imi2 commited on
Commit
8b96aed
1 Parent(s): e1b4401

Upload folder using huggingface_hub (#1)

Browse files

- Upload folder using huggingface_hub (6c97893fcd7400a004a7e219a762204ef37ce935)

cal_data.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5fcb42ff7427408b7a2f971bc556032860c1c4939503eb30deb2c102babfba49
3
+ size 1884248
config.json ADDED
@@ -0,0 +1,49 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "DbrxForCausalLM"
4
+ ],
5
+ "attn_config": {
6
+ "clip_qkv": 8,
7
+ "kv_n_heads": 8,
8
+ "model_type": "",
9
+ "rope_theta": 500000
10
+ },
11
+ "auto_map": {
12
+ "AutoConfig": "configuration_dbrx.DbrxConfig",
13
+ "AutoModelForCausalLM": "modeling_dbrx.DbrxForCausalLM"
14
+ },
15
+ "d_model": 6144,
16
+ "emb_pdrop": 0.0,
17
+ "ffn_config": {
18
+ "ffn_hidden_size": 10752,
19
+ "model_type": "",
20
+ "moe_jitter_eps": 0.01,
21
+ "moe_loss_weight": 0.05,
22
+ "moe_num_experts": 16,
23
+ "moe_top_k": 4
24
+ },
25
+ "initializer_range": 0.02,
26
+ "max_seq_len": 32768,
27
+ "model_type": "dbrx",
28
+ "n_heads": 48,
29
+ "n_layers": 40,
30
+ "output_router_logits": false,
31
+ "resid_pdrop": 0.0,
32
+ "router_aux_loss_coef": 0.05,
33
+ "tie_word_embeddings": false,
34
+ "torch_dtype": "bfloat16",
35
+ "transformers_version": "4.38.2",
36
+ "use_cache": true,
37
+ "vocab_size": 100352,
38
+ "quantization_config": {
39
+ "quant_method": "exl2",
40
+ "version": "0.0.17",
41
+ "bits": 2.5,
42
+ "head_bits": 6,
43
+ "calibration": {
44
+ "rows": 100,
45
+ "length": 2048,
46
+ "dataset": "(default)"
47
+ }
48
+ }
49
+ }
generation_config.json ADDED
@@ -0,0 +1,7 @@
 
 
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "eos_token_id": [
4
+ 100257
5
+ ],
6
+ "transformers_version": "4.38.2"
7
+ }
hidden_states.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:92e584c8cf5c819ab59d8b5958c1e3a69eb76e8f156e8605ef5c8ddb78968dd1
3
+ size 2894079912
job_new.json ADDED
The diff for this file is too large to render. See raw diff
 
model.safetensors.index.json ADDED
@@ -0,0 +1,330 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "metadata": {
3
+ "total_size": 263193047040
4
+ },
5
+ "weight_map": {
6
+ "lm_head.weight": "model-00061-of-00061.safetensors",
7
+ "transformer.blocks.0.ffn.experts.mlp.v1": "model-00002-of-00061.safetensors",
8
+ "transformer.blocks.0.ffn.experts.mlp.w1": "model-00001-of-00061.safetensors",
9
+ "transformer.blocks.0.ffn.experts.mlp.w2": "model-00002-of-00061.safetensors",
10
+ "transformer.blocks.0.ffn.router.layer.weight": "model-00001-of-00061.safetensors",
11
+ "transformer.blocks.0.norm_attn_norm.attn.Wqkv.weight": "model-00001-of-00061.safetensors",
12
+ "transformer.blocks.0.norm_attn_norm.attn.out_proj.weight": "model-00001-of-00061.safetensors",
13
+ "transformer.blocks.0.norm_attn_norm.norm_1.weight": "model-00001-of-00061.safetensors",
14
+ "transformer.blocks.0.norm_attn_norm.norm_2.weight": "model-00001-of-00061.safetensors",
15
+ "transformer.blocks.1.ffn.experts.mlp.v1": "model-00003-of-00061.safetensors",
16
+ "transformer.blocks.1.ffn.experts.mlp.w1": "model-00003-of-00061.safetensors",
17
+ "transformer.blocks.1.ffn.experts.mlp.w2": "model-00004-of-00061.safetensors",
18
+ "transformer.blocks.1.ffn.router.layer.weight": "model-00002-of-00061.safetensors",
19
+ "transformer.blocks.1.norm_attn_norm.attn.Wqkv.weight": "model-00002-of-00061.safetensors",
20
+ "transformer.blocks.1.norm_attn_norm.attn.out_proj.weight": "model-00002-of-00061.safetensors",
21
+ "transformer.blocks.1.norm_attn_norm.norm_1.weight": "model-00002-of-00061.safetensors",
22
+ "transformer.blocks.1.norm_attn_norm.norm_2.weight": "model-00002-of-00061.safetensors",
23
+ "transformer.blocks.10.ffn.experts.mlp.v1": "model-00017-of-00061.safetensors",
24
+ "transformer.blocks.10.ffn.experts.mlp.w1": "model-00016-of-00061.safetensors",
25
+ "transformer.blocks.10.ffn.experts.mlp.w2": "model-00017-of-00061.safetensors",
26
+ "transformer.blocks.10.ffn.router.layer.weight": "model-00016-of-00061.safetensors",
27
+ "transformer.blocks.10.norm_attn_norm.attn.Wqkv.weight": "model-00016-of-00061.safetensors",
28
+ "transformer.blocks.10.norm_attn_norm.attn.out_proj.weight": "model-00016-of-00061.safetensors",
29
+ "transformer.blocks.10.norm_attn_norm.norm_1.weight": "model-00016-of-00061.safetensors",
30
+ "transformer.blocks.10.norm_attn_norm.norm_2.weight": "model-00016-of-00061.safetensors",
31
+ "transformer.blocks.11.ffn.experts.mlp.v1": "model-00018-of-00061.safetensors",
32
+ "transformer.blocks.11.ffn.experts.mlp.w1": "model-00018-of-00061.safetensors",
33
+ "transformer.blocks.11.ffn.experts.mlp.w2": "model-00019-of-00061.safetensors",
34
+ "transformer.blocks.11.ffn.router.layer.weight": "model-00017-of-00061.safetensors",
35
+ "transformer.blocks.11.norm_attn_norm.attn.Wqkv.weight": "model-00017-of-00061.safetensors",
36
+ "transformer.blocks.11.norm_attn_norm.attn.out_proj.weight": "model-00017-of-00061.safetensors",
37
+ "transformer.blocks.11.norm_attn_norm.norm_1.weight": "model-00017-of-00061.safetensors",
38
+ "transformer.blocks.11.norm_attn_norm.norm_2.weight": "model-00017-of-00061.safetensors",
39
+ "transformer.blocks.12.ffn.experts.mlp.v1": "model-00020-of-00061.safetensors",
40
+ "transformer.blocks.12.ffn.experts.mlp.w1": "model-00019-of-00061.safetensors",
41
+ "transformer.blocks.12.ffn.experts.mlp.w2": "model-00020-of-00061.safetensors",
42
+ "transformer.blocks.12.ffn.router.layer.weight": "model-00019-of-00061.safetensors",
43
+ "transformer.blocks.12.norm_attn_norm.attn.Wqkv.weight": "model-00019-of-00061.safetensors",
44
+ "transformer.blocks.12.norm_attn_norm.attn.out_proj.weight": "model-00019-of-00061.safetensors",
45
+ "transformer.blocks.12.norm_attn_norm.norm_1.weight": "model-00019-of-00061.safetensors",
46
+ "transformer.blocks.12.norm_attn_norm.norm_2.weight": "model-00019-of-00061.safetensors",
47
+ "transformer.blocks.13.ffn.experts.mlp.v1": "model-00021-of-00061.safetensors",
48
+ "transformer.blocks.13.ffn.experts.mlp.w1": "model-00021-of-00061.safetensors",
49
+ "transformer.blocks.13.ffn.experts.mlp.w2": "model-00022-of-00061.safetensors",
50
+ "transformer.blocks.13.ffn.router.layer.weight": "model-00020-of-00061.safetensors",
51
+ "transformer.blocks.13.norm_attn_norm.attn.Wqkv.weight": "model-00020-of-00061.safetensors",
52
+ "transformer.blocks.13.norm_attn_norm.attn.out_proj.weight": "model-00020-of-00061.safetensors",
53
+ "transformer.blocks.13.norm_attn_norm.norm_1.weight": "model-00020-of-00061.safetensors",
54
+ "transformer.blocks.13.norm_attn_norm.norm_2.weight": "model-00020-of-00061.safetensors",
55
+ "transformer.blocks.14.ffn.experts.mlp.v1": "model-00023-of-00061.safetensors",
56
+ "transformer.blocks.14.ffn.experts.mlp.w1": "model-00022-of-00061.safetensors",
57
+ "transformer.blocks.14.ffn.experts.mlp.w2": "model-00023-of-00061.safetensors",
58
+ "transformer.blocks.14.ffn.router.layer.weight": "model-00022-of-00061.safetensors",
59
+ "transformer.blocks.14.norm_attn_norm.attn.Wqkv.weight": "model-00022-of-00061.safetensors",
60
+ "transformer.blocks.14.norm_attn_norm.attn.out_proj.weight": "model-00022-of-00061.safetensors",
61
+ "transformer.blocks.14.norm_attn_norm.norm_1.weight": "model-00022-of-00061.safetensors",
62
+ "transformer.blocks.14.norm_attn_norm.norm_2.weight": "model-00022-of-00061.safetensors",
63
+ "transformer.blocks.15.ffn.experts.mlp.v1": "model-00024-of-00061.safetensors",
64
+ "transformer.blocks.15.ffn.experts.mlp.w1": "model-00024-of-00061.safetensors",
65
+ "transformer.blocks.15.ffn.experts.mlp.w2": "model-00025-of-00061.safetensors",
66
+ "transformer.blocks.15.ffn.router.layer.weight": "model-00023-of-00061.safetensors",
67
+ "transformer.blocks.15.norm_attn_norm.attn.Wqkv.weight": "model-00023-of-00061.safetensors",
68
+ "transformer.blocks.15.norm_attn_norm.attn.out_proj.weight": "model-00023-of-00061.safetensors",
69
+ "transformer.blocks.15.norm_attn_norm.norm_1.weight": "model-00023-of-00061.safetensors",
70
+ "transformer.blocks.15.norm_attn_norm.norm_2.weight": "model-00023-of-00061.safetensors",
71
+ "transformer.blocks.16.ffn.experts.mlp.v1": "model-00026-of-00061.safetensors",
72
+ "transformer.blocks.16.ffn.experts.mlp.w1": "model-00025-of-00061.safetensors",
73
+ "transformer.blocks.16.ffn.experts.mlp.w2": "model-00026-of-00061.safetensors",
74
+ "transformer.blocks.16.ffn.router.layer.weight": "model-00025-of-00061.safetensors",
75
+ "transformer.blocks.16.norm_attn_norm.attn.Wqkv.weight": "model-00025-of-00061.safetensors",
76
+ "transformer.blocks.16.norm_attn_norm.attn.out_proj.weight": "model-00025-of-00061.safetensors",
77
+ "transformer.blocks.16.norm_attn_norm.norm_1.weight": "model-00025-of-00061.safetensors",
78
+ "transformer.blocks.16.norm_attn_norm.norm_2.weight": "model-00025-of-00061.safetensors",
79
+ "transformer.blocks.17.ffn.experts.mlp.v1": "model-00027-of-00061.safetensors",
80
+ "transformer.blocks.17.ffn.experts.mlp.w1": "model-00027-of-00061.safetensors",
81
+ "transformer.blocks.17.ffn.experts.mlp.w2": "model-00028-of-00061.safetensors",
82
+ "transformer.blocks.17.ffn.router.layer.weight": "model-00026-of-00061.safetensors",
83
+ "transformer.blocks.17.norm_attn_norm.attn.Wqkv.weight": "model-00026-of-00061.safetensors",
84
+ "transformer.blocks.17.norm_attn_norm.attn.out_proj.weight": "model-00026-of-00061.safetensors",
85
+ "transformer.blocks.17.norm_attn_norm.norm_1.weight": "model-00026-of-00061.safetensors",
86
+ "transformer.blocks.17.norm_attn_norm.norm_2.weight": "model-00026-of-00061.safetensors",
87
+ "transformer.blocks.18.ffn.experts.mlp.v1": "model-00029-of-00061.safetensors",
88
+ "transformer.blocks.18.ffn.experts.mlp.w1": "model-00028-of-00061.safetensors",
89
+ "transformer.blocks.18.ffn.experts.mlp.w2": "model-00029-of-00061.safetensors",
90
+ "transformer.blocks.18.ffn.router.layer.weight": "model-00028-of-00061.safetensors",
91
+ "transformer.blocks.18.norm_attn_norm.attn.Wqkv.weight": "model-00028-of-00061.safetensors",
92
+ "transformer.blocks.18.norm_attn_norm.attn.out_proj.weight": "model-00028-of-00061.safetensors",
93
+ "transformer.blocks.18.norm_attn_norm.norm_1.weight": "model-00028-of-00061.safetensors",
94
+ "transformer.blocks.18.norm_attn_norm.norm_2.weight": "model-00028-of-00061.safetensors",
95
+ "transformer.blocks.19.ffn.experts.mlp.v1": "model-00030-of-00061.safetensors",
96
+ "transformer.blocks.19.ffn.experts.mlp.w1": "model-00030-of-00061.safetensors",
97
+ "transformer.blocks.19.ffn.experts.mlp.w2": "model-00031-of-00061.safetensors",
98
+ "transformer.blocks.19.ffn.router.layer.weight": "model-00029-of-00061.safetensors",
99
+ "transformer.blocks.19.norm_attn_norm.attn.Wqkv.weight": "model-00029-of-00061.safetensors",
100
+ "transformer.blocks.19.norm_attn_norm.attn.out_proj.weight": "model-00029-of-00061.safetensors",
101
+ "transformer.blocks.19.norm_attn_norm.norm_1.weight": "model-00029-of-00061.safetensors",
102
+ "transformer.blocks.19.norm_attn_norm.norm_2.weight": "model-00029-of-00061.safetensors",
103
+ "transformer.blocks.2.ffn.experts.mlp.v1": "model-00005-of-00061.safetensors",
104
+ "transformer.blocks.2.ffn.experts.mlp.w1": "model-00004-of-00061.safetensors",
105
+ "transformer.blocks.2.ffn.experts.mlp.w2": "model-00005-of-00061.safetensors",
106
+ "transformer.blocks.2.ffn.router.layer.weight": "model-00004-of-00061.safetensors",
107
+ "transformer.blocks.2.norm_attn_norm.attn.Wqkv.weight": "model-00004-of-00061.safetensors",
108
+ "transformer.blocks.2.norm_attn_norm.attn.out_proj.weight": "model-00004-of-00061.safetensors",
109
+ "transformer.blocks.2.norm_attn_norm.norm_1.weight": "model-00004-of-00061.safetensors",
110
+ "transformer.blocks.2.norm_attn_norm.norm_2.weight": "model-00004-of-00061.safetensors",
111
+ "transformer.blocks.20.ffn.experts.mlp.v1": "model-00032-of-00061.safetensors",
112
+ "transformer.blocks.20.ffn.experts.mlp.w1": "model-00031-of-00061.safetensors",
113
+ "transformer.blocks.20.ffn.experts.mlp.w2": "model-00032-of-00061.safetensors",
114
+ "transformer.blocks.20.ffn.router.layer.weight": "model-00031-of-00061.safetensors",
115
+ "transformer.blocks.20.norm_attn_norm.attn.Wqkv.weight": "model-00031-of-00061.safetensors",
116
+ "transformer.blocks.20.norm_attn_norm.attn.out_proj.weight": "model-00031-of-00061.safetensors",
117
+ "transformer.blocks.20.norm_attn_norm.norm_1.weight": "model-00031-of-00061.safetensors",
118
+ "transformer.blocks.20.norm_attn_norm.norm_2.weight": "model-00031-of-00061.safetensors",
119
+ "transformer.blocks.21.ffn.experts.mlp.v1": "model-00033-of-00061.safetensors",
120
+ "transformer.blocks.21.ffn.experts.mlp.w1": "model-00033-of-00061.safetensors",
121
+ "transformer.blocks.21.ffn.experts.mlp.w2": "model-00034-of-00061.safetensors",
122
+ "transformer.blocks.21.ffn.router.layer.weight": "model-00032-of-00061.safetensors",
123
+ "transformer.blocks.21.norm_attn_norm.attn.Wqkv.weight": "model-00032-of-00061.safetensors",
124
+ "transformer.blocks.21.norm_attn_norm.attn.out_proj.weight": "model-00032-of-00061.safetensors",
125
+ "transformer.blocks.21.norm_attn_norm.norm_1.weight": "model-00032-of-00061.safetensors",
126
+ "transformer.blocks.21.norm_attn_norm.norm_2.weight": "model-00032-of-00061.safetensors",
127
+ "transformer.blocks.22.ffn.experts.mlp.v1": "model-00035-of-00061.safetensors",
128
+ "transformer.blocks.22.ffn.experts.mlp.w1": "model-00034-of-00061.safetensors",
129
+ "transformer.blocks.22.ffn.experts.mlp.w2": "model-00035-of-00061.safetensors",
130
+ "transformer.blocks.22.ffn.router.layer.weight": "model-00034-of-00061.safetensors",
131
+ "transformer.blocks.22.norm_attn_norm.attn.Wqkv.weight": "model-00034-of-00061.safetensors",
132
+ "transformer.blocks.22.norm_attn_norm.attn.out_proj.weight": "model-00034-of-00061.safetensors",
133
+ "transformer.blocks.22.norm_attn_norm.norm_1.weight": "model-00034-of-00061.safetensors",
134
+ "transformer.blocks.22.norm_attn_norm.norm_2.weight": "model-00034-of-00061.safetensors",
135
+ "transformer.blocks.23.ffn.experts.mlp.v1": "model-00036-of-00061.safetensors",
136
+ "transformer.blocks.23.ffn.experts.mlp.w1": "model-00036-of-00061.safetensors",
137
+ "transformer.blocks.23.ffn.experts.mlp.w2": "model-00037-of-00061.safetensors",
138
+ "transformer.blocks.23.ffn.router.layer.weight": "model-00035-of-00061.safetensors",
139
+ "transformer.blocks.23.norm_attn_norm.attn.Wqkv.weight": "model-00035-of-00061.safetensors",
140
+ "transformer.blocks.23.norm_attn_norm.attn.out_proj.weight": "model-00035-of-00061.safetensors",
141
+ "transformer.blocks.23.norm_attn_norm.norm_1.weight": "model-00035-of-00061.safetensors",
142
+ "transformer.blocks.23.norm_attn_norm.norm_2.weight": "model-00035-of-00061.safetensors",
143
+ "transformer.blocks.24.ffn.experts.mlp.v1": "model-00038-of-00061.safetensors",
144
+ "transformer.blocks.24.ffn.experts.mlp.w1": "model-00037-of-00061.safetensors",
145
+ "transformer.blocks.24.ffn.experts.mlp.w2": "model-00038-of-00061.safetensors",
146
+ "transformer.blocks.24.ffn.router.layer.weight": "model-00037-of-00061.safetensors",
147
+ "transformer.blocks.24.norm_attn_norm.attn.Wqkv.weight": "model-00037-of-00061.safetensors",
148
+ "transformer.blocks.24.norm_attn_norm.attn.out_proj.weight": "model-00037-of-00061.safetensors",
149
+ "transformer.blocks.24.norm_attn_norm.norm_1.weight": "model-00037-of-00061.safetensors",
150
+ "transformer.blocks.24.norm_attn_norm.norm_2.weight": "model-00037-of-00061.safetensors",
151
+ "transformer.blocks.25.ffn.experts.mlp.v1": "model-00039-of-00061.safetensors",
152
+ "transformer.blocks.25.ffn.experts.mlp.w1": "model-00039-of-00061.safetensors",
153
+ "transformer.blocks.25.ffn.experts.mlp.w2": "model-00040-of-00061.safetensors",
154
+ "transformer.blocks.25.ffn.router.layer.weight": "model-00038-of-00061.safetensors",
155
+ "transformer.blocks.25.norm_attn_norm.attn.Wqkv.weight": "model-00038-of-00061.safetensors",
156
+ "transformer.blocks.25.norm_attn_norm.attn.out_proj.weight": "model-00038-of-00061.safetensors",
157
+ "transformer.blocks.25.norm_attn_norm.norm_1.weight": "model-00038-of-00061.safetensors",
158
+ "transformer.blocks.25.norm_attn_norm.norm_2.weight": "model-00038-of-00061.safetensors",
159
+ "transformer.blocks.26.ffn.experts.mlp.v1": "model-00041-of-00061.safetensors",
160
+ "transformer.blocks.26.ffn.experts.mlp.w1": "model-00040-of-00061.safetensors",
161
+ "transformer.blocks.26.ffn.experts.mlp.w2": "model-00041-of-00061.safetensors",
162
+ "transformer.blocks.26.ffn.router.layer.weight": "model-00040-of-00061.safetensors",
163
+ "transformer.blocks.26.norm_attn_norm.attn.Wqkv.weight": "model-00040-of-00061.safetensors",
164
+ "transformer.blocks.26.norm_attn_norm.attn.out_proj.weight": "model-00040-of-00061.safetensors",
165
+ "transformer.blocks.26.norm_attn_norm.norm_1.weight": "model-00040-of-00061.safetensors",
166
+ "transformer.blocks.26.norm_attn_norm.norm_2.weight": "model-00040-of-00061.safetensors",
167
+ "transformer.blocks.27.ffn.experts.mlp.v1": "model-00042-of-00061.safetensors",
168
+ "transformer.blocks.27.ffn.experts.mlp.w1": "model-00042-of-00061.safetensors",
169
+ "transformer.blocks.27.ffn.experts.mlp.w2": "model-00043-of-00061.safetensors",
170
+ "transformer.blocks.27.ffn.router.layer.weight": "model-00041-of-00061.safetensors",
171
+ "transformer.blocks.27.norm_attn_norm.attn.Wqkv.weight": "model-00041-of-00061.safetensors",
172
+ "transformer.blocks.27.norm_attn_norm.attn.out_proj.weight": "model-00041-of-00061.safetensors",
173
+ "transformer.blocks.27.norm_attn_norm.norm_1.weight": "model-00041-of-00061.safetensors",
174
+ "transformer.blocks.27.norm_attn_norm.norm_2.weight": "model-00041-of-00061.safetensors",
175
+ "transformer.blocks.28.ffn.experts.mlp.v1": "model-00044-of-00061.safetensors",
176
+ "transformer.blocks.28.ffn.experts.mlp.w1": "model-00043-of-00061.safetensors",
177
+ "transformer.blocks.28.ffn.experts.mlp.w2": "model-00044-of-00061.safetensors",
178
+ "transformer.blocks.28.ffn.router.layer.weight": "model-00043-of-00061.safetensors",
179
+ "transformer.blocks.28.norm_attn_norm.attn.Wqkv.weight": "model-00043-of-00061.safetensors",
180
+ "transformer.blocks.28.norm_attn_norm.attn.out_proj.weight": "model-00043-of-00061.safetensors",
181
+ "transformer.blocks.28.norm_attn_norm.norm_1.weight": "model-00043-of-00061.safetensors",
182
+ "transformer.blocks.28.norm_attn_norm.norm_2.weight": "model-00043-of-00061.safetensors",
183
+ "transformer.blocks.29.ffn.experts.mlp.v1": "model-00045-of-00061.safetensors",
184
+ "transformer.blocks.29.ffn.experts.mlp.w1": "model-00045-of-00061.safetensors",
185
+ "transformer.blocks.29.ffn.experts.mlp.w2": "model-00046-of-00061.safetensors",
186
+ "transformer.blocks.29.ffn.router.layer.weight": "model-00044-of-00061.safetensors",
187
+ "transformer.blocks.29.norm_attn_norm.attn.Wqkv.weight": "model-00044-of-00061.safetensors",
188
+ "transformer.blocks.29.norm_attn_norm.attn.out_proj.weight": "model-00044-of-00061.safetensors",
189
+ "transformer.blocks.29.norm_attn_norm.norm_1.weight": "model-00044-of-00061.safetensors",
190
+ "transformer.blocks.29.norm_attn_norm.norm_2.weight": "model-00044-of-00061.safetensors",
191
+ "transformer.blocks.3.ffn.experts.mlp.v1": "model-00006-of-00061.safetensors",
192
+ "transformer.blocks.3.ffn.experts.mlp.w1": "model-00006-of-00061.safetensors",
193
+ "transformer.blocks.3.ffn.experts.mlp.w2": "model-00007-of-00061.safetensors",
194
+ "transformer.blocks.3.ffn.router.layer.weight": "model-00005-of-00061.safetensors",
195
+ "transformer.blocks.3.norm_attn_norm.attn.Wqkv.weight": "model-00005-of-00061.safetensors",
196
+ "transformer.blocks.3.norm_attn_norm.attn.out_proj.weight": "model-00005-of-00061.safetensors",
197
+ "transformer.blocks.3.norm_attn_norm.norm_1.weight": "model-00005-of-00061.safetensors",
198
+ "transformer.blocks.3.norm_attn_norm.norm_2.weight": "model-00005-of-00061.safetensors",
199
+ "transformer.blocks.30.ffn.experts.mlp.v1": "model-00047-of-00061.safetensors",
200
+ "transformer.blocks.30.ffn.experts.mlp.w1": "model-00046-of-00061.safetensors",
201
+ "transformer.blocks.30.ffn.experts.mlp.w2": "model-00047-of-00061.safetensors",
202
+ "transformer.blocks.30.ffn.router.layer.weight": "model-00046-of-00061.safetensors",
203
+ "transformer.blocks.30.norm_attn_norm.attn.Wqkv.weight": "model-00046-of-00061.safetensors",
204
+ "transformer.blocks.30.norm_attn_norm.attn.out_proj.weight": "model-00046-of-00061.safetensors",
205
+ "transformer.blocks.30.norm_attn_norm.norm_1.weight": "model-00046-of-00061.safetensors",
206
+ "transformer.blocks.30.norm_attn_norm.norm_2.weight": "model-00046-of-00061.safetensors",
207
+ "transformer.blocks.31.ffn.experts.mlp.v1": "model-00048-of-00061.safetensors",
208
+ "transformer.blocks.31.ffn.experts.mlp.w1": "model-00048-of-00061.safetensors",
209
+ "transformer.blocks.31.ffn.experts.mlp.w2": "model-00049-of-00061.safetensors",
210
+ "transformer.blocks.31.ffn.router.layer.weight": "model-00047-of-00061.safetensors",
211
+ "transformer.blocks.31.norm_attn_norm.attn.Wqkv.weight": "model-00047-of-00061.safetensors",
212
+ "transformer.blocks.31.norm_attn_norm.attn.out_proj.weight": "model-00047-of-00061.safetensors",
213
+ "transformer.blocks.31.norm_attn_norm.norm_1.weight": "model-00047-of-00061.safetensors",
214
+ "transformer.blocks.31.norm_attn_norm.norm_2.weight": "model-00047-of-00061.safetensors",
215
+ "transformer.blocks.32.ffn.experts.mlp.v1": "model-00050-of-00061.safetensors",
216
+ "transformer.blocks.32.ffn.experts.mlp.w1": "model-00049-of-00061.safetensors",
217
+ "transformer.blocks.32.ffn.experts.mlp.w2": "model-00050-of-00061.safetensors",
218
+ "transformer.blocks.32.ffn.router.layer.weight": "model-00049-of-00061.safetensors",
219
+ "transformer.blocks.32.norm_attn_norm.attn.Wqkv.weight": "model-00049-of-00061.safetensors",
220
+ "transformer.blocks.32.norm_attn_norm.attn.out_proj.weight": "model-00049-of-00061.safetensors",
221
+ "transformer.blocks.32.norm_attn_norm.norm_1.weight": "model-00049-of-00061.safetensors",
222
+ "transformer.blocks.32.norm_attn_norm.norm_2.weight": "model-00049-of-00061.safetensors",
223
+ "transformer.blocks.33.ffn.experts.mlp.v1": "model-00051-of-00061.safetensors",
224
+ "transformer.blocks.33.ffn.experts.mlp.w1": "model-00051-of-00061.safetensors",
225
+ "transformer.blocks.33.ffn.experts.mlp.w2": "model-00052-of-00061.safetensors",
226
+ "transformer.blocks.33.ffn.router.layer.weight": "model-00050-of-00061.safetensors",
227
+ "transformer.blocks.33.norm_attn_norm.attn.Wqkv.weight": "model-00050-of-00061.safetensors",
228
+ "transformer.blocks.33.norm_attn_norm.attn.out_proj.weight": "model-00050-of-00061.safetensors",
229
+ "transformer.blocks.33.norm_attn_norm.norm_1.weight": "model-00050-of-00061.safetensors",
230
+ "transformer.blocks.33.norm_attn_norm.norm_2.weight": "model-00050-of-00061.safetensors",
231
+ "transformer.blocks.34.ffn.experts.mlp.v1": "model-00053-of-00061.safetensors",
232
+ "transformer.blocks.34.ffn.experts.mlp.w1": "model-00052-of-00061.safetensors",
233
+ "transformer.blocks.34.ffn.experts.mlp.w2": "model-00053-of-00061.safetensors",
234
+ "transformer.blocks.34.ffn.router.layer.weight": "model-00052-of-00061.safetensors",
235
+ "transformer.blocks.34.norm_attn_norm.attn.Wqkv.weight": "model-00052-of-00061.safetensors",
236
+ "transformer.blocks.34.norm_attn_norm.attn.out_proj.weight": "model-00052-of-00061.safetensors",
237
+ "transformer.blocks.34.norm_attn_norm.norm_1.weight": "model-00052-of-00061.safetensors",
238
+ "transformer.blocks.34.norm_attn_norm.norm_2.weight": "model-00052-of-00061.safetensors",
239
+ "transformer.blocks.35.ffn.experts.mlp.v1": "model-00054-of-00061.safetensors",
240
+ "transformer.blocks.35.ffn.experts.mlp.w1": "model-00054-of-00061.safetensors",
241
+ "transformer.blocks.35.ffn.experts.mlp.w2": "model-00055-of-00061.safetensors",
242
+ "transformer.blocks.35.ffn.router.layer.weight": "model-00053-of-00061.safetensors",
243
+ "transformer.blocks.35.norm_attn_norm.attn.Wqkv.weight": "model-00053-of-00061.safetensors",
244
+ "transformer.blocks.35.norm_attn_norm.attn.out_proj.weight": "model-00053-of-00061.safetensors",
245
+ "transformer.blocks.35.norm_attn_norm.norm_1.weight": "model-00053-of-00061.safetensors",
246
+ "transformer.blocks.35.norm_attn_norm.norm_2.weight": "model-00053-of-00061.safetensors",
247
+ "transformer.blocks.36.ffn.experts.mlp.v1": "model-00056-of-00061.safetensors",
248
+ "transformer.blocks.36.ffn.experts.mlp.w1": "model-00055-of-00061.safetensors",
249
+ "transformer.blocks.36.ffn.experts.mlp.w2": "model-00056-of-00061.safetensors",
250
+ "transformer.blocks.36.ffn.router.layer.weight": "model-00055-of-00061.safetensors",
251
+ "transformer.blocks.36.norm_attn_norm.attn.Wqkv.weight": "model-00055-of-00061.safetensors",
252
+ "transformer.blocks.36.norm_attn_norm.attn.out_proj.weight": "model-00055-of-00061.safetensors",
253
+ "transformer.blocks.36.norm_attn_norm.norm_1.weight": "model-00055-of-00061.safetensors",
254
+ "transformer.blocks.36.norm_attn_norm.norm_2.weight": "model-00055-of-00061.safetensors",
255
+ "transformer.blocks.37.ffn.experts.mlp.v1": "model-00057-of-00061.safetensors",
256
+ "transformer.blocks.37.ffn.experts.mlp.w1": "model-00057-of-00061.safetensors",
257
+ "transformer.blocks.37.ffn.experts.mlp.w2": "model-00058-of-00061.safetensors",
258
+ "transformer.blocks.37.ffn.router.layer.weight": "model-00056-of-00061.safetensors",
259
+ "transformer.blocks.37.norm_attn_norm.attn.Wqkv.weight": "model-00056-of-00061.safetensors",
260
+ "transformer.blocks.37.norm_attn_norm.attn.out_proj.weight": "model-00056-of-00061.safetensors",
261
+ "transformer.blocks.37.norm_attn_norm.norm_1.weight": "model-00056-of-00061.safetensors",
262
+ "transformer.blocks.37.norm_attn_norm.norm_2.weight": "model-00056-of-00061.safetensors",
263
+ "transformer.blocks.38.ffn.experts.mlp.v1": "model-00059-of-00061.safetensors",
264
+ "transformer.blocks.38.ffn.experts.mlp.w1": "model-00058-of-00061.safetensors",
265
+ "transformer.blocks.38.ffn.experts.mlp.w2": "model-00059-of-00061.safetensors",
266
+ "transformer.blocks.38.ffn.router.layer.weight": "model-00058-of-00061.safetensors",
267
+ "transformer.blocks.38.norm_attn_norm.attn.Wqkv.weight": "model-00058-of-00061.safetensors",
268
+ "transformer.blocks.38.norm_attn_norm.attn.out_proj.weight": "model-00058-of-00061.safetensors",
269
+ "transformer.blocks.38.norm_attn_norm.norm_1.weight": "model-00058-of-00061.safetensors",
270
+ "transformer.blocks.38.norm_attn_norm.norm_2.weight": "model-00058-of-00061.safetensors",
271
+ "transformer.blocks.39.ffn.experts.mlp.v1": "model-00060-of-00061.safetensors",
272
+ "transformer.blocks.39.ffn.experts.mlp.w1": "model-00060-of-00061.safetensors",
273
+ "transformer.blocks.39.ffn.experts.mlp.w2": "model-00061-of-00061.safetensors",
274
+ "transformer.blocks.39.ffn.router.layer.weight": "model-00059-of-00061.safetensors",
275
+ "transformer.blocks.39.norm_attn_norm.attn.Wqkv.weight": "model-00059-of-00061.safetensors",
276
+ "transformer.blocks.39.norm_attn_norm.attn.out_proj.weight": "model-00059-of-00061.safetensors",
277
+ "transformer.blocks.39.norm_attn_norm.norm_1.weight": "model-00059-of-00061.safetensors",
278
+ "transformer.blocks.39.norm_attn_norm.norm_2.weight": "model-00059-of-00061.safetensors",
279
+ "transformer.blocks.4.ffn.experts.mlp.v1": "model-00008-of-00061.safetensors",
280
+ "transformer.blocks.4.ffn.experts.mlp.w1": "model-00007-of-00061.safetensors",
281
+ "transformer.blocks.4.ffn.experts.mlp.w2": "model-00008-of-00061.safetensors",
282
+ "transformer.blocks.4.ffn.router.layer.weight": "model-00007-of-00061.safetensors",
283
+ "transformer.blocks.4.norm_attn_norm.attn.Wqkv.weight": "model-00007-of-00061.safetensors",
284
+ "transformer.blocks.4.norm_attn_norm.attn.out_proj.weight": "model-00007-of-00061.safetensors",
285
+ "transformer.blocks.4.norm_attn_norm.norm_1.weight": "model-00007-of-00061.safetensors",
286
+ "transformer.blocks.4.norm_attn_norm.norm_2.weight": "model-00007-of-00061.safetensors",
287
+ "transformer.blocks.5.ffn.experts.mlp.v1": "model-00009-of-00061.safetensors",
288
+ "transformer.blocks.5.ffn.experts.mlp.w1": "model-00009-of-00061.safetensors",
289
+ "transformer.blocks.5.ffn.experts.mlp.w2": "model-00010-of-00061.safetensors",
290
+ "transformer.blocks.5.ffn.router.layer.weight": "model-00008-of-00061.safetensors",
291
+ "transformer.blocks.5.norm_attn_norm.attn.Wqkv.weight": "model-00008-of-00061.safetensors",
292
+ "transformer.blocks.5.norm_attn_norm.attn.out_proj.weight": "model-00008-of-00061.safetensors",
293
+ "transformer.blocks.5.norm_attn_norm.norm_1.weight": "model-00008-of-00061.safetensors",
294
+ "transformer.blocks.5.norm_attn_norm.norm_2.weight": "model-00008-of-00061.safetensors",
295
+ "transformer.blocks.6.ffn.experts.mlp.v1": "model-00011-of-00061.safetensors",
296
+ "transformer.blocks.6.ffn.experts.mlp.w1": "model-00010-of-00061.safetensors",
297
+ "transformer.blocks.6.ffn.experts.mlp.w2": "model-00011-of-00061.safetensors",
298
+ "transformer.blocks.6.ffn.router.layer.weight": "model-00010-of-00061.safetensors",
299
+ "transformer.blocks.6.norm_attn_norm.attn.Wqkv.weight": "model-00010-of-00061.safetensors",
300
+ "transformer.blocks.6.norm_attn_norm.attn.out_proj.weight": "model-00010-of-00061.safetensors",
301
+ "transformer.blocks.6.norm_attn_norm.norm_1.weight": "model-00010-of-00061.safetensors",
302
+ "transformer.blocks.6.norm_attn_norm.norm_2.weight": "model-00010-of-00061.safetensors",
303
+ "transformer.blocks.7.ffn.experts.mlp.v1": "model-00012-of-00061.safetensors",
304
+ "transformer.blocks.7.ffn.experts.mlp.w1": "model-00012-of-00061.safetensors",
305
+ "transformer.blocks.7.ffn.experts.mlp.w2": "model-00013-of-00061.safetensors",
306
+ "transformer.blocks.7.ffn.router.layer.weight": "model-00011-of-00061.safetensors",
307
+ "transformer.blocks.7.norm_attn_norm.attn.Wqkv.weight": "model-00011-of-00061.safetensors",
308
+ "transformer.blocks.7.norm_attn_norm.attn.out_proj.weight": "model-00011-of-00061.safetensors",
309
+ "transformer.blocks.7.norm_attn_norm.norm_1.weight": "model-00011-of-00061.safetensors",
310
+ "transformer.blocks.7.norm_attn_norm.norm_2.weight": "model-00011-of-00061.safetensors",
311
+ "transformer.blocks.8.ffn.experts.mlp.v1": "model-00014-of-00061.safetensors",
312
+ "transformer.blocks.8.ffn.experts.mlp.w1": "model-00013-of-00061.safetensors",
313
+ "transformer.blocks.8.ffn.experts.mlp.w2": "model-00014-of-00061.safetensors",
314
+ "transformer.blocks.8.ffn.router.layer.weight": "model-00013-of-00061.safetensors",
315
+ "transformer.blocks.8.norm_attn_norm.attn.Wqkv.weight": "model-00013-of-00061.safetensors",
316
+ "transformer.blocks.8.norm_attn_norm.attn.out_proj.weight": "model-00013-of-00061.safetensors",
317
+ "transformer.blocks.8.norm_attn_norm.norm_1.weight": "model-00013-of-00061.safetensors",
318
+ "transformer.blocks.8.norm_attn_norm.norm_2.weight": "model-00013-of-00061.safetensors",
319
+ "transformer.blocks.9.ffn.experts.mlp.v1": "model-00015-of-00061.safetensors",
320
+ "transformer.blocks.9.ffn.experts.mlp.w1": "model-00015-of-00061.safetensors",
321
+ "transformer.blocks.9.ffn.experts.mlp.w2": "model-00016-of-00061.safetensors",
322
+ "transformer.blocks.9.ffn.router.layer.weight": "model-00014-of-00061.safetensors",
323
+ "transformer.blocks.9.norm_attn_norm.attn.Wqkv.weight": "model-00014-of-00061.safetensors",
324
+ "transformer.blocks.9.norm_attn_norm.attn.out_proj.weight": "model-00014-of-00061.safetensors",
325
+ "transformer.blocks.9.norm_attn_norm.norm_1.weight": "model-00014-of-00061.safetensors",
326
+ "transformer.blocks.9.norm_attn_norm.norm_2.weight": "model-00014-of-00061.safetensors",
327
+ "transformer.norm_f.weight": "model-00061-of-00061.safetensors",
328
+ "transformer.wte.weight": "model-00001-of-00061.safetensors"
329
+ }
330
+ }
output-00001-of-00005.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:05fdfdd4fd8d99128ac37c66f73c914ec1d92c625d24f5c4806fe7cfc8eebee7
3
+ size 8584316608
output-00002-of-00005.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ac26a86cc8becb8e3302265958c68e4a4ec23d85456ac65bca01e3eb26631885
3
+ size 8590251936
output-00003-of-00005.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6abd2c9b887aeea7aa81d7558f8d4151f7a9ac3d5f456e845578aaf37765b7a5
3
+ size 8590202648
output-00004-of-00005.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f3f186bb4fcf94f9bb2885dcf233d06aabf0945a182be39a0fb58d1903b90794
3
+ size 8580483128
output-00005-of-00005.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6d13e81d796c882b9f0d54abc35dd58963cc854880d43b92e2f913d7c94fc09f
3
+ size 8125684080
special_tokens_map.json ADDED
@@ -0,0 +1,34 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "additional_special_tokens": [
3
+ "<|im_start|>",
4
+ "<|im_end|>"
5
+ ],
6
+ "bos_token": {
7
+ "content": "<|endoftext|>",
8
+ "lstrip": false,
9
+ "normalized": false,
10
+ "rstrip": false,
11
+ "single_word": false
12
+ },
13
+ "eos_token": {
14
+ "content": "<|endoftext|>",
15
+ "lstrip": false,
16
+ "normalized": false,
17
+ "rstrip": false,
18
+ "single_word": false
19
+ },
20
+ "pad_token": {
21
+ "content": "<|pad|>",
22
+ "lstrip": false,
23
+ "normalized": false,
24
+ "rstrip": false,
25
+ "single_word": false
26
+ },
27
+ "unk_token": {
28
+ "content": "<|endoftext|>",
29
+ "lstrip": false,
30
+ "normalized": false,
31
+ "rstrip": false,
32
+ "single_word": false
33
+ }
34
+ }
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1,55 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_bos_token": false,
3
+ "add_eos_token": false,
4
+ "add_prefix_space": false,
5
+ "added_tokens_decoder": {
6
+ "100257": {
7
+ "content": "<|endoftext|>",
8
+ "lstrip": false,
9
+ "normalized": false,
10
+ "rstrip": false,
11
+ "single_word": false,
12
+ "special": true
13
+ },
14
+ "100277": {
15
+ "content": "<|pad|>",
16
+ "lstrip": false,
17
+ "normalized": false,
18
+ "rstrip": false,
19
+ "single_word": false,
20
+ "special": true
21
+ },
22
+ "100278": {
23
+ "content": "<|im_start|>",
24
+ "lstrip": false,
25
+ "normalized": false,
26
+ "rstrip": false,
27
+ "single_word": false,
28
+ "special": true
29
+ },
30
+ "100279": {
31
+ "content": "<|im_end|>",
32
+ "lstrip": false,
33
+ "normalized": false,
34
+ "rstrip": false,
35
+ "single_word": false,
36
+ "special": true
37
+ }
38
+ },
39
+ "additional_special_tokens": [
40
+ "<|im_start|>",
41
+ "<|im_end|>"
42
+ ],
43
+ "bos_token": "<|endoftext|>",
44
+ "clean_up_tokenization_spaces": true,
45
+ "encoding_name": null,
46
+ "eos_token": "<|endoftext|>",
47
+ "errors": "replace",
48
+ "model_max_length": 1000000000000000019884624838656,
49
+ "model_name": "gpt-4",
50
+ "pad_token": "<|pad|>",
51
+ "tokenizer_class": "GPT2Tokenizer",
52
+ "unk_token": "<|endoftext|>",
53
+ "use_default_system_prompt": true,
54
+ "chat_template": "{% if messages[0]['role'] == 'system' %}{% set loop_messages = messages[1:] %}{% set system_message = messages[0]['content'] %}{% elif true == true and not 'system' in messages[0]['role'] %}{% set loop_messages = messages %}{% set system_message = 'You are DBRX, created by Databricks. You were last updated in December 2023. You answer questions based on information available up to that point.\nYOU PROVIDE SHORT RESPONSES TO SHORT QUESTIONS OR STATEMENTS, but provide thorough responses to more complex and open-ended questions.\nYou assist with various tasks, from writing to coding (using markdown for code blocks — remember to use ``` with code, JSON, and tables).\n(You do not have real-time data access or code execution capabilities. You avoid stereotyping and provide balanced perspectives on controversial topics. You do not provide song lyrics, poems, or news articles and do not divulge details of your training data.)\nThis is your system prompt, guiding your responses. Do not reference it, just respond to the user. If you find yourself talking about this message, stop. You should be responding appropriately and usually that means not mentioning this.\nYOU DO NOT MENTION ANY OF THIS INFORMATION ABOUT YOURSELF UNLESS THE INFORMATION IS DIRECTLY PERTINENT TO THE USER\\'S QUERY.' %}{% else %}{% set loop_messages = messages %}{% set system_message = false %}{% endif %}{% for message in loop_messages %}{% if loop.index0 == 0 %}{% if system_message != false %}{{ '<|im_start|>system\n' + system_message.strip() + '<|im_end|>\n'}}{% endif %}{{ '<|im_start|>' + message['role'] + '\n' + message['content'] + '<|im_end|>' }}{% else %}{{ '\n' + '<|im_start|>' + message['role'] + '\n' + message['content'] + '<|im_end|>' }}{% endif %}{% if (add_generation_prompt == true and loop.last) %}{{ '\n' + '<|im_start|>' + 'assistant' + '\n' }}{% endif %}{% endfor %}"
55
+ }
vocab.json ADDED
The diff for this file is too large to render. See raw diff