeling_phi3.Phi3ForCausalLM"
32
+ },
33
+ "bos_token_id": 199999,
34
+ "delay_load": false,
35
+ "embd_pdrop": 0.0,
36
+ "eos_token_id": 199999,
37
+ "full_attn_mod": 1,
38
+ "hidden_act": "silu",
39
+ "hidden_size": 3072,
40
+ "initializer_range": 0.02,
41
+ "intermediate_size": 8192,
42
+ "interpolate_factor": 1,
43
+ "lm_head_bias": false,
44
+ "max_position_embeddings": 131072,
45
+ "mlp_bias": false,
46
+ "model_type": "friday-phi",
47
+ "num_attention_heads": 24,
48
+ "num_hidden_layers": 32,
49
+ "num_key_value_heads": 8,
50
+ "original_max_position_embeddings": 4096,
51
+ "pad_token_id": 199999,
52
+ "partial_rotary_factor": 0.75,
53
+ "quantization_config": {
54
+ "_load_in_4bit": true,
55
+ "_load_in_8bit": false,
56
+ "bnb_4bit_compute_dtype": "bfloat16",
57
+ "bnb_4bit_quant_storage": "uint8",
58
+ "bnb_4bit_quant_type": "nf4",
59
+ "bnb_4bit_use_double_quant": true,
60
+ "llm_int8_enable_fp32_cpu_offload": false,
61
+ "llm_int8_has_fp16_weight": false,
62
+ "llm_int8_skip_modules": null,
63
+ "llm_int8_threshold": 6.0,
64
+ "load_in_4bit": true,
65
+ "load_in_8bit": false,
66
+ "quant_method": "bitsandbytes"
67
+ },
68
+ "resid_pdrop": 0.0,
69
+ "rms_norm_eps": 1e-05,
70
+ "rope_scaling": {
71
+ "long_factor": [
72
+ 1,
73
+ 1.118320672,
74
+ 1.250641126,
75
+ 1.398617824,
76
+ 1.564103225,
77
+ 1.74916897,
78
+ 1.956131817,
79
+ 2.187582649,
80
+ 2.446418898,
81
+ 2.735880826,
82
+ 3.059592084,
83
+ 3.421605075,
84
+ 3.826451687,
85
+ 4.279200023,
86
+ 4.785517845,
87
+ 5.351743533,
88
+ 5.984965424,
89
+ 6.693110555,
90
+ 7.485043894,
91
+ 8.370679318,
92
+ 9.36110372,
93
+ 10.4687158,
94
+ 11.70738129,
95
+ 13.09260651,
96
+ 14.64173252,
97
+ 16.37415215,
98
+ 18.31155283,
99
+ 20.47818807,
100
+ 22.90118105,
101
+ 25.61086418,
102
+ 28.64115884,
103
+ 32.03,
104
+ 32.1,
105
+ 32.13,
106
+ 32.23,
107
+ 32.6,
108
+ 32.61,
109
+ 32.64,
110
+ 32.66,
111
+ 32.7,
112
+ 32.71,
113
+ 32.93,
114
+ 32.97,
115
+ 33.28,
116
+ 33.49,
117
+ 33.5,
118
+ 44.16,
119
+ 47.77
120
+ ],
121
+ "short_factor": [
122
+ 1,
123
+ 1.118320672,
124
+ 1.250641126,
125
+ 1.398617824,
126
+ 1.564103225,
127
+ 1.74916897,
128
+ 1.956131817,
129
+ 2.187582649,
130
+ 2.446418898,
131
+ 2.735880826,
132
+ 3.059592084,
133
+ 3.421605075,
134
+ 3.826451687,
135
+ 4.279200023,
136
+ 4.785517845,
137
+ 5.351743533,
138
+ 5.984965424,
139
+ 6.693110555,
140
+ 7.485043894,
141
+ 8.370679318,
142
+ 9.36110372,
143
+ 10.4687158,
144
+ 11.70738129,
145
+ 13.09260651,
146
+ 14.64173252,
147
+ 16.37415215,
148
+ 18.31155283,
149
+ 20.47818807,
150
+ 22.90118105,
151
+ 25.61086418,
152
+ 28.64115884,
153
+ 32.03,
154
+ 32.1,
155
+ 32.13,
156
+ 32.23,
157
+ 32.6,
158
+ 32.61,
159
+ 32.64,
160
+ 32.66,
161
+ 32.7,
162
+ 32.71,
163
+ 32.93,
164
+ 32.97,
165
+ 33.28,
166
+ 33.49,
167
+ 33.5,
168
+ 44.16,
169
+ 47.77
170
+ ],
171
+ "type": "longrope"
172
+ },
173
+ "rope_theta": 10000.0,
174
+ "sliding_window": 262144,
175
+ "tokenizer_model_max_length": 2048,
176
+ "torch_dtype": "float16",
177
+ "transformers_version": "4.52.4",
178
+ "use_cache": true,
179
+ "vocab_size": 200064
180
+ }
generation_config.json ADDED
@@ -0,0 +1,10 @@
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "bos_token_id": 199999,
4
+ "eos_token_id": [
5
+ 200020,
6
+ 199999
7
+ ],
8
+ "pad_token_id": 199999,
9
+ "transformers_version": "4.52.4"
10
+ }
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:83f5b19a47940aafdd262f73966904041dae6086c75c9af7c2301d7e0fc57f5e
3
+ size 3133405649