Upload 4 files
Browse files
.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%|βββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββοΏ½οΏ½βββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββ| 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%|βββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββοΏ½οΏ½βββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββ| 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
|