Hugging Face's logo

imi2
/
oxenai_1bitLLM_bitnet_b1_58-large-instruct-v2-gguf

GGUF
Inference Endpoints
Model card Files Community
imi2 commited on
Commit
df1ac9f
β€’
1 Parent(s): 14f73c8

Upload 4 files

Browse files
Files changed (5) hide show
  1. .gitattributes +2 -0
  2. bitnet_b1_58-large-1bitLLM_bitnet_b1_58-instruct-v2-TQ1_0.gguf +3 -0
  3. bitnet_b1_58-large-1bitLLM_bitnet_b1_58-instruct-v2-TQ2_0.gguf +3 -0
  4. conversion-tq1_0.txt +292 -0
  5. conversion-tq2_0.txt +292 -0
.gitattributes CHANGED
@@ -33,3 +33,5 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
33
  *.zip filter=lfs diff=lfs merge=lfs -text
34
  *.zst filter=lfs diff=lfs merge=lfs -text
35
  *tfevents* filter=lfs diff=lfs merge=lfs -text
 
 
 
33
  *.zip filter=lfs diff=lfs merge=lfs -text
34
  *.zst filter=lfs diff=lfs merge=lfs -text
35
  *tfevents* filter=lfs diff=lfs merge=lfs -text
36
+ bitnet_b1_58-large-1bitLLM_bitnet_b1_58-instruct-v2-TQ1_0.gguf filter=lfs diff=lfs merge=lfs -text
37
+ bitnet_b1_58-large-1bitLLM_bitnet_b1_58-instruct-v2-TQ2_0.gguf filter=lfs diff=lfs merge=lfs -text
bitnet_b1_58-large-1bitLLM_bitnet_b1_58-instruct-v2-TQ1_0.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f7f9d9e0aa148ec3e377ca846518587c20ecfdca4490d33f3cf414d0b047e157
3
+ size 243219136
bitnet_b1_58-large-1bitLLM_bitnet_b1_58-instruct-v2-TQ2_0.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a1e87fff1e0358afde03a7ea6e7e92d7dc9df6b4da8aae7841764674051de713
3
+ size 275069632
conversion-tq1_0.txt ADDED
@@ -0,0 +1,292 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ python convert_hf_to_gguf.py --outtype tq1_0 /home/user/Storage/1bitLLM_bitnet_b1_58-large-instruct-v2
2
+ INFO:hf-to-gguf:Loading model: 1bitLLM_bitnet_b1_58-large-instruct-v2
3
+ INFO:gguf.gguf_writer:gguf: This GGUF file is for Little Endian only
4
+ INFO:hf-to-gguf:Exporting model...
5
+ INFO:hf-to-gguf:gguf: loading model part 'model.safetensors'
6
+ INFO:hf-to-gguf:token_embd.weight, torch.float32 --> F16, shape = {1536, 32002}
7
+ INFO:hf-to-gguf:blk.0.attn_norm.weight, torch.float32 --> F32, shape = {1536}
8
+ INFO:hf-to-gguf:blk.0.ffn_down.weight, torch.float32 --> TQ1_0, shape = {4096, 1536}
9
+ INFO:hf-to-gguf:blk.0.ffn_sub_norm.weight, torch.float32 --> F32, shape = {4096}
10
+ INFO:hf-to-gguf:blk.0.ffn_gate.weight, torch.float32 --> TQ1_0, shape = {1536, 4096}
11
+ INFO:hf-to-gguf:blk.0.ffn_up.weight, torch.float32 --> TQ1_0, shape = {1536, 4096}
12
+ INFO:hf-to-gguf:blk.0.ffn_norm.weight, torch.float32 --> F32, shape = {1536}
13
+ INFO:hf-to-gguf:blk.0.attn_sub_norm.weight, torch.float32 --> F32, shape = {1536}
14
+ INFO:hf-to-gguf:blk.0.attn_k.weight, torch.float32 --> TQ1_0, shape = {1536, 1536}
15
+ INFO:hf-to-gguf:blk.0.attn_output.weight, torch.float32 --> TQ1_0, shape = {1536, 1536}
16
+ INFO:hf-to-gguf:blk.0.attn_q.weight, torch.float32 --> TQ1_0, shape = {1536, 1536}
17
+ INFO:hf-to-gguf:blk.0.attn_v.weight, torch.float32 --> TQ1_0, shape = {1536, 1536}
18
+ INFO:hf-to-gguf:blk.1.attn_norm.weight, torch.float32 --> F32, shape = {1536}
19
+ INFO:hf-to-gguf:blk.1.ffn_down.weight, torch.float32 --> TQ1_0, shape = {4096, 1536}
20
+ INFO:hf-to-gguf:blk.1.ffn_sub_norm.weight, torch.float32 --> F32, shape = {4096}
21
+ INFO:hf-to-gguf:blk.1.ffn_gate.weight, torch.float32 --> TQ1_0, shape = {1536, 4096}
22
+ INFO:hf-to-gguf:blk.1.ffn_up.weight, torch.float32 --> TQ1_0, shape = {1536, 4096}
23
+ INFO:hf-to-gguf:blk.1.ffn_norm.weight, torch.float32 --> F32, shape = {1536}
24
+ INFO:hf-to-gguf:blk.1.attn_sub_norm.weight, torch.float32 --> F32, shape = {1536}
25
+ INFO:hf-to-gguf:blk.1.attn_k.weight, torch.float32 --> TQ1_0, shape = {1536, 1536}
26
+ INFO:hf-to-gguf:blk.1.attn_output.weight, torch.float32 --> TQ1_0, shape = {1536, 1536}
27
+ INFO:hf-to-gguf:blk.1.attn_q.weight, torch.float32 --> TQ1_0, shape = {1536, 1536}
28
+ INFO:hf-to-gguf:blk.1.attn_v.weight, torch.float32 --> TQ1_0, shape = {1536, 1536}
29
+ INFO:hf-to-gguf:blk.10.attn_norm.weight, torch.float32 --> F32, shape = {1536}
30
+ INFO:hf-to-gguf:blk.10.ffn_down.weight, torch.float32 --> TQ1_0, shape = {4096, 1536}
31
+ INFO:hf-to-gguf:blk.10.ffn_sub_norm.weight, torch.float32 --> F32, shape = {4096}
32
+ INFO:hf-to-gguf:blk.10.ffn_gate.weight, torch.float32 --> TQ1_0, shape = {1536, 4096}
33
+ INFO:hf-to-gguf:blk.10.ffn_up.weight, torch.float32 --> TQ1_0, shape = {1536, 4096}
34
+ INFO:hf-to-gguf:blk.10.ffn_norm.weight, torch.float32 --> F32, shape = {1536}
35
+ INFO:hf-to-gguf:blk.10.attn_sub_norm.weight, torch.float32 --> F32, shape = {1536}
36
+ INFO:hf-to-gguf:blk.10.attn_k.weight, torch.float32 --> TQ1_0, shape = {1536, 1536}
37
+ INFO:hf-to-gguf:blk.10.attn_output.weight, torch.float32 --> TQ1_0, shape = {1536, 1536}
38
+ INFO:hf-to-gguf:blk.10.attn_q.weight, torch.float32 --> TQ1_0, shape = {1536, 1536}
39
+ INFO:hf-to-gguf:blk.10.attn_v.weight, torch.float32 --> TQ1_0, shape = {1536, 1536}
40
+ INFO:hf-to-gguf:blk.11.attn_norm.weight, torch.float32 --> F32, shape = {1536}
41
+ INFO:hf-to-gguf:blk.11.ffn_down.weight, torch.float32 --> TQ1_0, shape = {4096, 1536}
42
+ INFO:hf-to-gguf:blk.11.ffn_sub_norm.weight, torch.float32 --> F32, shape = {4096}
43
+ INFO:hf-to-gguf:blk.11.ffn_gate.weight, torch.float32 --> TQ1_0, shape = {1536, 4096}
44
+ INFO:hf-to-gguf:blk.11.ffn_up.weight, torch.float32 --> TQ1_0, shape = {1536, 4096}
45
+ INFO:hf-to-gguf:blk.11.ffn_norm.weight, torch.float32 --> F32, shape = {1536}
46
+ INFO:hf-to-gguf:blk.11.attn_sub_norm.weight, torch.float32 --> F32, shape = {1536}
47
+ INFO:hf-to-gguf:blk.11.attn_k.weight, torch.float32 --> TQ1_0, shape = {1536, 1536}
48
+ INFO:hf-to-gguf:blk.11.attn_output.weight, torch.float32 --> TQ1_0, shape = {1536, 1536}
49
+ INFO:hf-to-gguf:blk.11.attn_q.weight, torch.float32 --> TQ1_0, shape = {1536, 1536}
50
+ INFO:hf-to-gguf:blk.11.attn_v.weight, torch.float32 --> TQ1_0, shape = {1536, 1536}
51
+ INFO:hf-to-gguf:blk.12.attn_norm.weight, torch.float32 --> F32, shape = {1536}
52
+ INFO:hf-to-gguf:blk.12.ffn_down.weight, torch.float32 --> TQ1_0, shape = {4096, 1536}
53
+ INFO:hf-to-gguf:blk.12.ffn_sub_norm.weight, torch.float32 --> F32, shape = {4096}
54
+ INFO:hf-to-gguf:blk.12.ffn_gate.weight, torch.float32 --> TQ1_0, shape = {1536, 4096}
55
+ INFO:hf-to-gguf:blk.12.ffn_up.weight, torch.float32 --> TQ1_0, shape = {1536, 4096}
56
+ INFO:hf-to-gguf:blk.12.ffn_norm.weight, torch.float32 --> F32, shape = {1536}
57
+ INFO:hf-to-gguf:blk.12.attn_sub_norm.weight, torch.float32 --> F32, shape = {1536}
58
+ INFO:hf-to-gguf:blk.12.attn_k.weight, torch.float32 --> TQ1_0, shape = {1536, 1536}
59
+ INFO:hf-to-gguf:blk.12.attn_output.weight, torch.float32 --> TQ1_0, shape = {1536, 1536}
60
+ INFO:hf-to-gguf:blk.12.attn_q.weight, torch.float32 --> TQ1_0, shape = {1536, 1536}
61
+ INFO:hf-to-gguf:blk.12.attn_v.weight, torch.float32 --> TQ1_0, shape = {1536, 1536}
62
+ INFO:hf-to-gguf:blk.13.attn_norm.weight, torch.float32 --> F32, shape = {1536}
63
+ INFO:hf-to-gguf:blk.13.ffn_down.weight, torch.float32 --> TQ1_0, shape = {4096, 1536}
64
+ INFO:hf-to-gguf:blk.13.ffn_sub_norm.weight, torch.float32 --> F32, shape = {4096}
65
+ INFO:hf-to-gguf:blk.13.ffn_gate.weight, torch.float32 --> TQ1_0, shape = {1536, 4096}
66
+ INFO:hf-to-gguf:blk.13.ffn_up.weight, torch.float32 --> TQ1_0, shape = {1536, 4096}
67
+ INFO:hf-to-gguf:blk.13.ffn_norm.weight, torch.float32 --> F32, shape = {1536}
68
+ INFO:hf-to-gguf:blk.13.attn_sub_norm.weight, torch.float32 --> F32, shape = {1536}
69
+ INFO:hf-to-gguf:blk.13.attn_k.weight, torch.float32 --> TQ1_0, shape = {1536, 1536}
70
+ INFO:hf-to-gguf:blk.13.attn_output.weight, torch.float32 --> TQ1_0, shape = {1536, 1536}
71
+ INFO:hf-to-gguf:blk.13.attn_q.weight, torch.float32 --> TQ1_0, shape = {1536, 1536}
72
+ INFO:hf-to-gguf:blk.13.attn_v.weight, torch.float32 --> TQ1_0, shape = {1536, 1536}
73
+ INFO:hf-to-gguf:blk.14.attn_norm.weight, torch.float32 --> F32, shape = {1536}
74
+ INFO:hf-to-gguf:blk.14.ffn_down.weight, torch.float32 --> TQ1_0, shape = {4096, 1536}
75
+ INFO:hf-to-gguf:blk.14.ffn_sub_norm.weight, torch.float32 --> F32, shape = {4096}
76
+ INFO:hf-to-gguf:blk.14.ffn_gate.weight, torch.float32 --> TQ1_0, shape = {1536, 4096}
77
+ INFO:hf-to-gguf:blk.14.ffn_up.weight, torch.float32 --> TQ1_0, shape = {1536, 4096}
78
+ INFO:hf-to-gguf:blk.14.ffn_norm.weight, torch.float32 --> F32, shape = {1536}
79
+ INFO:hf-to-gguf:blk.14.attn_sub_norm.weight, torch.float32 --> F32, shape = {1536}
80
+ INFO:hf-to-gguf:blk.14.attn_k.weight, torch.float32 --> TQ1_0, shape = {1536, 1536}
81
+ INFO:hf-to-gguf:blk.14.attn_output.weight, torch.float32 --> TQ1_0, shape = {1536, 1536}
82
+ INFO:hf-to-gguf:blk.14.attn_q.weight, torch.float32 --> TQ1_0, shape = {1536, 1536}
83
+ INFO:hf-to-gguf:blk.14.attn_v.weight, torch.float32 --> TQ1_0, shape = {1536, 1536}
84
+ INFO:hf-to-gguf:blk.15.attn_norm.weight, torch.float32 --> F32, shape = {1536}
85
+ INFO:hf-to-gguf:blk.15.ffn_down.weight, torch.float32 --> TQ1_0, shape = {4096, 1536}
86
+ INFO:hf-to-gguf:blk.15.ffn_sub_norm.weight, torch.float32 --> F32, shape = {4096}
87
+ INFO:hf-to-gguf:blk.15.ffn_gate.weight, torch.float32 --> TQ1_0, shape = {1536, 4096}
88
+ INFO:hf-to-gguf:blk.15.ffn_up.weight, torch.float32 --> TQ1_0, shape = {1536, 4096}
89
+ INFO:hf-to-gguf:blk.15.ffn_norm.weight, torch.float32 --> F32, shape = {1536}
90
+ INFO:hf-to-gguf:blk.15.attn_sub_norm.weight, torch.float32 --> F32, shape = {1536}
91
+ INFO:hf-to-gguf:blk.15.attn_k.weight, torch.float32 --> TQ1_0, shape = {1536, 1536}
92
+ INFO:hf-to-gguf:blk.15.attn_output.weight, torch.float32 --> TQ1_0, shape = {1536, 1536}
93
+ INFO:hf-to-gguf:blk.15.attn_q.weight, torch.float32 --> TQ1_0, shape = {1536, 1536}
94
+ INFO:hf-to-gguf:blk.15.attn_v.weight, torch.float32 --> TQ1_0, shape = {1536, 1536}
95
+ INFO:hf-to-gguf:blk.16.attn_norm.weight, torch.float32 --> F32, shape = {1536}
96
+ INFO:hf-to-gguf:blk.16.ffn_down.weight, torch.float32 --> TQ1_0, shape = {4096, 1536}
97
+ INFO:hf-to-gguf:blk.16.ffn_sub_norm.weight, torch.float32 --> F32, shape = {4096}
98
+ INFO:hf-to-gguf:blk.16.ffn_gate.weight, torch.float32 --> TQ1_0, shape = {1536, 4096}
99
+ INFO:hf-to-gguf:blk.16.ffn_up.weight, torch.float32 --> TQ1_0, shape = {1536, 4096}
100
+ INFO:hf-to-gguf:blk.16.ffn_norm.weight, torch.float32 --> F32, shape = {1536}
101
+ INFO:hf-to-gguf:blk.16.attn_sub_norm.weight, torch.float32 --> F32, shape = {1536}
102
+ INFO:hf-to-gguf:blk.16.attn_k.weight, torch.float32 --> TQ1_0, shape = {1536, 1536}
103
+ INFO:hf-to-gguf:blk.16.attn_output.weight, torch.float32 --> TQ1_0, shape = {1536, 1536}
104
+ INFO:hf-to-gguf:blk.16.attn_q.weight, torch.float32 --> TQ1_0, shape = {1536, 1536}
105
+ INFO:hf-to-gguf:blk.16.attn_v.weight, torch.float32 --> TQ1_0, shape = {1536, 1536}
106
+ INFO:hf-to-gguf:blk.17.attn_norm.weight, torch.float32 --> F32, shape = {1536}
107
+ INFO:hf-to-gguf:blk.17.ffn_down.weight, torch.float32 --> TQ1_0, shape = {4096, 1536}
108
+ INFO:hf-to-gguf:blk.17.ffn_sub_norm.weight, torch.float32 --> F32, shape = {4096}
109
+ INFO:hf-to-gguf:blk.17.ffn_gate.weight, torch.float32 --> TQ1_0, shape = {1536, 4096}
110
+ INFO:hf-to-gguf:blk.17.ffn_up.weight, torch.float32 --> TQ1_0, shape = {1536, 4096}
111
+ INFO:hf-to-gguf:blk.17.ffn_norm.weight, torch.float32 --> F32, shape = {1536}
112
+ INFO:hf-to-gguf:blk.17.attn_sub_norm.weight, torch.float32 --> F32, shape = {1536}
113
+ INFO:hf-to-gguf:blk.17.attn_k.weight, torch.float32 --> TQ1_0, shape = {1536, 1536}
114
+ INFO:hf-to-gguf:blk.17.attn_output.weight, torch.float32 --> TQ1_0, shape = {1536, 1536}
115
+ INFO:hf-to-gguf:blk.17.attn_q.weight, torch.float32 --> TQ1_0, shape = {1536, 1536}
116
+ INFO:hf-to-gguf:blk.17.attn_v.weight, torch.float32 --> TQ1_0, shape = {1536, 1536}
117
+ INFO:hf-to-gguf:blk.18.attn_norm.weight, torch.float32 --> F32, shape = {1536}
118
+ INFO:hf-to-gguf:blk.18.ffn_down.weight, torch.float32 --> TQ1_0, shape = {4096, 1536}
119
+ INFO:hf-to-gguf:blk.18.ffn_sub_norm.weight, torch.float32 --> F32, shape = {4096}
120
+ INFO:hf-to-gguf:blk.18.ffn_gate.weight, torch.float32 --> TQ1_0, shape = {1536, 4096}
121
+ INFO:hf-to-gguf:blk.18.ffn_up.weight, torch.float32 --> TQ1_0, shape = {1536, 4096}
122
+ INFO:hf-to-gguf:blk.18.ffn_norm.weight, torch.float32 --> F32, shape = {1536}
123
+ INFO:hf-to-gguf:blk.18.attn_sub_norm.weight, torch.float32 --> F32, shape = {1536}
124
+ INFO:hf-to-gguf:blk.18.attn_k.weight, torch.float32 --> TQ1_0, shape = {1536, 1536}
125
+ INFO:hf-to-gguf:blk.18.attn_output.weight, torch.float32 --> TQ1_0, shape = {1536, 1536}
126
+ INFO:hf-to-gguf:blk.18.attn_q.weight, torch.float32 --> TQ1_0, shape = {1536, 1536}
127
+ INFO:hf-to-gguf:blk.18.attn_v.weight, torch.float32 --> TQ1_0, shape = {1536, 1536}
128
+ INFO:hf-to-gguf:blk.19.attn_norm.weight, torch.float32 --> F32, shape = {1536}
129
+ INFO:hf-to-gguf:blk.19.ffn_down.weight, torch.float32 --> TQ1_0, shape = {4096, 1536}
130
+ INFO:hf-to-gguf:blk.19.ffn_sub_norm.weight, torch.float32 --> F32, shape = {4096}
131
+ INFO:hf-to-gguf:blk.19.ffn_gate.weight, torch.float32 --> TQ1_0, shape = {1536, 4096}
132
+ INFO:hf-to-gguf:blk.19.ffn_up.weight, torch.float32 --> TQ1_0, shape = {1536, 4096}
133
+ INFO:hf-to-gguf:blk.19.ffn_norm.weight, torch.float32 --> F32, shape = {1536}
134
+ INFO:hf-to-gguf:blk.19.attn_sub_norm.weight, torch.float32 --> F32, shape = {1536}
135
+ INFO:hf-to-gguf:blk.19.attn_k.weight, torch.float32 --> TQ1_0, shape = {1536, 1536}
136
+ INFO:hf-to-gguf:blk.19.attn_output.weight, torch.float32 --> TQ1_0, shape = {1536, 1536}
137
+ INFO:hf-to-gguf:blk.19.attn_q.weight, torch.float32 --> TQ1_0, shape = {1536, 1536}
138
+ INFO:hf-to-gguf:blk.19.attn_v.weight, torch.float32 --> TQ1_0, shape = {1536, 1536}
139
+ INFO:hf-to-gguf:blk.2.attn_norm.weight, torch.float32 --> F32, shape = {1536}
140
+ INFO:hf-to-gguf:blk.2.ffn_down.weight, torch.float32 --> TQ1_0, shape = {4096, 1536}
141
+ INFO:hf-to-gguf:blk.2.ffn_sub_norm.weight, torch.float32 --> F32, shape = {4096}
142
+ INFO:hf-to-gguf:blk.2.ffn_gate.weight, torch.float32 --> TQ1_0, shape = {1536, 4096}
143
+ INFO:hf-to-gguf:blk.2.ffn_up.weight, torch.float32 --> TQ1_0, shape = {1536, 4096}
144
+ INFO:hf-to-gguf:blk.2.ffn_norm.weight, torch.float32 --> F32, shape = {1536}
145
+ INFO:hf-to-gguf:blk.2.attn_sub_norm.weight, torch.float32 --> F32, shape = {1536}
146
+ INFO:hf-to-gguf:blk.2.attn_k.weight, torch.float32 --> TQ1_0, shape = {1536, 1536}
147
+ INFO:hf-to-gguf:blk.2.attn_output.weight, torch.float32 --> TQ1_0, shape = {1536, 1536}
148
+ INFO:hf-to-gguf:blk.2.attn_q.weight, torch.float32 --> TQ1_0, shape = {1536, 1536}
149
+ INFO:hf-to-gguf:blk.2.attn_v.weight, torch.float32 --> TQ1_0, shape = {1536, 1536}
150
+ INFO:hf-to-gguf:blk.20.attn_norm.weight, torch.float32 --> F32, shape = {1536}
151
+ INFO:hf-to-gguf:blk.20.ffn_down.weight, torch.float32 --> TQ1_0, shape = {4096, 1536}
152
+ INFO:hf-to-gguf:blk.20.ffn_sub_norm.weight, torch.float32 --> F32, shape = {4096}
153
+ INFO:hf-to-gguf:blk.20.ffn_gate.weight, torch.float32 --> TQ1_0, shape = {1536, 4096}
154
+ INFO:hf-to-gguf:blk.20.ffn_up.weight, torch.float32 --> TQ1_0, shape = {1536, 4096}
155
+ INFO:hf-to-gguf:blk.20.ffn_norm.weight, torch.float32 --> F32, shape = {1536}
156
+ INFO:hf-to-gguf:blk.20.attn_sub_norm.weight, torch.float32 --> F32, shape = {1536}
157
+ INFO:hf-to-gguf:blk.20.attn_k.weight, torch.float32 --> TQ1_0, shape = {1536, 1536}
158
+ INFO:hf-to-gguf:blk.20.attn_output.weight, torch.float32 --> TQ1_0, shape = {1536, 1536}
159
+ INFO:hf-to-gguf:blk.20.attn_q.weight, torch.float32 --> TQ1_0, shape = {1536, 1536}
160
+ INFO:hf-to-gguf:blk.20.attn_v.weight, torch.float32 --> TQ1_0, shape = {1536, 1536}
161
+ INFO:hf-to-gguf:blk.21.attn_norm.weight, torch.float32 --> F32, shape = {1536}
162
+ INFO:hf-to-gguf:blk.21.ffn_down.weight, torch.float32 --> TQ1_0, shape = {4096, 1536}
163
+ INFO:hf-to-gguf:blk.21.ffn_sub_norm.weight, torch.float32 --> F32, shape = {4096}
164
+ INFO:hf-to-gguf:blk.21.ffn_gate.weight, torch.float32 --> TQ1_0, shape = {1536, 4096}
165
+ INFO:hf-to-gguf:blk.21.ffn_up.weight, torch.float32 --> TQ1_0, shape = {1536, 4096}
166
+ INFO:hf-to-gguf:blk.21.ffn_norm.weight, torch.float32 --> F32, shape = {1536}
167
+ INFO:hf-to-gguf:blk.21.attn_sub_norm.weight, torch.float32 --> F32, shape = {1536}
168
+ INFO:hf-to-gguf:blk.21.attn_k.weight, torch.float32 --> TQ1_0, shape = {1536, 1536}
169
+ INFO:hf-to-gguf:blk.21.attn_output.weight, torch.float32 --> TQ1_0, shape = {1536, 1536}
170
+ INFO:hf-to-gguf:blk.21.attn_q.weight, torch.float32 --> TQ1_0, shape = {1536, 1536}
171
+ INFO:hf-to-gguf:blk.21.attn_v.weight, torch.float32 --> TQ1_0, shape = {1536, 1536}
172
+ INFO:hf-to-gguf:blk.22.attn_norm.weight, torch.float32 --> F32, shape = {1536}
173
+ INFO:hf-to-gguf:blk.22.ffn_down.weight, torch.float32 --> TQ1_0, shape = {4096, 1536}
174
+ INFO:hf-to-gguf:blk.22.ffn_sub_norm.weight, torch.float32 --> F32, shape = {4096}
175
+ INFO:hf-to-gguf:blk.22.ffn_gate.weight, torch.float32 --> TQ1_0, shape = {1536, 4096}
176
+ INFO:hf-to-gguf:blk.22.ffn_up.weight, torch.float32 --> TQ1_0, shape = {1536, 4096}
177
+ INFO:hf-to-gguf:blk.22.ffn_norm.weight, torch.float32 --> F32, shape = {1536}
178
+ INFO:hf-to-gguf:blk.22.attn_sub_norm.weight, torch.float32 --> F32, shape = {1536}
179
+ INFO:hf-to-gguf:blk.22.attn_k.weight, torch.float32 --> TQ1_0, shape = {1536, 1536}
180
+ INFO:hf-to-gguf:blk.22.attn_output.weight, torch.float32 --> TQ1_0, shape = {1536, 1536}
181
+ INFO:hf-to-gguf:blk.22.attn_q.weight, torch.float32 --> TQ1_0, shape = {1536, 1536}
182
+ INFO:hf-to-gguf:blk.22.attn_v.weight, torch.float32 --> TQ1_0, shape = {1536, 1536}
183
+ INFO:hf-to-gguf:blk.23.attn_norm.weight, torch.float32 --> F32, shape = {1536}
184
+ INFO:hf-to-gguf:blk.23.ffn_down.weight, torch.float32 --> TQ1_0, shape = {4096, 1536}
185
+ INFO:hf-to-gguf:blk.23.ffn_sub_norm.weight, torch.float32 --> F32, shape = {4096}
186
+ INFO:hf-to-gguf:blk.23.ffn_gate.weight, torch.float32 --> TQ1_0, shape = {1536, 4096}
187
+ INFO:hf-to-gguf:blk.23.ffn_up.weight, torch.float32 --> TQ1_0, shape = {1536, 4096}
188
+ INFO:hf-to-gguf:blk.23.ffn_norm.weight, torch.float32 --> F32, shape = {1536}
189
+ INFO:hf-to-gguf:blk.23.attn_sub_norm.weight, torch.float32 --> F32, shape = {1536}
190
+ INFO:hf-to-gguf:blk.23.attn_k.weight, torch.float32 --> TQ1_0, shape = {1536, 1536}
191
+ INFO:hf-to-gguf:blk.23.attn_output.weight, torch.float32 --> TQ1_0, shape = {1536, 1536}
192
+ INFO:hf-to-gguf:blk.23.attn_q.weight, torch.float32 --> TQ1_0, shape = {1536, 1536}
193
+ INFO:hf-to-gguf:blk.23.attn_v.weight, torch.float32 --> TQ1_0, shape = {1536, 1536}
194
+ INFO:hf-to-gguf:blk.3.attn_norm.weight, torch.float32 --> F32, shape = {1536}
195
+ INFO:hf-to-gguf:blk.3.ffn_down.weight, torch.float32 --> TQ1_0, shape = {4096, 1536}
196
+ INFO:hf-to-gguf:blk.3.ffn_sub_norm.weight, torch.float32 --> F32, shape = {4096}
197
+ INFO:hf-to-gguf:blk.3.ffn_gate.weight, torch.float32 --> TQ1_0, shape = {1536, 4096}
198
+ INFO:hf-to-gguf:blk.3.ffn_up.weight, torch.float32 --> TQ1_0, shape = {1536, 4096}
199
+ INFO:hf-to-gguf:blk.3.ffn_norm.weight, torch.float32 --> F32, shape = {1536}
200
+ INFO:hf-to-gguf:blk.3.attn_sub_norm.weight, torch.float32 --> F32, shape = {1536}
201
+ INFO:hf-to-gguf:blk.3.attn_k.weight, torch.float32 --> TQ1_0, shape = {1536, 1536}
202
+ INFO:hf-to-gguf:blk.3.attn_output.weight, torch.float32 --> TQ1_0, shape = {1536, 1536}
203
+ INFO:hf-to-gguf:blk.3.attn_q.weight, torch.float32 --> TQ1_0, shape = {1536, 1536}
204
+ INFO:hf-to-gguf:blk.3.attn_v.weight, torch.float32 --> TQ1_0, shape = {1536, 1536}
205
+ INFO:hf-to-gguf:blk.4.attn_norm.weight, torch.float32 --> F32, shape = {1536}
206
+ INFO:hf-to-gguf:blk.4.ffn_down.weight, torch.float32 --> TQ1_0, shape = {4096, 1536}
207
+ INFO:hf-to-gguf:blk.4.ffn_sub_norm.weight, torch.float32 --> F32, shape = {4096}
208
+ INFO:hf-to-gguf:blk.4.ffn_gate.weight, torch.float32 --> TQ1_0, shape = {1536, 4096}
209
+ INFO:hf-to-gguf:blk.4.ffn_up.weight, torch.float32 --> TQ1_0, shape = {1536, 4096}
210
+ INFO:hf-to-gguf:blk.4.ffn_norm.weight, torch.float32 --> F32, shape = {1536}
211
+ INFO:hf-to-gguf:blk.4.attn_sub_norm.weight, torch.float32 --> F32, shape = {1536}
212
+ INFO:hf-to-gguf:blk.4.attn_k.weight, torch.float32 --> TQ1_0, shape = {1536, 1536}
213
+ INFO:hf-to-gguf:blk.4.attn_output.weight, torch.float32 --> TQ1_0, shape = {1536, 1536}
214
+ INFO:hf-to-gguf:blk.4.attn_q.weight, torch.float32 --> TQ1_0, shape = {1536, 1536}
215
+ INFO:hf-to-gguf:blk.4.attn_v.weight, torch.float32 --> TQ1_0, shape = {1536, 1536}
216
+ INFO:hf-to-gguf:blk.5.attn_norm.weight, torch.float32 --> F32, shape = {1536}
217
+ INFO:hf-to-gguf:blk.5.ffn_down.weight, torch.float32 --> TQ1_0, shape = {4096, 1536}
218
+ INFO:hf-to-gguf:blk.5.ffn_sub_norm.weight, torch.float32 --> F32, shape = {4096}
219
+ INFO:hf-to-gguf:blk.5.ffn_gate.weight, torch.float32 --> TQ1_0, shape = {1536, 4096}
220
+ INFO:hf-to-gguf:blk.5.ffn_up.weight, torch.float32 --> TQ1_0, shape = {1536, 4096}
221
+ INFO:hf-to-gguf:blk.5.ffn_norm.weight, torch.float32 --> F32, shape = {1536}
222
+ INFO:hf-to-gguf:blk.5.attn_sub_norm.weight, torch.float32 --> F32, shape = {1536}
223
+ INFO:hf-to-gguf:blk.5.attn_k.weight, torch.float32 --> TQ1_0, shape = {1536, 1536}
224
+ INFO:hf-to-gguf:blk.5.attn_output.weight, torch.float32 --> TQ1_0, shape = {1536, 1536}
225
+ INFO:hf-to-gguf:blk.5.attn_q.weight, torch.float32 --> TQ1_0, shape = {1536, 1536}
226
+ INFO:hf-to-gguf:blk.5.attn_v.weight, torch.float32 --> TQ1_0, shape = {1536, 1536}
227
+ INFO:hf-to-gguf:blk.6.attn_norm.weight, torch.float32 --> F32, shape = {1536}
228
+ INFO:hf-to-gguf:blk.6.ffn_down.weight, torch.float32 --> TQ1_0, shape = {4096, 1536}
229
+ INFO:hf-to-gguf:blk.6.ffn_sub_norm.weight, torch.float32 --> F32, shape = {4096}
230
+ INFO:hf-to-gguf:blk.6.ffn_gate.weight, torch.float32 --> TQ1_0, shape = {1536, 4096}
231
+ INFO:hf-to-gguf:blk.6.ffn_up.weight, torch.float32 --> TQ1_0, shape = {1536, 4096}
232
+ INFO:hf-to-gguf:blk.6.ffn_norm.weight, torch.float32 --> F32, shape = {1536}
233
+ INFO:hf-to-gguf:blk.6.attn_sub_norm.weight, torch.float32 --> F32, shape = {1536}
234
+ INFO:hf-to-gguf:blk.6.attn_k.weight, torch.float32 --> TQ1_0, shape = {1536, 1536}
235
+ INFO:hf-to-gguf:blk.6.attn_output.weight, torch.float32 --> TQ1_0, shape = {1536, 1536}
236
+ INFO:hf-to-gguf:blk.6.attn_q.weight, torch.float32 --> TQ1_0, shape = {1536, 1536}
237
+ INFO:hf-to-gguf:blk.6.attn_v.weight, torch.float32 --> TQ1_0, shape = {1536, 1536}
238
+ INFO:hf-to-gguf:blk.7.attn_norm.weight, torch.float32 --> F32, shape = {1536}
239
+ INFO:hf-to-gguf:blk.7.ffn_down.weight, torch.float32 --> TQ1_0, shape = {4096, 1536}
240
+ INFO:hf-to-gguf:blk.7.ffn_sub_norm.weight, torch.float32 --> F32, shape = {4096}
241
+ INFO:hf-to-gguf:blk.7.ffn_gate.weight, torch.float32 --> TQ1_0, shape = {1536, 4096}
242
+ INFO:hf-to-gguf:blk.7.ffn_up.weight, torch.float32 --> TQ1_0, shape = {1536, 4096}
243
+ INFO:hf-to-gguf:blk.7.ffn_norm.weight, torch.float32 --> F32, shape = {1536}
244
+ INFO:hf-to-gguf:blk.7.attn_sub_norm.weight, torch.float32 --> F32, shape = {1536}
245
+ INFO:hf-to-gguf:blk.7.attn_k.weight, torch.float32 --> TQ1_0, shape = {1536, 1536}
246
+ INFO:hf-to-gguf:blk.7.attn_output.weight, torch.float32 --> TQ1_0, shape = {1536, 1536}
247
+ INFO:hf-to-gguf:blk.7.attn_q.weight, torch.float32 --> TQ1_0, shape = {1536, 1536}
248
+ INFO:hf-to-gguf:blk.7.attn_v.weight, torch.float32 --> TQ1_0, shape = {1536, 1536}
249
+ INFO:hf-to-gguf:blk.8.attn_norm.weight, torch.float32 --> F32, shape = {1536}
250
+ INFO:hf-to-gguf:blk.8.ffn_down.weight, torch.float32 --> TQ1_0, shape = {4096, 1536}
251
+ INFO:hf-to-gguf:blk.8.ffn_sub_norm.weight, torch.float32 --> F32, shape = {4096}
252
+ INFO:hf-to-gguf:blk.8.ffn_gate.weight, torch.float32 --> TQ1_0, shape = {1536, 4096}
253
+ INFO:hf-to-gguf:blk.8.ffn_up.weight, torch.float32 --> TQ1_0, shape = {1536, 4096}
254
+ INFO:hf-to-gguf:blk.8.ffn_norm.weight, torch.float32 --> F32, shape = {1536}
255
+ INFO:hf-to-gguf:blk.8.attn_sub_norm.weight, torch.float32 --> F32, shape = {1536}
256
+ INFO:hf-to-gguf:blk.8.attn_k.weight, torch.float32 --> TQ1_0, shape = {1536, 1536}
257
+ INFO:hf-to-gguf:blk.8.attn_output.weight, torch.float32 --> TQ1_0, shape = {1536, 1536}
258
+ INFO:hf-to-gguf:blk.8.attn_q.weight, torch.float32 --> TQ1_0, shape = {1536, 1536}
259
+ INFO:hf-to-gguf:blk.8.attn_v.weight, torch.float32 --> TQ1_0, shape = {1536, 1536}
260
+ INFO:hf-to-gguf:blk.9.attn_norm.weight, torch.float32 --> F32, shape = {1536}
261
+ INFO:hf-to-gguf:blk.9.ffn_down.weight, torch.float32 --> TQ1_0, shape = {4096, 1536}
262
+ INFO:hf-to-gguf:blk.9.ffn_sub_norm.weight, torch.float32 --> F32, shape = {4096}
263
+ INFO:hf-to-gguf:blk.9.ffn_gate.weight, torch.float32 --> TQ1_0, shape = {1536, 4096}
264
+ INFO:hf-to-gguf:blk.9.ffn_up.weight, torch.float32 --> TQ1_0, shape = {1536, 4096}
265
+ INFO:hf-to-gguf:blk.9.ffn_norm.weight, torch.float32 --> F32, shape = {1536}
266
+ INFO:hf-to-gguf:blk.9.attn_sub_norm.weight, torch.float32 --> F32, shape = {1536}
267
+ INFO:hf-to-gguf:blk.9.attn_k.weight, torch.float32 --> TQ1_0, shape = {1536, 1536}
268
+ INFO:hf-to-gguf:blk.9.attn_output.weight, torch.float32 --> TQ1_0, shape = {1536, 1536}
269
+ INFO:hf-to-gguf:blk.9.attn_q.weight, torch.float32 --> TQ1_0, shape = {1536, 1536}
270
+ INFO:hf-to-gguf:blk.9.attn_v.weight, torch.float32 --> TQ1_0, shape = {1536, 1536}
271
+ INFO:hf-to-gguf:output_norm.weight, torch.float32 --> F32, shape = {1536}
272
+ INFO:hf-to-gguf:Set meta model
273
+ INFO:hf-to-gguf:Set model parameters
274
+ INFO:hf-to-gguf:gguf: context length = 2048
275
+ INFO:hf-to-gguf:gguf: embedding length = 1536
276
+ INFO:hf-to-gguf:gguf: feed forward length = 4096
277
+ INFO:hf-to-gguf:gguf: head count = 16
278
+ INFO:hf-to-gguf:gguf: key-value head count = 16
279
+ INFO:hf-to-gguf:gguf: rope theta = 10000.0
280
+ INFO:hf-to-gguf:gguf: rms norm epsilon = 1e-05
281
+ INFO:hf-to-gguf:gguf: file type = 36
282
+ INFO:hf-to-gguf:Set model tokenizer
283
+ INFO:gguf.vocab:Setting special token type bos to 1
284
+ INFO:gguf.vocab:Setting special token type eos to 2
285
+ INFO:gguf.vocab:Setting special token type pad to 32000
286
+ INFO:gguf.vocab:Setting add_bos_token to True
287
+ INFO:gguf.vocab:Setting add_eos_token to False
288
+ INFO:hf-to-gguf:Set model quantization version
289
+ INFO:gguf.gguf_writer:Writing the following files:
290
+ INFO:gguf.gguf_writer:/home/user/Storage/1bitLLM_bitnet_b1_58-large-instruct-v2/bitnet_b1_58-large-1bitLLM_bitnet_b1_58-instruct-v2-TQ1_0.gguf: n_tensors = 266, total_size = 242.5M
291
+ Writing: 100%|β–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆοΏ½οΏ½β–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆ| 242M/242M [00:06<00:00, 38.3Mbyte/s]
292
+ INFO:hf-to-gguf:Model successfully exported to /home/user/Storage/1bitLLM_bitnet_b1_58-large-instruct-v2/bitnet_b1_58-large-1bitLLM_bitnet_b1_58-instruct-v2-TQ1_0.gguf
conversion-tq2_0.txt ADDED
@@ -0,0 +1,292 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ python convert_hf_to_gguf.py --outtype tq2_0 /home/user/Storage/1bitLLM_bitnet_b1_58-large-instruct-v2
2
+ INFO:hf-to-gguf:Loading model: 1bitLLM_bitnet_b1_58-large-instruct-v2
3
+ INFO:gguf.gguf_writer:gguf: This GGUF file is for Little Endian only
4
+ INFO:hf-to-gguf:Exporting model...
5
+ INFO:hf-to-gguf:gguf: loading model part 'model.safetensors'
6
+ INFO:hf-to-gguf:token_embd.weight, torch.float32 --> F16, shape = {1536, 32002}
7
+ INFO:hf-to-gguf:blk.0.attn_norm.weight, torch.float32 --> F32, shape = {1536}
8
+ INFO:hf-to-gguf:blk.0.ffn_down.weight, torch.float32 --> TQ2_0, shape = {4096, 1536}
9
+ INFO:hf-to-gguf:blk.0.ffn_sub_norm.weight, torch.float32 --> F32, shape = {4096}
10
+ INFO:hf-to-gguf:blk.0.ffn_gate.weight, torch.float32 --> TQ2_0, shape = {1536, 4096}
11
+ INFO:hf-to-gguf:blk.0.ffn_up.weight, torch.float32 --> TQ2_0, shape = {1536, 4096}
12
+ INFO:hf-to-gguf:blk.0.ffn_norm.weight, torch.float32 --> F32, shape = {1536}
13
+ INFO:hf-to-gguf:blk.0.attn_sub_norm.weight, torch.float32 --> F32, shape = {1536}
14
+ INFO:hf-to-gguf:blk.0.attn_k.weight, torch.float32 --> TQ2_0, shape = {1536, 1536}
15
+ INFO:hf-to-gguf:blk.0.attn_output.weight, torch.float32 --> TQ2_0, shape = {1536, 1536}
16
+ INFO:hf-to-gguf:blk.0.attn_q.weight, torch.float32 --> TQ2_0, shape = {1536, 1536}
17
+ INFO:hf-to-gguf:blk.0.attn_v.weight, torch.float32 --> TQ2_0, shape = {1536, 1536}
18
+ INFO:hf-to-gguf:blk.1.attn_norm.weight, torch.float32 --> F32, shape = {1536}
19
+ INFO:hf-to-gguf:blk.1.ffn_down.weight, torch.float32 --> TQ2_0, shape = {4096, 1536}
20
+ INFO:hf-to-gguf:blk.1.ffn_sub_norm.weight, torch.float32 --> F32, shape = {4096}
21
+ INFO:hf-to-gguf:blk.1.ffn_gate.weight, torch.float32 --> TQ2_0, shape = {1536, 4096}
22
+ INFO:hf-to-gguf:blk.1.ffn_up.weight, torch.float32 --> TQ2_0, shape = {1536, 4096}
23
+ INFO:hf-to-gguf:blk.1.ffn_norm.weight, torch.float32 --> F32, shape = {1536}
24
+ INFO:hf-to-gguf:blk.1.attn_sub_norm.weight, torch.float32 --> F32, shape = {1536}
25
+ INFO:hf-to-gguf:blk.1.attn_k.weight, torch.float32 --> TQ2_0, shape = {1536, 1536}
26
+ INFO:hf-to-gguf:blk.1.attn_output.weight, torch.float32 --> TQ2_0, shape = {1536, 1536}
27
+ INFO:hf-to-gguf:blk.1.attn_q.weight, torch.float32 --> TQ2_0, shape = {1536, 1536}
28
+ INFO:hf-to-gguf:blk.1.attn_v.weight, torch.float32 --> TQ2_0, shape = {1536, 1536}
29
+ INFO:hf-to-gguf:blk.10.attn_norm.weight, torch.float32 --> F32, shape = {1536}
30
+ INFO:hf-to-gguf:blk.10.ffn_down.weight, torch.float32 --> TQ2_0, shape = {4096, 1536}
31
+ INFO:hf-to-gguf:blk.10.ffn_sub_norm.weight, torch.float32 --> F32, shape = {4096}
32
+ INFO:hf-to-gguf:blk.10.ffn_gate.weight, torch.float32 --> TQ2_0, shape = {1536, 4096}
33
+ INFO:hf-to-gguf:blk.10.ffn_up.weight, torch.float32 --> TQ2_0, shape = {1536, 4096}
34
+ INFO:hf-to-gguf:blk.10.ffn_norm.weight, torch.float32 --> F32, shape = {1536}
35
+ INFO:hf-to-gguf:blk.10.attn_sub_norm.weight, torch.float32 --> F32, shape = {1536}
36
+ INFO:hf-to-gguf:blk.10.attn_k.weight, torch.float32 --> TQ2_0, shape = {1536, 1536}
37
+ INFO:hf-to-gguf:blk.10.attn_output.weight, torch.float32 --> TQ2_0, shape = {1536, 1536}
38
+ INFO:hf-to-gguf:blk.10.attn_q.weight, torch.float32 --> TQ2_0, shape = {1536, 1536}
39
+ INFO:hf-to-gguf:blk.10.attn_v.weight, torch.float32 --> TQ2_0, shape = {1536, 1536}
40
+ INFO:hf-to-gguf:blk.11.attn_norm.weight, torch.float32 --> F32, shape = {1536}
41
+ INFO:hf-to-gguf:blk.11.ffn_down.weight, torch.float32 --> TQ2_0, shape = {4096, 1536}
42
+ INFO:hf-to-gguf:blk.11.ffn_sub_norm.weight, torch.float32 --> F32, shape = {4096}
43
+ INFO:hf-to-gguf:blk.11.ffn_gate.weight, torch.float32 --> TQ2_0, shape = {1536, 4096}
44
+ INFO:hf-to-gguf:blk.11.ffn_up.weight, torch.float32 --> TQ2_0, shape = {1536, 4096}
45
+ INFO:hf-to-gguf:blk.11.ffn_norm.weight, torch.float32 --> F32, shape = {1536}
46
+ INFO:hf-to-gguf:blk.11.attn_sub_norm.weight, torch.float32 --> F32, shape = {1536}
47
+ INFO:hf-to-gguf:blk.11.attn_k.weight, torch.float32 --> TQ2_0, shape = {1536, 1536}
48
+ INFO:hf-to-gguf:blk.11.attn_output.weight, torch.float32 --> TQ2_0, shape = {1536, 1536}
49
+ INFO:hf-to-gguf:blk.11.attn_q.weight, torch.float32 --> TQ2_0, shape = {1536, 1536}
50
+ INFO:hf-to-gguf:blk.11.attn_v.weight, torch.float32 --> TQ2_0, shape = {1536, 1536}
51
+ INFO:hf-to-gguf:blk.12.attn_norm.weight, torch.float32 --> F32, shape = {1536}
52
+ INFO:hf-to-gguf:blk.12.ffn_down.weight, torch.float32 --> TQ2_0, shape = {4096, 1536}
53
+ INFO:hf-to-gguf:blk.12.ffn_sub_norm.weight, torch.float32 --> F32, shape = {4096}
54
+ INFO:hf-to-gguf:blk.12.ffn_gate.weight, torch.float32 --> TQ2_0, shape = {1536, 4096}
55
+ INFO:hf-to-gguf:blk.12.ffn_up.weight, torch.float32 --> TQ2_0, shape = {1536, 4096}
56
+ INFO:hf-to-gguf:blk.12.ffn_norm.weight, torch.float32 --> F32, shape = {1536}
57
+ INFO:hf-to-gguf:blk.12.attn_sub_norm.weight, torch.float32 --> F32, shape = {1536}
58
+ INFO:hf-to-gguf:blk.12.attn_k.weight, torch.float32 --> TQ2_0, shape = {1536, 1536}
59
+ INFO:hf-to-gguf:blk.12.attn_output.weight, torch.float32 --> TQ2_0, shape = {1536, 1536}
60
+ INFO:hf-to-gguf:blk.12.attn_q.weight, torch.float32 --> TQ2_0, shape = {1536, 1536}
61
+ INFO:hf-to-gguf:blk.12.attn_v.weight, torch.float32 --> TQ2_0, shape = {1536, 1536}
62
+ INFO:hf-to-gguf:blk.13.attn_norm.weight, torch.float32 --> F32, shape = {1536}
63
+ INFO:hf-to-gguf:blk.13.ffn_down.weight, torch.float32 --> TQ2_0, shape = {4096, 1536}
64
+ INFO:hf-to-gguf:blk.13.ffn_sub_norm.weight, torch.float32 --> F32, shape = {4096}
65
+ INFO:hf-to-gguf:blk.13.ffn_gate.weight, torch.float32 --> TQ2_0, shape = {1536, 4096}
66
+ INFO:hf-to-gguf:blk.13.ffn_up.weight, torch.float32 --> TQ2_0, shape = {1536, 4096}
67
+ INFO:hf-to-gguf:blk.13.ffn_norm.weight, torch.float32 --> F32, shape = {1536}
68
+ INFO:hf-to-gguf:blk.13.attn_sub_norm.weight, torch.float32 --> F32, shape = {1536}
69
+ INFO:hf-to-gguf:blk.13.attn_k.weight, torch.float32 --> TQ2_0, shape = {1536, 1536}
70
+ INFO:hf-to-gguf:blk.13.attn_output.weight, torch.float32 --> TQ2_0, shape = {1536, 1536}
71
+ INFO:hf-to-gguf:blk.13.attn_q.weight, torch.float32 --> TQ2_0, shape = {1536, 1536}
72
+ INFO:hf-to-gguf:blk.13.attn_v.weight, torch.float32 --> TQ2_0, shape = {1536, 1536}
73
+ INFO:hf-to-gguf:blk.14.attn_norm.weight, torch.float32 --> F32, shape = {1536}
74
+ INFO:hf-to-gguf:blk.14.ffn_down.weight, torch.float32 --> TQ2_0, shape = {4096, 1536}
75
+ INFO:hf-to-gguf:blk.14.ffn_sub_norm.weight, torch.float32 --> F32, shape = {4096}
76
+ INFO:hf-to-gguf:blk.14.ffn_gate.weight, torch.float32 --> TQ2_0, shape = {1536, 4096}
77
+ INFO:hf-to-gguf:blk.14.ffn_up.weight, torch.float32 --> TQ2_0, shape = {1536, 4096}
78
+ INFO:hf-to-gguf:blk.14.ffn_norm.weight, torch.float32 --> F32, shape = {1536}
79
+ INFO:hf-to-gguf:blk.14.attn_sub_norm.weight, torch.float32 --> F32, shape = {1536}
80
+ INFO:hf-to-gguf:blk.14.attn_k.weight, torch.float32 --> TQ2_0, shape = {1536, 1536}
81
+ INFO:hf-to-gguf:blk.14.attn_output.weight, torch.float32 --> TQ2_0, shape = {1536, 1536}
82
+ INFO:hf-to-gguf:blk.14.attn_q.weight, torch.float32 --> TQ2_0, shape = {1536, 1536}
83
+ INFO:hf-to-gguf:blk.14.attn_v.weight, torch.float32 --> TQ2_0, shape = {1536, 1536}
84
+ INFO:hf-to-gguf:blk.15.attn_norm.weight, torch.float32 --> F32, shape = {1536}
85
+ INFO:hf-to-gguf:blk.15.ffn_down.weight, torch.float32 --> TQ2_0, shape = {4096, 1536}
86
+ INFO:hf-to-gguf:blk.15.ffn_sub_norm.weight, torch.float32 --> F32, shape = {4096}
87
+ INFO:hf-to-gguf:blk.15.ffn_gate.weight, torch.float32 --> TQ2_0, shape = {1536, 4096}
88
+ INFO:hf-to-gguf:blk.15.ffn_up.weight, torch.float32 --> TQ2_0, shape = {1536, 4096}
89
+ INFO:hf-to-gguf:blk.15.ffn_norm.weight, torch.float32 --> F32, shape = {1536}
90
+ INFO:hf-to-gguf:blk.15.attn_sub_norm.weight, torch.float32 --> F32, shape = {1536}
91
+ INFO:hf-to-gguf:blk.15.attn_k.weight, torch.float32 --> TQ2_0, shape = {1536, 1536}
92
+ INFO:hf-to-gguf:blk.15.attn_output.weight, torch.float32 --> TQ2_0, shape = {1536, 1536}
93
+ INFO:hf-to-gguf:blk.15.attn_q.weight, torch.float32 --> TQ2_0, shape = {1536, 1536}
94
+ INFO:hf-to-gguf:blk.15.attn_v.weight, torch.float32 --> TQ2_0, shape = {1536, 1536}
95
+ INFO:hf-to-gguf:blk.16.attn_norm.weight, torch.float32 --> F32, shape = {1536}
96
+ INFO:hf-to-gguf:blk.16.ffn_down.weight, torch.float32 --> TQ2_0, shape = {4096, 1536}
97
+ INFO:hf-to-gguf:blk.16.ffn_sub_norm.weight, torch.float32 --> F32, shape = {4096}
98
+ INFO:hf-to-gguf:blk.16.ffn_gate.weight, torch.float32 --> TQ2_0, shape = {1536, 4096}
99
+ INFO:hf-to-gguf:blk.16.ffn_up.weight, torch.float32 --> TQ2_0, shape = {1536, 4096}
100
+ INFO:hf-to-gguf:blk.16.ffn_norm.weight, torch.float32 --> F32, shape = {1536}
101
+ INFO:hf-to-gguf:blk.16.attn_sub_norm.weight, torch.float32 --> F32, shape = {1536}
102
+ INFO:hf-to-gguf:blk.16.attn_k.weight, torch.float32 --> TQ2_0, shape = {1536, 1536}
103
+ INFO:hf-to-gguf:blk.16.attn_output.weight, torch.float32 --> TQ2_0, shape = {1536, 1536}
104
+ INFO:hf-to-gguf:blk.16.attn_q.weight, torch.float32 --> TQ2_0, shape = {1536, 1536}
105
+ INFO:hf-to-gguf:blk.16.attn_v.weight, torch.float32 --> TQ2_0, shape = {1536, 1536}
106
+ INFO:hf-to-gguf:blk.17.attn_norm.weight, torch.float32 --> F32, shape = {1536}
107
+ INFO:hf-to-gguf:blk.17.ffn_down.weight, torch.float32 --> TQ2_0, shape = {4096, 1536}
108
+ INFO:hf-to-gguf:blk.17.ffn_sub_norm.weight, torch.float32 --> F32, shape = {4096}
109
+ INFO:hf-to-gguf:blk.17.ffn_gate.weight, torch.float32 --> TQ2_0, shape = {1536, 4096}
110
+ INFO:hf-to-gguf:blk.17.ffn_up.weight, torch.float32 --> TQ2_0, shape = {1536, 4096}
111
+ INFO:hf-to-gguf:blk.17.ffn_norm.weight, torch.float32 --> F32, shape = {1536}
112
+ INFO:hf-to-gguf:blk.17.attn_sub_norm.weight, torch.float32 --> F32, shape = {1536}
113
+ INFO:hf-to-gguf:blk.17.attn_k.weight, torch.float32 --> TQ2_0, shape = {1536, 1536}
114
+ INFO:hf-to-gguf:blk.17.attn_output.weight, torch.float32 --> TQ2_0, shape = {1536, 1536}
115
+ INFO:hf-to-gguf:blk.17.attn_q.weight, torch.float32 --> TQ2_0, shape = {1536, 1536}
116
+ INFO:hf-to-gguf:blk.17.attn_v.weight, torch.float32 --> TQ2_0, shape = {1536, 1536}
117
+ INFO:hf-to-gguf:blk.18.attn_norm.weight, torch.float32 --> F32, shape = {1536}
118
+ INFO:hf-to-gguf:blk.18.ffn_down.weight, torch.float32 --> TQ2_0, shape = {4096, 1536}
119
+ INFO:hf-to-gguf:blk.18.ffn_sub_norm.weight, torch.float32 --> F32, shape = {4096}
120
+ INFO:hf-to-gguf:blk.18.ffn_gate.weight, torch.float32 --> TQ2_0, shape = {1536, 4096}
121
+ INFO:hf-to-gguf:blk.18.ffn_up.weight, torch.float32 --> TQ2_0, shape = {1536, 4096}
122
+ INFO:hf-to-gguf:blk.18.ffn_norm.weight, torch.float32 --> F32, shape = {1536}
123
+ INFO:hf-to-gguf:blk.18.attn_sub_norm.weight, torch.float32 --> F32, shape = {1536}
124
+ INFO:hf-to-gguf:blk.18.attn_k.weight, torch.float32 --> TQ2_0, shape = {1536, 1536}
125
+ INFO:hf-to-gguf:blk.18.attn_output.weight, torch.float32 --> TQ2_0, shape = {1536, 1536}
126
+ INFO:hf-to-gguf:blk.18.attn_q.weight, torch.float32 --> TQ2_0, shape = {1536, 1536}
127
+ INFO:hf-to-gguf:blk.18.attn_v.weight, torch.float32 --> TQ2_0, shape = {1536, 1536}
128
+ INFO:hf-to-gguf:blk.19.attn_norm.weight, torch.float32 --> F32, shape = {1536}
129
+ INFO:hf-to-gguf:blk.19.ffn_down.weight, torch.float32 --> TQ2_0, shape = {4096, 1536}
130
+ INFO:hf-to-gguf:blk.19.ffn_sub_norm.weight, torch.float32 --> F32, shape = {4096}
131
+ INFO:hf-to-gguf:blk.19.ffn_gate.weight, torch.float32 --> TQ2_0, shape = {1536, 4096}
132
+ INFO:hf-to-gguf:blk.19.ffn_up.weight, torch.float32 --> TQ2_0, shape = {1536, 4096}
133
+ INFO:hf-to-gguf:blk.19.ffn_norm.weight, torch.float32 --> F32, shape = {1536}
134
+ INFO:hf-to-gguf:blk.19.attn_sub_norm.weight, torch.float32 --> F32, shape = {1536}
135
+ INFO:hf-to-gguf:blk.19.attn_k.weight, torch.float32 --> TQ2_0, shape = {1536, 1536}
136
+ INFO:hf-to-gguf:blk.19.attn_output.weight, torch.float32 --> TQ2_0, shape = {1536, 1536}
137
+ INFO:hf-to-gguf:blk.19.attn_q.weight, torch.float32 --> TQ2_0, shape = {1536, 1536}
138
+ INFO:hf-to-gguf:blk.19.attn_v.weight, torch.float32 --> TQ2_0, shape = {1536, 1536}
139
+ INFO:hf-to-gguf:blk.2.attn_norm.weight, torch.float32 --> F32, shape = {1536}
140
+ INFO:hf-to-gguf:blk.2.ffn_down.weight, torch.float32 --> TQ2_0, shape = {4096, 1536}
141
+ INFO:hf-to-gguf:blk.2.ffn_sub_norm.weight, torch.float32 --> F32, shape = {4096}
142
+ INFO:hf-to-gguf:blk.2.ffn_gate.weight, torch.float32 --> TQ2_0, shape = {1536, 4096}
143
+ INFO:hf-to-gguf:blk.2.ffn_up.weight, torch.float32 --> TQ2_0, shape = {1536, 4096}
144
+ INFO:hf-to-gguf:blk.2.ffn_norm.weight, torch.float32 --> F32, shape = {1536}
145
+ INFO:hf-to-gguf:blk.2.attn_sub_norm.weight, torch.float32 --> F32, shape = {1536}
146
+ INFO:hf-to-gguf:blk.2.attn_k.weight, torch.float32 --> TQ2_0, shape = {1536, 1536}
147
+ INFO:hf-to-gguf:blk.2.attn_output.weight, torch.float32 --> TQ2_0, shape = {1536, 1536}
148
+ INFO:hf-to-gguf:blk.2.attn_q.weight, torch.float32 --> TQ2_0, shape = {1536, 1536}
149
+ INFO:hf-to-gguf:blk.2.attn_v.weight, torch.float32 --> TQ2_0, shape = {1536, 1536}
150
+ INFO:hf-to-gguf:blk.20.attn_norm.weight, torch.float32 --> F32, shape = {1536}
151
+ INFO:hf-to-gguf:blk.20.ffn_down.weight, torch.float32 --> TQ2_0, shape = {4096, 1536}
152
+ INFO:hf-to-gguf:blk.20.ffn_sub_norm.weight, torch.float32 --> F32, shape = {4096}
153
+ INFO:hf-to-gguf:blk.20.ffn_gate.weight, torch.float32 --> TQ2_0, shape = {1536, 4096}
154
+ INFO:hf-to-gguf:blk.20.ffn_up.weight, torch.float32 --> TQ2_0, shape = {1536, 4096}
155
+ INFO:hf-to-gguf:blk.20.ffn_norm.weight, torch.float32 --> F32, shape = {1536}
156
+ INFO:hf-to-gguf:blk.20.attn_sub_norm.weight, torch.float32 --> F32, shape = {1536}
157
+ INFO:hf-to-gguf:blk.20.attn_k.weight, torch.float32 --> TQ2_0, shape = {1536, 1536}
158
+ INFO:hf-to-gguf:blk.20.attn_output.weight, torch.float32 --> TQ2_0, shape = {1536, 1536}
159
+ INFO:hf-to-gguf:blk.20.attn_q.weight, torch.float32 --> TQ2_0, shape = {1536, 1536}
160
+ INFO:hf-to-gguf:blk.20.attn_v.weight, torch.float32 --> TQ2_0, shape = {1536, 1536}
161
+ INFO:hf-to-gguf:blk.21.attn_norm.weight, torch.float32 --> F32, shape = {1536}
162
+ INFO:hf-to-gguf:blk.21.ffn_down.weight, torch.float32 --> TQ2_0, shape = {4096, 1536}
163
+ INFO:hf-to-gguf:blk.21.ffn_sub_norm.weight, torch.float32 --> F32, shape = {4096}
164
+ INFO:hf-to-gguf:blk.21.ffn_gate.weight, torch.float32 --> TQ2_0, shape = {1536, 4096}
165
+ INFO:hf-to-gguf:blk.21.ffn_up.weight, torch.float32 --> TQ2_0, shape = {1536, 4096}
166
+ INFO:hf-to-gguf:blk.21.ffn_norm.weight, torch.float32 --> F32, shape = {1536}
167
+ INFO:hf-to-gguf:blk.21.attn_sub_norm.weight, torch.float32 --> F32, shape = {1536}
168
+ INFO:hf-to-gguf:blk.21.attn_k.weight, torch.float32 --> TQ2_0, shape = {1536, 1536}
169
+ INFO:hf-to-gguf:blk.21.attn_output.weight, torch.float32 --> TQ2_0, shape = {1536, 1536}
170
+ INFO:hf-to-gguf:blk.21.attn_q.weight, torch.float32 --> TQ2_0, shape = {1536, 1536}
171
+ INFO:hf-to-gguf:blk.21.attn_v.weight, torch.float32 --> TQ2_0, shape = {1536, 1536}
172
+ INFO:hf-to-gguf:blk.22.attn_norm.weight, torch.float32 --> F32, shape = {1536}
173
+ INFO:hf-to-gguf:blk.22.ffn_down.weight, torch.float32 --> TQ2_0, shape = {4096, 1536}
174
+ INFO:hf-to-gguf:blk.22.ffn_sub_norm.weight, torch.float32 --> F32, shape = {4096}
175
+ INFO:hf-to-gguf:blk.22.ffn_gate.weight, torch.float32 --> TQ2_0, shape = {1536, 4096}
176
+ INFO:hf-to-gguf:blk.22.ffn_up.weight, torch.float32 --> TQ2_0, shape = {1536, 4096}
177
+ INFO:hf-to-gguf:blk.22.ffn_norm.weight, torch.float32 --> F32, shape = {1536}
178
+ INFO:hf-to-gguf:blk.22.attn_sub_norm.weight, torch.float32 --> F32, shape = {1536}
179
+ INFO:hf-to-gguf:blk.22.attn_k.weight, torch.float32 --> TQ2_0, shape = {1536, 1536}
180
+ INFO:hf-to-gguf:blk.22.attn_output.weight, torch.float32 --> TQ2_0, shape = {1536, 1536}
181
+ INFO:hf-to-gguf:blk.22.attn_q.weight, torch.float32 --> TQ2_0, shape = {1536, 1536}
182
+ INFO:hf-to-gguf:blk.22.attn_v.weight, torch.float32 --> TQ2_0, shape = {1536, 1536}
183
+ INFO:hf-to-gguf:blk.23.attn_norm.weight, torch.float32 --> F32, shape = {1536}
184
+ INFO:hf-to-gguf:blk.23.ffn_down.weight, torch.float32 --> TQ2_0, shape = {4096, 1536}
185
+ INFO:hf-to-gguf:blk.23.ffn_sub_norm.weight, torch.float32 --> F32, shape = {4096}
186
+ INFO:hf-to-gguf:blk.23.ffn_gate.weight, torch.float32 --> TQ2_0, shape = {1536, 4096}
187
+ INFO:hf-to-gguf:blk.23.ffn_up.weight, torch.float32 --> TQ2_0, shape = {1536, 4096}
188
+ INFO:hf-to-gguf:blk.23.ffn_norm.weight, torch.float32 --> F32, shape = {1536}
189
+ INFO:hf-to-gguf:blk.23.attn_sub_norm.weight, torch.float32 --> F32, shape = {1536}
190
+ INFO:hf-to-gguf:blk.23.attn_k.weight, torch.float32 --> TQ2_0, shape = {1536, 1536}
191
+ INFO:hf-to-gguf:blk.23.attn_output.weight, torch.float32 --> TQ2_0, shape = {1536, 1536}
192
+ INFO:hf-to-gguf:blk.23.attn_q.weight, torch.float32 --> TQ2_0, shape = {1536, 1536}
193
+ INFO:hf-to-gguf:blk.23.attn_v.weight, torch.float32 --> TQ2_0, shape = {1536, 1536}
194
+ INFO:hf-to-gguf:blk.3.attn_norm.weight, torch.float32 --> F32, shape = {1536}
195
+ INFO:hf-to-gguf:blk.3.ffn_down.weight, torch.float32 --> TQ2_0, shape = {4096, 1536}
196
+ INFO:hf-to-gguf:blk.3.ffn_sub_norm.weight, torch.float32 --> F32, shape = {4096}
197
+ INFO:hf-to-gguf:blk.3.ffn_gate.weight, torch.float32 --> TQ2_0, shape = {1536, 4096}
198
+ INFO:hf-to-gguf:blk.3.ffn_up.weight, torch.float32 --> TQ2_0, shape = {1536, 4096}
199
+ INFO:hf-to-gguf:blk.3.ffn_norm.weight, torch.float32 --> F32, shape = {1536}
200
+ INFO:hf-to-gguf:blk.3.attn_sub_norm.weight, torch.float32 --> F32, shape = {1536}
201
+ INFO:hf-to-gguf:blk.3.attn_k.weight, torch.float32 --> TQ2_0, shape = {1536, 1536}
202
+ INFO:hf-to-gguf:blk.3.attn_output.weight, torch.float32 --> TQ2_0, shape = {1536, 1536}
203
+ INFO:hf-to-gguf:blk.3.attn_q.weight, torch.float32 --> TQ2_0, shape = {1536, 1536}
204
+ INFO:hf-to-gguf:blk.3.attn_v.weight, torch.float32 --> TQ2_0, shape = {1536, 1536}
205
+ INFO:hf-to-gguf:blk.4.attn_norm.weight, torch.float32 --> F32, shape = {1536}
206
+ INFO:hf-to-gguf:blk.4.ffn_down.weight, torch.float32 --> TQ2_0, shape = {4096, 1536}
207
+ INFO:hf-to-gguf:blk.4.ffn_sub_norm.weight, torch.float32 --> F32, shape = {4096}
208
+ INFO:hf-to-gguf:blk.4.ffn_gate.weight, torch.float32 --> TQ2_0, shape = {1536, 4096}
209
+ INFO:hf-to-gguf:blk.4.ffn_up.weight, torch.float32 --> TQ2_0, shape = {1536, 4096}
210
+ INFO:hf-to-gguf:blk.4.ffn_norm.weight, torch.float32 --> F32, shape = {1536}
211
+ INFO:hf-to-gguf:blk.4.attn_sub_norm.weight, torch.float32 --> F32, shape = {1536}
212
+ INFO:hf-to-gguf:blk.4.attn_k.weight, torch.float32 --> TQ2_0, shape = {1536, 1536}
213
+ INFO:hf-to-gguf:blk.4.attn_output.weight, torch.float32 --> TQ2_0, shape = {1536, 1536}
214
+ INFO:hf-to-gguf:blk.4.attn_q.weight, torch.float32 --> TQ2_0, shape = {1536, 1536}
215
+ INFO:hf-to-gguf:blk.4.attn_v.weight, torch.float32 --> TQ2_0, shape = {1536, 1536}
216
+ INFO:hf-to-gguf:blk.5.attn_norm.weight, torch.float32 --> F32, shape = {1536}
217
+ INFO:hf-to-gguf:blk.5.ffn_down.weight, torch.float32 --> TQ2_0, shape = {4096, 1536}
218
+ INFO:hf-to-gguf:blk.5.ffn_sub_norm.weight, torch.float32 --> F32, shape = {4096}
219
+ INFO:hf-to-gguf:blk.5.ffn_gate.weight, torch.float32 --> TQ2_0, shape = {1536, 4096}
220
+ INFO:hf-to-gguf:blk.5.ffn_up.weight, torch.float32 --> TQ2_0, shape = {1536, 4096}
221
+ INFO:hf-to-gguf:blk.5.ffn_norm.weight, torch.float32 --> F32, shape = {1536}
222
+ INFO:hf-to-gguf:blk.5.attn_sub_norm.weight, torch.float32 --> F32, shape = {1536}
223
+ INFO:hf-to-gguf:blk.5.attn_k.weight, torch.float32 --> TQ2_0, shape = {1536, 1536}
224
+ INFO:hf-to-gguf:blk.5.attn_output.weight, torch.float32 --> TQ2_0, shape = {1536, 1536}
225
+ INFO:hf-to-gguf:blk.5.attn_q.weight, torch.float32 --> TQ2_0, shape = {1536, 1536}
226
+ INFO:hf-to-gguf:blk.5.attn_v.weight, torch.float32 --> TQ2_0, shape = {1536, 1536}
227
+ INFO:hf-to-gguf:blk.6.attn_norm.weight, torch.float32 --> F32, shape = {1536}
228
+ INFO:hf-to-gguf:blk.6.ffn_down.weight, torch.float32 --> TQ2_0, shape = {4096, 1536}
229
+ INFO:hf-to-gguf:blk.6.ffn_sub_norm.weight, torch.float32 --> F32, shape = {4096}
230
+ INFO:hf-to-gguf:blk.6.ffn_gate.weight, torch.float32 --> TQ2_0, shape = {1536, 4096}
231
+ INFO:hf-to-gguf:blk.6.ffn_up.weight, torch.float32 --> TQ2_0, shape = {1536, 4096}
232
+ INFO:hf-to-gguf:blk.6.ffn_norm.weight, torch.float32 --> F32, shape = {1536}
233
+ INFO:hf-to-gguf:blk.6.attn_sub_norm.weight, torch.float32 --> F32, shape = {1536}
234
+ INFO:hf-to-gguf:blk.6.attn_k.weight, torch.float32 --> TQ2_0, shape = {1536, 1536}
235
+ INFO:hf-to-gguf:blk.6.attn_output.weight, torch.float32 --> TQ2_0, shape = {1536, 1536}
236
+ INFO:hf-to-gguf:blk.6.attn_q.weight, torch.float32 --> TQ2_0, shape = {1536, 1536}
237
+ INFO:hf-to-gguf:blk.6.attn_v.weight, torch.float32 --> TQ2_0, shape = {1536, 1536}
238
+ INFO:hf-to-gguf:blk.7.attn_norm.weight, torch.float32 --> F32, shape = {1536}
239
+ INFO:hf-to-gguf:blk.7.ffn_down.weight, torch.float32 --> TQ2_0, shape = {4096, 1536}
240
+ INFO:hf-to-gguf:blk.7.ffn_sub_norm.weight, torch.float32 --> F32, shape = {4096}
241
+ INFO:hf-to-gguf:blk.7.ffn_gate.weight, torch.float32 --> TQ2_0, shape = {1536, 4096}
242
+ INFO:hf-to-gguf:blk.7.ffn_up.weight, torch.float32 --> TQ2_0, shape = {1536, 4096}
243
+ INFO:hf-to-gguf:blk.7.ffn_norm.weight, torch.float32 --> F32, shape = {1536}
244
+ INFO:hf-to-gguf:blk.7.attn_sub_norm.weight, torch.float32 --> F32, shape = {1536}
245
+ INFO:hf-to-gguf:blk.7.attn_k.weight, torch.float32 --> TQ2_0, shape = {1536, 1536}
246
+ INFO:hf-to-gguf:blk.7.attn_output.weight, torch.float32 --> TQ2_0, shape = {1536, 1536}
247
+ INFO:hf-to-gguf:blk.7.attn_q.weight, torch.float32 --> TQ2_0, shape = {1536, 1536}
248
+ INFO:hf-to-gguf:blk.7.attn_v.weight, torch.float32 --> TQ2_0, shape = {1536, 1536}
249
+ INFO:hf-to-gguf:blk.8.attn_norm.weight, torch.float32 --> F32, shape = {1536}
250
+ INFO:hf-to-gguf:blk.8.ffn_down.weight, torch.float32 --> TQ2_0, shape = {4096, 1536}
251
+ INFO:hf-to-gguf:blk.8.ffn_sub_norm.weight, torch.float32 --> F32, shape = {4096}
252
+ INFO:hf-to-gguf:blk.8.ffn_gate.weight, torch.float32 --> TQ2_0, shape = {1536, 4096}
253
+ INFO:hf-to-gguf:blk.8.ffn_up.weight, torch.float32 --> TQ2_0, shape = {1536, 4096}
254
+ INFO:hf-to-gguf:blk.8.ffn_norm.weight, torch.float32 --> F32, shape = {1536}
255
+ INFO:hf-to-gguf:blk.8.attn_sub_norm.weight, torch.float32 --> F32, shape = {1536}
256
+ INFO:hf-to-gguf:blk.8.attn_k.weight, torch.float32 --> TQ2_0, shape = {1536, 1536}
257
+ INFO:hf-to-gguf:blk.8.attn_output.weight, torch.float32 --> TQ2_0, shape = {1536, 1536}
258
+ INFO:hf-to-gguf:blk.8.attn_q.weight, torch.float32 --> TQ2_0, shape = {1536, 1536}
259
+ INFO:hf-to-gguf:blk.8.attn_v.weight, torch.float32 --> TQ2_0, shape = {1536, 1536}
260
+ INFO:hf-to-gguf:blk.9.attn_norm.weight, torch.float32 --> F32, shape = {1536}
261
+ INFO:hf-to-gguf:blk.9.ffn_down.weight, torch.float32 --> TQ2_0, shape = {4096, 1536}
262
+ INFO:hf-to-gguf:blk.9.ffn_sub_norm.weight, torch.float32 --> F32, shape = {4096}
263
+ INFO:hf-to-gguf:blk.9.ffn_gate.weight, torch.float32 --> TQ2_0, shape = {1536, 4096}
264
+ INFO:hf-to-gguf:blk.9.ffn_up.weight, torch.float32 --> TQ2_0, shape = {1536, 4096}
265
+ INFO:hf-to-gguf:blk.9.ffn_norm.weight, torch.float32 --> F32, shape = {1536}
266
+ INFO:hf-to-gguf:blk.9.attn_sub_norm.weight, torch.float32 --> F32, shape = {1536}
267
+ INFO:hf-to-gguf:blk.9.attn_k.weight, torch.float32 --> TQ2_0, shape = {1536, 1536}
268
+ INFO:hf-to-gguf:blk.9.attn_output.weight, torch.float32 --> TQ2_0, shape = {1536, 1536}
269
+ INFO:hf-to-gguf:blk.9.attn_q.weight, torch.float32 --> TQ2_0, shape = {1536, 1536}
270
+ INFO:hf-to-gguf:blk.9.attn_v.weight, torch.float32 --> TQ2_0, shape = {1536, 1536}
271
+ INFO:hf-to-gguf:output_norm.weight, torch.float32 --> F32, shape = {1536}
272
+ INFO:hf-to-gguf:Set meta model
273
+ INFO:hf-to-gguf:Set model parameters
274
+ INFO:hf-to-gguf:gguf: context length = 2048
275
+ INFO:hf-to-gguf:gguf: embedding length = 1536
276
+ INFO:hf-to-gguf:gguf: feed forward length = 4096
277
+ INFO:hf-to-gguf:gguf: head count = 16
278
+ INFO:hf-to-gguf:gguf: key-value head count = 16
279
+ INFO:hf-to-gguf:gguf: rope theta = 10000.0
280
+ INFO:hf-to-gguf:gguf: rms norm epsilon = 1e-05
281
+ INFO:hf-to-gguf:gguf: file type = 37
282
+ INFO:hf-to-gguf:Set model tokenizer
283
+ INFO:gguf.vocab:Setting special token type bos to 1
284
+ INFO:gguf.vocab:Setting special token type eos to 2
285
+ INFO:gguf.vocab:Setting special token type pad to 32000
286
+ INFO:gguf.vocab:Setting add_bos_token to True
287
+ INFO:gguf.vocab:Setting add_eos_token to False
288
+ INFO:hf-to-gguf:Set model quantization version
289
+ INFO:gguf.gguf_writer:Writing the following files:
290
+ INFO:gguf.gguf_writer:/home/user/Storage/1bitLLM_bitnet_b1_58-large-instruct-v2/bitnet_b1_58-large-1bitLLM_bitnet_b1_58-instruct-v2-TQ2_0.gguf: n_tensors = 266, total_size = 274.3M
291
+ Writing: 100%|β–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆοΏ½οΏ½β–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆ| 274M/274M [00:04<00:00, 57.7Mbyte/s]
292
+ INFO:hf-to-gguf:Model successfully exported to /home/user/Storage/1bitLLM_bitnet_b1_58-large-instruct-v2/bitnet_b1_58-large-1bitLLM_bitnet_b1_58-instruct-v2-TQ2_0.gguf