Text Generation
GGUF
English
quant
experimental
imatrix
conversational
Qwen3-30B-A3B-GGUF / scores /Qwen3-30B-A3B-IQ3_M.md
eaddario's picture
Add GGUF internal file structure
a630e18 verified
|
raw
history blame
189 kB

Qwen3-30B-A3B-IQ3_M.gguf - GGUF Internal File Dump

  • Endian: LITTLE endian

Key Value Metadata Store

There are 44 key-value pairs in this file

POS TYPE Count Key Value
1 UINT32 1 GGUF.version 3
2 UINT64 1 GGUF.tensor_count 579
3 UINT64 1 GGUF.kv_count 41
4 STRING 1 general.architecture qwen3moe
5 STRING 1 general.type model
6 STRING 1 general.name Qwen3 30B A3B
7 STRING 1 general.basename Qwen3
8 STRING 1 general.size_label 30B-A3B
9 STRING 1 general.license apache-2.0
10 STRING 1 general.license.link https://huggingface.co/Qwen/Qwen3-30B-A3B/blob/main/LICENSE
11 UINT32 1 general.base_model.count 1
12 STRING 1 general.base_model.0.name Qwen3 30B A3B Base
13 STRING 1 general.base_model.0.organization Qwen
14 STRING 1 general.base_model.0.repo_url https://huggingface.co/Qwen/Qwen3-30B-A3B-Base
15 [STRING] 1 general.tags [ text-generation ]
16 UINT32 1 qwen3moe.block_count 48
17 UINT32 1 qwen3moe.context_length 40960
18 UINT32 1 qwen3moe.embedding_length 2048
19 UINT32 1 qwen3moe.feed_forward_length 6144
20 UINT32 1 qwen3moe.attention.head_count 32
21 UINT32 1 qwen3moe.attention.head_count_kv 4
22 FLOAT32 1 qwen3moe.rope.freq_base 1000000.0
23 FLOAT32 1 qwen3moe.attention.layer_norm_rms_epsilon 1e-06
24 UINT32 1 qwen3moe.expert_used_count 8
25 UINT32 1 qwen3moe.attention.key_length 128
26 UINT32 1 qwen3moe.attention.value_length 128
27 UINT32 1 qwen3moe.expert_count 128
28 UINT32 1 qwen3moe.expert_feed_forward_length 768
29 STRING 1 tokenizer.ggml.model gpt2
30 STRING 1 tokenizer.ggml.pre qwen2
31 [STRING] 151936 tokenizer.ggml.tokens [ !, ", #, $, %, ... ]
32 [INT32] 151936 tokenizer.ggml.token_type [ 1, 1, 1, 1, 1, 1, 1, ... ]
33 [STRING] 151387 tokenizer.ggml.merges [ Ġ Ġ, ĠĠ ĠĠ, i n, Ġ t, ĠĠĠĠ ĠĠĠĠ, ... ]
34 UINT32 1 tokenizer.ggml.eos_token_id 151645
35 UINT32 1 tokenizer.ggml.padding_token_id 151643
36 UINT32 1 tokenizer.ggml.bos_token_id 151643
37 BOOL 1 tokenizer.ggml.add_bos_token False
38 STRING 1 tokenizer.chat_template `{%- if tools %}{{- '<
39 UINT32 1 general.quantization_version 2
40 UINT32 1 general.file_type 27
41 STRING 1 quantize.imatrix.file ./imatrix/imatrix-Qwen3-30B-A3B-large.dat
42 STRING 1 quantize.imatrix.dataset ../../datasets/imatrix/calibration_all_large.txt
43 INT32 1 quantize.imatrix.entries_count 382
44 INT32 1 quantize.imatrix.chunks_count 4978

Tensors Overview ~31B Elements

Total number of elements in all tensors: 30532122624 Elements

Tensor Data Offset

This table contains the offset and data segment relative to start of file

T_ID Tensor Layer Name Data Offset (B) Data Size (B)
0 output.weight 0x5b18c0 0x7f82800
1 output_norm.weight 0x85340c0 0x2000
2 token_embd.weight 0x85360c0 0x7f82800
3 blk.0.attn_k.weight 0x104b88c0 0x62000
4 blk.0.attn_k_norm.weight 0x1051a8c0 0x200
5 blk.0.attn_norm.weight 0x1051aac0 0x2000
6 blk.0.attn_output.weight 0x1051cac0 0x480000
7 blk.0.attn_q.weight 0x1099cac0 0x310000
8 blk.0.attn_q_norm.weight 0x10cacac0 0x200
9 blk.0.attn_v.weight 0x10caccc0 0x6e000
10 blk.0.ffn_down_exps.weight 0x10d1acc0 0x6c00000
11 blk.0.ffn_gate_exps.weight 0x1791acc0 0x4980000
12 blk.0.ffn_gate_inp.weight 0x1c29acc0 0x100000
13 blk.0.ffn_norm.weight 0x1c39acc0 0x2000
14 blk.0.ffn_up_exps.weight 0x1c39ccc0 0x4980000
15 blk.1.attn_k.weight 0x20d1ccc0 0x62000
16 blk.1.attn_k_norm.weight 0x20d7ecc0 0x200
17 blk.1.attn_norm.weight 0x20d7eec0 0x2000
18 blk.1.attn_output.weight 0x20d80ec0 0x480000
19 blk.1.attn_q.weight 0x21200ec0 0x310000
20 blk.1.attn_q_norm.weight 0x21510ec0 0x200
21 blk.1.attn_v.weight 0x215110c0 0x6e000
22 blk.1.ffn_down_exps.weight 0x2157f0c0 0x6c00000
23 blk.1.ffn_gate_exps.weight 0x2817f0c0 0x4980000
24 blk.1.ffn_gate_inp.weight 0x2caff0c0 0x100000
25 blk.1.ffn_norm.weight 0x2cbff0c0 0x2000
26 blk.1.ffn_up_exps.weight 0x2cc010c0 0x4980000
27 blk.2.attn_k.weight 0x315810c0 0x62000
28 blk.2.attn_k_norm.weight 0x315e30c0 0x200
29 blk.2.attn_norm.weight 0x315e32c0 0x2000
30 blk.2.attn_output.weight 0x315e52c0 0x480000
31 blk.2.attn_q.weight 0x31a652c0 0x310000
32 blk.2.attn_q_norm.weight 0x31d752c0 0x200
33 blk.2.attn_v.weight 0x31d754c0 0x6e000
34 blk.2.ffn_down_exps.weight 0x31de34c0 0x6c00000
35 blk.2.ffn_gate_exps.weight 0x389e34c0 0x4980000
36 blk.2.ffn_gate_inp.weight 0x3d3634c0 0x100000
37 blk.2.ffn_norm.weight 0x3d4634c0 0x2000
38 blk.2.ffn_up_exps.weight 0x3d4654c0 0x4980000
39 blk.3.attn_k.weight 0x41de54c0 0x62000
40 blk.3.attn_k_norm.weight 0x41e474c0 0x200
41 blk.3.attn_norm.weight 0x41e476c0 0x2000
42 blk.3.attn_output.weight 0x41e496c0 0x480000
43 blk.3.attn_q.weight 0x422c96c0 0x310000
44 blk.3.attn_q_norm.weight 0x425d96c0 0x200
45 blk.3.attn_v.weight 0x425d98c0 0x6e000
46 blk.3.ffn_down_exps.weight 0x426478c0 0x6c00000
47 blk.3.ffn_gate_exps.weight 0x492478c0 0x4980000
48 blk.3.ffn_gate_inp.weight 0x4dbc78c0 0x100000
49 blk.3.ffn_norm.weight 0x4dcc78c0 0x2000
50 blk.3.ffn_up_exps.weight 0x4dcc98c0 0x4980000
51 blk.4.attn_k.weight 0x526498c0 0x62000
52 blk.4.attn_k_norm.weight 0x526ab8c0 0x200
53 blk.4.attn_norm.weight 0x526abac0 0x2000
54 blk.4.attn_output.weight 0x526adac0 0x480000
55 blk.4.attn_q.weight 0x52b2dac0 0x310000
56 blk.4.attn_q_norm.weight 0x52e3dac0 0x200
57 blk.4.attn_v.weight 0x52e3dcc0 0x6e000
58 blk.4.ffn_down_exps.weight 0x52eabcc0 0x6c00000
59 blk.4.ffn_gate_exps.weight 0x59aabcc0 0x4980000
60 blk.4.ffn_gate_inp.weight 0x5e42bcc0 0x100000
61 blk.4.ffn_norm.weight 0x5e52bcc0 0x2000
62 blk.4.ffn_up_exps.weight 0x5e52dcc0 0x4980000
63 blk.5.attn_k.weight 0x62eadcc0 0x62000
64 blk.5.attn_k_norm.weight 0x62f0fcc0 0x200
65 blk.5.attn_norm.weight 0x62f0fec0 0x2000
66 blk.5.attn_output.weight 0x62f11ec0 0x480000
67 blk.5.attn_q.weight 0x63391ec0 0x310000
68 blk.5.attn_q_norm.weight 0x636a1ec0 0x200
69 blk.5.attn_v.weight 0x636a20c0 0x6e000
70 blk.5.ffn_down_exps.weight 0x637100c0 0x6c00000
71 blk.5.ffn_gate_exps.weight 0x6a3100c0 0x4980000
72 blk.5.ffn_gate_inp.weight 0x6ec900c0 0x100000
73 blk.5.ffn_norm.weight 0x6ed900c0 0x2000
74 blk.5.ffn_up_exps.weight 0x6ed920c0 0x4980000
75 blk.6.attn_k.weight 0x737120c0 0x62000
76 blk.6.attn_k_norm.weight 0x737740c0 0x200
77 blk.6.attn_norm.weight 0x737742c0 0x2000
78 blk.6.attn_output.weight 0x737762c0 0x480000
79 blk.6.attn_q.weight 0x73bf62c0 0x310000
80 blk.6.attn_q_norm.weight 0x73f062c0 0x200
81 blk.6.attn_v.weight 0x73f064c0 0x6e000
82 blk.6.ffn_down_exps.weight 0x73f744c0 0x6c00000
83 blk.6.ffn_gate_exps.weight 0x7ab744c0 0x4980000
84 blk.6.ffn_gate_inp.weight 0x7f4f44c0 0x100000
85 blk.6.ffn_norm.weight 0x7f5f44c0 0x2000
86 blk.6.ffn_up_exps.weight 0x7f5f64c0 0x4980000
87 blk.7.attn_k.weight 0x83f764c0 0x62000
88 blk.7.attn_k_norm.weight 0x83fd84c0 0x200
89 blk.7.attn_norm.weight 0x83fd86c0 0x2000
90 blk.7.attn_output.weight 0x83fda6c0 0x480000
91 blk.7.attn_q.weight 0x8445a6c0 0x310000
92 blk.7.attn_q_norm.weight 0x8476a6c0 0x200
93 blk.7.attn_v.weight 0x8476a8c0 0x6e000
94 blk.7.ffn_down_exps.weight 0x847d88c0 0x6c00000
95 blk.7.ffn_gate_exps.weight 0x8b3d88c0 0x4980000
96 blk.7.ffn_gate_inp.weight 0x8fd588c0 0x100000
97 blk.7.ffn_norm.weight 0x8fe588c0 0x2000
98 blk.7.ffn_up_exps.weight 0x8fe5a8c0 0x4980000
99 blk.8.attn_k.weight 0x947da8c0 0x62000
100 blk.8.attn_k_norm.weight 0x9483c8c0 0x200
101 blk.8.attn_norm.weight 0x9483cac0 0x2000
102 blk.8.attn_output.weight 0x9483eac0 0x480000
103 blk.8.attn_q.weight 0x94cbeac0 0x310000
104 blk.8.attn_q_norm.weight 0x94fceac0 0x200
105 blk.8.attn_v.weight 0x94fcecc0 0x6e000
106 blk.8.ffn_down_exps.weight 0x9503ccc0 0x6c00000
107 blk.8.ffn_gate_exps.weight 0x9bc3ccc0 0x4980000
108 blk.8.ffn_gate_inp.weight 0xa05bccc0 0x100000
109 blk.8.ffn_norm.weight 0xa06bccc0 0x2000
110 blk.8.ffn_up_exps.weight 0xa06becc0 0x4980000
111 blk.9.attn_k.weight 0xa503ecc0 0x62000
112 blk.9.attn_k_norm.weight 0xa50a0cc0 0x200
113 blk.9.attn_norm.weight 0xa50a0ec0 0x2000
114 blk.9.attn_output.weight 0xa50a2ec0 0x480000
115 blk.9.attn_q.weight 0xa5522ec0 0x310000
116 blk.9.attn_q_norm.weight 0xa5832ec0 0x200
117 blk.9.attn_v.weight 0xa58330c0 0x6e000
118 blk.9.ffn_down_exps.weight 0xa58a10c0 0x6c00000
119 blk.9.ffn_gate_exps.weight 0xac4a10c0 0x4980000
120 blk.9.ffn_gate_inp.weight 0xb0e210c0 0x100000
121 blk.9.ffn_norm.weight 0xb0f210c0 0x2000
122 blk.9.ffn_up_exps.weight 0xb0f230c0 0x4980000
123 blk.10.attn_k.weight 0xb58a30c0 0x62000
124 blk.10.attn_k_norm.weight 0xb59050c0 0x200
125 blk.10.attn_norm.weight 0xb59052c0 0x2000
126 blk.10.attn_output.weight 0xb59072c0 0x480000
127 blk.10.attn_q.weight 0xb5d872c0 0x310000
128 blk.10.attn_q_norm.weight 0xb60972c0 0x200
129 blk.10.attn_v.weight 0xb60974c0 0x6e000
130 blk.10.ffn_down_exps.weight 0xb61054c0 0x6c00000
131 blk.10.ffn_gate_exps.weight 0xbcd054c0 0x4980000
132 blk.10.ffn_gate_inp.weight 0xc16854c0 0x100000
133 blk.10.ffn_norm.weight 0xc17854c0 0x2000
134 blk.10.ffn_up_exps.weight 0xc17874c0 0x4980000
135 blk.11.attn_k.weight 0xc61074c0 0x62000
136 blk.11.attn_k_norm.weight 0xc61694c0 0x200
137 blk.11.attn_norm.weight 0xc61696c0 0x2000
138 blk.11.attn_output.weight 0xc616b6c0 0x480000
139 blk.11.attn_q.weight 0xc65eb6c0 0x310000
140 blk.11.attn_q_norm.weight 0xc68fb6c0 0x200
141 blk.11.attn_v.weight 0xc68fb8c0 0x6e000
142 blk.11.ffn_down_exps.weight 0xc69698c0 0x6c00000
143 blk.11.ffn_gate_exps.weight 0xcd5698c0 0x4980000
144 blk.11.ffn_gate_inp.weight 0xd1ee98c0 0x100000
145 blk.11.ffn_norm.weight 0xd1fe98c0 0x2000
146 blk.11.ffn_up_exps.weight 0xd1feb8c0 0x4980000
147 blk.12.attn_k.weight 0xd696b8c0 0x62000
148 blk.12.attn_k_norm.weight 0xd69cd8c0 0x200
149 blk.12.attn_norm.weight 0xd69cdac0 0x2000
150 blk.12.attn_output.weight 0xd69cfac0 0x480000
151 blk.12.attn_q.weight 0xd6e4fac0 0x310000
152 blk.12.attn_q_norm.weight 0xd715fac0 0x200
153 blk.12.attn_v.weight 0xd715fcc0 0x6e000
154 blk.12.ffn_down_exps.weight 0xd71cdcc0 0x6c00000
155 blk.12.ffn_gate_exps.weight 0xdddcdcc0 0x4980000
156 blk.12.ffn_gate_inp.weight 0xe274dcc0 0x100000
157 blk.12.ffn_norm.weight 0xe284dcc0 0x2000
158 blk.12.ffn_up_exps.weight 0xe284fcc0 0x4980000
159 blk.13.attn_k.weight 0xe71cfcc0 0x62000
160 blk.13.attn_k_norm.weight 0xe7231cc0 0x200
161 blk.13.attn_norm.weight 0xe7231ec0 0x2000
162 blk.13.attn_output.weight 0xe7233ec0 0x480000
163 blk.13.attn_q.weight 0xe76b3ec0 0x310000
164 blk.13.attn_q_norm.weight 0xe79c3ec0 0x200
165 blk.13.attn_v.weight 0xe79c40c0 0x6e000
166 blk.13.ffn_down_exps.weight 0xe7a320c0 0x6c00000
167 blk.13.ffn_gate_exps.weight 0xee6320c0 0x5280000
168 blk.13.ffn_gate_inp.weight 0xf38b20c0 0x100000
169 blk.13.ffn_norm.weight 0xf39b20c0 0x2000
170 blk.13.ffn_up_exps.weight 0xf39b40c0 0x5280000
171 blk.14.attn_k.weight 0xf8c340c0 0x62000
172 blk.14.attn_k_norm.weight 0xf8c960c0 0x200
173 blk.14.attn_norm.weight 0xf8c962c0 0x2000
174 blk.14.attn_output.weight 0xf8c982c0 0x480000
175 blk.14.attn_q.weight 0xf91182c0 0x310000
176 blk.14.attn_q_norm.weight 0xf94282c0 0x200
177 blk.14.attn_v.weight 0xf94284c0 0x6e000
178 blk.14.ffn_down_exps.weight 0xf94964c0 0x6c00000
179 blk.14.ffn_gate_exps.weight 0x1000964c0 0x4980000
180 blk.14.ffn_gate_inp.weight 0x104a164c0 0x100000
181 blk.14.ffn_norm.weight 0x104b164c0 0x2000
182 blk.14.ffn_up_exps.weight 0x104b184c0 0x4980000
183 blk.15.attn_k.weight 0x1094984c0 0x62000
184 blk.15.attn_k_norm.weight 0x1094fa4c0 0x200
185 blk.15.attn_norm.weight 0x1094fa6c0 0x2000
186 blk.15.attn_output.weight 0x1094fc6c0 0x480000
187 blk.15.attn_q.weight 0x10997c6c0 0x310000
188 blk.15.attn_q_norm.weight 0x109c8c6c0 0x200
189 blk.15.attn_v.weight 0x109c8c8c0 0x6e000
190 blk.15.ffn_down_exps.weight 0x109cfa8c0 0x6c00000
191 blk.15.ffn_gate_exps.weight 0x1108fa8c0 0x5280000
192 blk.15.ffn_gate_inp.weight 0x115b7a8c0 0x100000
193 blk.15.ffn_norm.weight 0x115c7a8c0 0x2000
194 blk.15.ffn_up_exps.weight 0x115c7c8c0 0x5280000
195 blk.16.attn_k.weight 0x11aefc8c0 0x62000
196 blk.16.attn_k_norm.weight 0x11af5e8c0 0x200
197 blk.16.attn_norm.weight 0x11af5eac0 0x2000
198 blk.16.attn_output.weight 0x11af60ac0 0x480000
199 blk.16.attn_q.weight 0x11b3e0ac0 0x310000
200 blk.16.attn_q_norm.weight 0x11b6f0ac0 0x200
201 blk.16.attn_v.weight 0x11b6f0cc0 0x6e000
202 blk.16.ffn_down_exps.weight 0x11b75ecc0 0x6c00000
203 blk.16.ffn_gate_exps.weight 0x12235ecc0 0x4980000
204 blk.16.ffn_gate_inp.weight 0x126cdecc0 0x100000
205 blk.16.ffn_norm.weight 0x126ddecc0 0x2000
206 blk.16.ffn_up_exps.weight 0x126de0cc0 0x4980000
207 blk.17.attn_k.weight 0x12b760cc0 0x62000
208 blk.17.attn_k_norm.weight 0x12b7c2cc0 0x200
209 blk.17.attn_norm.weight 0x12b7c2ec0 0x2000
210 blk.17.attn_output.weight 0x12b7c4ec0 0x480000
211 blk.17.attn_q.weight 0x12bc44ec0 0x310000
212 blk.17.attn_q_norm.weight 0x12bf54ec0 0x200
213 blk.17.attn_v.weight 0x12bf550c0 0x6e000
214 blk.17.ffn_down_exps.weight 0x12bfc30c0 0x6c00000
215 blk.17.ffn_gate_exps.weight 0x132bc30c0 0x4980000
216 blk.17.ffn_gate_inp.weight 0x1375430c0 0x100000
217 blk.17.ffn_norm.weight 0x1376430c0 0x2000
218 blk.17.ffn_up_exps.weight 0x1376450c0 0x4980000
219 blk.18.attn_k.weight 0x13bfc50c0 0x62000
220 blk.18.attn_k_norm.weight 0x13c0270c0 0x200
221 blk.18.attn_norm.weight 0x13c0272c0 0x2000
222 blk.18.attn_output.weight 0x13c0292c0 0x480000
223 blk.18.attn_q.weight 0x13c4a92c0 0x310000
224 blk.18.attn_q_norm.weight 0x13c7b92c0 0x200
225 blk.18.attn_v.weight 0x13c7b94c0 0x6e000
226 blk.18.ffn_down_exps.weight 0x13c8274c0 0x6c00000
227 blk.18.ffn_gate_exps.weight 0x1434274c0 0x4980000
228 blk.18.ffn_gate_inp.weight 0x147da74c0 0x100000
229 blk.18.ffn_norm.weight 0x147ea74c0 0x2000
230 blk.18.ffn_up_exps.weight 0x147ea94c0 0x4980000
231 blk.19.attn_k.weight 0x14c8294c0 0x62000
232 blk.19.attn_k_norm.weight 0x14c88b4c0 0x200
233 blk.19.attn_norm.weight 0x14c88b6c0 0x2000
234 blk.19.attn_output.weight 0x14c88d6c0 0x480000
235 blk.19.attn_q.weight 0x14cd0d6c0 0x310000
236 blk.19.attn_q_norm.weight 0x14d01d6c0 0x200
237 blk.19.attn_v.weight 0x14d01d8c0 0x6e000
238 blk.19.ffn_down_exps.weight 0x14d08b8c0 0x6c00000
239 blk.19.ffn_gate_exps.weight 0x153c8b8c0 0x4980000
240 blk.19.ffn_gate_inp.weight 0x15860b8c0 0x100000
241 blk.19.ffn_norm.weight 0x15870b8c0 0x2000
242 blk.19.ffn_up_exps.weight 0x15870d8c0 0x4980000
243 blk.20.attn_k.weight 0x15d08d8c0 0x62000
244 blk.20.attn_k_norm.weight 0x15d0ef8c0 0x200
245 blk.20.attn_norm.weight 0x15d0efac0 0x2000
246 blk.20.attn_output.weight 0x15d0f1ac0 0x480000
247 blk.20.attn_q.weight 0x15d571ac0 0x310000
248 blk.20.attn_q_norm.weight 0x15d881ac0 0x200
249 blk.20.attn_v.weight 0x15d881cc0 0x6e000
250 blk.20.ffn_down_exps.weight 0x15d8efcc0 0x6c00000
251 blk.20.ffn_gate_exps.weight 0x1644efcc0 0x4980000
252 blk.20.ffn_gate_inp.weight 0x168e6fcc0 0x100000
253 blk.20.ffn_norm.weight 0x168f6fcc0 0x2000
254 blk.20.ffn_up_exps.weight 0x168f71cc0 0x4980000
255 blk.21.attn_k.weight 0x16d8f1cc0 0x62000
256 blk.21.attn_k_norm.weight 0x16d953cc0 0x200
257 blk.21.attn_norm.weight 0x16d953ec0 0x2000
258 blk.21.attn_output.weight 0x16d955ec0 0x480000
259 blk.21.attn_q.weight 0x16ddd5ec0 0x310000
260 blk.21.attn_q_norm.weight 0x16e0e5ec0 0x200
261 blk.21.attn_v.weight 0x16e0e60c0 0x6e000
262 blk.21.ffn_down_exps.weight 0x16e1540c0 0x6c00000
263 blk.21.ffn_gate_exps.weight 0x174d540c0 0x4980000
264 blk.21.ffn_gate_inp.weight 0x1796d40c0 0x100000
265 blk.21.ffn_norm.weight 0x1797d40c0 0x2000
266 blk.21.ffn_up_exps.weight 0x1797d60c0 0x4980000
267 blk.22.attn_k.weight 0x17e1560c0 0x62000
268 blk.22.attn_k_norm.weight 0x17e1b80c0 0x200
269 blk.22.attn_norm.weight 0x17e1b82c0 0x2000
270 blk.22.attn_output.weight 0x17e1ba2c0 0x480000
271 blk.22.attn_q.weight 0x17e63a2c0 0x310000
272 blk.22.attn_q_norm.weight 0x17e94a2c0 0x200
273 blk.22.attn_v.weight 0x17e94a4c0 0x6e000
274 blk.22.ffn_down_exps.weight 0x17e9b84c0 0x6c00000
275 blk.22.ffn_gate_exps.weight 0x1855b84c0 0x4980000
276 blk.22.ffn_gate_inp.weight 0x189f384c0 0x100000
277 blk.22.ffn_norm.weight 0x18a0384c0 0x2000
278 blk.22.ffn_up_exps.weight 0x18a03a4c0 0x4980000
279 blk.23.attn_k.weight 0x18e9ba4c0 0x62000
280 blk.23.attn_k_norm.weight 0x18ea1c4c0 0x200
281 blk.23.attn_norm.weight 0x18ea1c6c0 0x2000
282 blk.23.attn_output.weight 0x18ea1e6c0 0x480000
283 blk.23.attn_q.weight 0x18ee9e6c0 0x310000
284 blk.23.attn_q_norm.weight 0x18f1ae6c0 0x200
285 blk.23.attn_v.weight 0x18f1ae8c0 0x6e000
286 blk.23.ffn_down_exps.weight 0x18f21c8c0 0x6c00000
287 blk.23.ffn_gate_exps.weight 0x195e1c8c0 0x4980000
288 blk.23.ffn_gate_inp.weight 0x19a79c8c0 0x100000
289 blk.23.ffn_norm.weight 0x19a89c8c0 0x2000
290 blk.23.ffn_up_exps.weight 0x19a89e8c0 0x4980000
291 blk.24.attn_k.weight 0x19f21e8c0 0x6e000
292 blk.24.attn_k_norm.weight 0x19f28c8c0 0x200
293 blk.24.attn_norm.weight 0x19f28cac0 0x2000
294 blk.24.attn_output.weight 0x19f28eac0 0x480000
295 blk.24.attn_q.weight 0x19f70eac0 0x370000
296 blk.24.attn_q_norm.weight 0x19fa7eac0 0x200
297 blk.24.attn_v.weight 0x19fa7ecc0 0x90000
298 blk.24.ffn_down_exps.weight 0x19fb0ecc0 0x6c00000
299 blk.24.ffn_gate_exps.weight 0x1a670ecc0 0x4980000
300 blk.24.ffn_gate_inp.weight 0x1ab08ecc0 0x100000
301 blk.24.ffn_norm.weight 0x1ab18ecc0 0x2000
302 blk.24.ffn_up_exps.weight 0x1ab190cc0 0x4980000
303 blk.25.attn_k.weight 0x1afb10cc0 0x6e000
304 blk.25.attn_k_norm.weight 0x1afb7ecc0 0x200
305 blk.25.attn_norm.weight 0x1afb7eec0 0x2000
306 blk.25.attn_output.weight 0x1afb80ec0 0x480000
307 blk.25.attn_q.weight 0x1b0000ec0 0x370000
308 blk.25.attn_q_norm.weight 0x1b0370ec0 0x200
309 blk.25.attn_v.weight 0x1b03710c0 0x90000
310 blk.25.ffn_down_exps.weight 0x1b04010c0 0x6c00000
311 blk.25.ffn_gate_exps.weight 0x1b70010c0 0x5280000
312 blk.25.ffn_gate_inp.weight 0x1bc2810c0 0x100000
313 blk.25.ffn_norm.weight 0x1bc3810c0 0x2000
314 blk.25.ffn_up_exps.weight 0x1bc3830c0 0x5280000
315 blk.26.attn_k.weight 0x1c16030c0 0x6e000
316 blk.26.attn_k_norm.weight 0x1c16710c0 0x200
317 blk.26.attn_norm.weight 0x1c16712c0 0x2000
318 blk.26.attn_output.weight 0x1c16732c0 0x480000
319 blk.26.attn_q.weight 0x1c1af32c0 0x370000
320 blk.26.attn_q_norm.weight 0x1c1e632c0 0x200
321 blk.26.attn_v.weight 0x1c1e634c0 0x90000
322 blk.26.ffn_down_exps.weight 0x1c1ef34c0 0x6c00000
323 blk.26.ffn_gate_exps.weight 0x1c8af34c0 0x4980000
324 blk.26.ffn_gate_inp.weight 0x1cd4734c0 0x100000
325 blk.26.ffn_norm.weight 0x1cd5734c0 0x2000
326 blk.26.ffn_up_exps.weight 0x1cd5754c0 0x4980000
327 blk.27.attn_k.weight 0x1d1ef54c0 0x6e000
328 blk.27.attn_k_norm.weight 0x1d1f634c0 0x200
329 blk.27.attn_norm.weight 0x1d1f636c0 0x2000
330 blk.27.attn_output.weight 0x1d1f656c0 0x480000
331 blk.27.attn_q.weight 0x1d23e56c0 0x370000
332 blk.27.attn_q_norm.weight 0x1d27556c0 0x200
333 blk.27.attn_v.weight 0x1d27558c0 0x90000
334 blk.27.ffn_down_exps.weight 0x1d27e58c0 0x6c00000
335 blk.27.ffn_gate_exps.weight 0x1d93e58c0 0x5280000
336 blk.27.ffn_gate_inp.weight 0x1de6658c0 0x100000
337 blk.27.ffn_norm.weight 0x1de7658c0 0x2000
338 blk.27.ffn_up_exps.weight 0x1de7678c0 0x5280000
339 blk.28.attn_k.weight 0x1e39e78c0 0x6e000
340 blk.28.attn_k_norm.weight 0x1e3a558c0 0x200
341 blk.28.attn_norm.weight 0x1e3a55ac0 0x2000
342 blk.28.attn_output.weight 0x1e3a57ac0 0x480000
343 blk.28.attn_q.weight 0x1e3ed7ac0 0x370000
344 blk.28.attn_q_norm.weight 0x1e4247ac0 0x200
345 blk.28.attn_v.weight 0x1e4247cc0 0x90000
346 blk.28.ffn_down_exps.weight 0x1e42d7cc0 0x6c00000
347 blk.28.ffn_gate_exps.weight 0x1eaed7cc0 0x5280000
348 blk.28.ffn_gate_inp.weight 0x1f0157cc0 0x100000
349 blk.28.ffn_norm.weight 0x1f0257cc0 0x2000
350 blk.28.ffn_up_exps.weight 0x1f0259cc0 0x5280000
351 blk.29.attn_k.weight 0x1f54d9cc0 0x6e000
352 blk.29.attn_k_norm.weight 0x1f5547cc0 0x200
353 blk.29.attn_norm.weight 0x1f5547ec0 0x2000
354 blk.29.attn_output.weight 0x1f5549ec0 0x480000
355 blk.29.attn_q.weight 0x1f59c9ec0 0x370000
356 blk.29.attn_q_norm.weight 0x1f5d39ec0 0x200
357 blk.29.attn_v.weight 0x1f5d3a0c0 0x90000
358 blk.29.ffn_down_exps.weight 0x1f5dca0c0 0x6c00000
359 blk.29.ffn_gate_exps.weight 0x1fc9ca0c0 0x5280000
360 blk.29.ffn_gate_inp.weight 0x201c4a0c0 0x100000
361 blk.29.ffn_norm.weight 0x201d4a0c0 0x2000
362 blk.29.ffn_up_exps.weight 0x201d4c0c0 0x5280000
363 blk.30.attn_k.weight 0x206fcc0c0 0x6e000
364 blk.30.attn_k_norm.weight 0x20703a0c0 0x200
365 blk.30.attn_norm.weight 0x20703a2c0 0x2000
366 blk.30.attn_output.weight 0x20703c2c0 0x480000
367 blk.30.attn_q.weight 0x2074bc2c0 0x370000
368 blk.30.attn_q_norm.weight 0x20782c2c0 0x200
369 blk.30.attn_v.weight 0x20782c4c0 0x90000
370 blk.30.ffn_down_exps.weight 0x2078bc4c0 0x6c00000
371 blk.30.ffn_gate_exps.weight 0x20e4bc4c0 0x5280000
372 blk.30.ffn_gate_inp.weight 0x21373c4c0 0x100000
373 blk.30.ffn_norm.weight 0x21383c4c0 0x2000
374 blk.30.ffn_up_exps.weight 0x21383e4c0 0x5280000
375 blk.31.attn_k.weight 0x218abe4c0 0x6e000
376 blk.31.attn_k_norm.weight 0x218b2c4c0 0x200
377 blk.31.attn_norm.weight 0x218b2c6c0 0x2000
378 blk.31.attn_output.weight 0x218b2e6c0 0x480000
379 blk.31.attn_q.weight 0x218fae6c0 0x370000
380 blk.31.attn_q_norm.weight 0x21931e6c0 0x200
381 blk.31.attn_v.weight 0x21931e8c0 0x90000
382 blk.31.ffn_down_exps.weight 0x2193ae8c0 0x6c00000
383 blk.31.ffn_gate_exps.weight 0x21ffae8c0 0x5280000
384 blk.31.ffn_gate_inp.weight 0x22522e8c0 0x100000
385 blk.31.ffn_norm.weight 0x22532e8c0 0x2000
386 blk.31.ffn_up_exps.weight 0x2253308c0 0x5280000
387 blk.32.attn_k.weight 0x22a5b08c0 0x6e000
388 blk.32.attn_k_norm.weight 0x22a61e8c0 0x200
389 blk.32.attn_norm.weight 0x22a61eac0 0x2000
390 blk.32.attn_output.weight 0x22a620ac0 0x480000
391 blk.32.attn_q.weight 0x22aaa0ac0 0x370000
392 blk.32.attn_q_norm.weight 0x22ae10ac0 0x200
393 blk.32.attn_v.weight 0x22ae10cc0 0x90000
394 blk.32.ffn_down_exps.weight 0x22aea0cc0 0x6c00000
395 blk.32.ffn_gate_exps.weight 0x231aa0cc0 0x5280000
396 blk.32.ffn_gate_inp.weight 0x236d20cc0 0x100000
397 blk.32.ffn_norm.weight 0x236e20cc0 0x2000
398 blk.32.ffn_up_exps.weight 0x236e22cc0 0x5280000
399 blk.33.attn_k.weight 0x23c0a2cc0 0x6e000
400 blk.33.attn_k_norm.weight 0x23c110cc0 0x200
401 blk.33.attn_norm.weight 0x23c110ec0 0x2000
402 blk.33.attn_output.weight 0x23c112ec0 0x480000
403 blk.33.attn_q.weight 0x23c592ec0 0x370000
404 blk.33.attn_q_norm.weight 0x23c902ec0 0x200
405 blk.33.attn_v.weight 0x23c9030c0 0x90000
406 blk.33.ffn_down_exps.weight 0x23c9930c0 0x6c00000
407 blk.33.ffn_gate_exps.weight 0x2435930c0 0x5280000
408 blk.33.ffn_gate_inp.weight 0x2488130c0 0x100000
409 blk.33.ffn_norm.weight 0x2489130c0 0x2000
410 blk.33.ffn_up_exps.weight 0x2489150c0 0x5280000
411 blk.34.attn_k.weight 0x24db950c0 0x6e000
412 blk.34.attn_k_norm.weight 0x24dc030c0 0x200
413 blk.34.attn_norm.weight 0x24dc032c0 0x2000
414 blk.34.attn_output.weight 0x24dc052c0 0x480000
415 blk.34.attn_q.weight 0x24e0852c0 0x370000
416 blk.34.attn_q_norm.weight 0x24e3f52c0 0x200
417 blk.34.attn_v.weight 0x24e3f54c0 0x90000
418 blk.34.ffn_down_exps.weight 0x24e4854c0 0x6c00000
419 blk.34.ffn_gate_exps.weight 0x2550854c0 0x5280000
420 blk.34.ffn_gate_inp.weight 0x25a3054c0 0x100000
421 blk.34.ffn_norm.weight 0x25a4054c0 0x2000
422 blk.34.ffn_up_exps.weight 0x25a4074c0 0x5280000
423 blk.35.attn_k.weight 0x25f6874c0 0x6e000
424 blk.35.attn_k_norm.weight 0x25f6f54c0 0x200
425 blk.35.attn_norm.weight 0x25f6f56c0 0x2000
426 blk.35.attn_output.weight 0x25f6f76c0 0x480000
427 blk.35.attn_q.weight 0x25fb776c0 0x370000
428 blk.35.attn_q_norm.weight 0x25fee76c0 0x200
429 blk.35.attn_v.weight 0x25fee78c0 0x90000
430 blk.35.ffn_down_exps.weight 0x25ff778c0 0x6c00000
431 blk.35.ffn_gate_exps.weight 0x266b778c0 0x5280000
432 blk.35.ffn_gate_inp.weight 0x26bdf78c0 0x100000
433 blk.35.ffn_norm.weight 0x26bef78c0 0x2000
434 blk.35.ffn_up_exps.weight 0x26bef98c0 0x5280000
435 blk.36.attn_k.weight 0x2711798c0 0x6e000
436 blk.36.attn_k_norm.weight 0x2711e78c0 0x200
437 blk.36.attn_norm.weight 0x2711e7ac0 0x2000
438 blk.36.attn_output.weight 0x2711e9ac0 0x480000
439 blk.36.attn_q.weight 0x271669ac0 0x370000
440 blk.36.attn_q_norm.weight 0x2719d9ac0 0x200
441 blk.36.attn_v.weight 0x2719d9cc0 0x90000
442 blk.36.ffn_down_exps.weight 0x271a69cc0 0x6c00000
443 blk.36.ffn_gate_exps.weight 0x278669cc0 0x5280000
444 blk.36.ffn_gate_inp.weight 0x27d8e9cc0 0x100000
445 blk.36.ffn_norm.weight 0x27d9e9cc0 0x2000
446 blk.36.ffn_up_exps.weight 0x27d9ebcc0 0x5280000
447 blk.37.attn_k.weight 0x282c6bcc0 0x6e000
448 blk.37.attn_k_norm.weight 0x282cd9cc0 0x200
449 blk.37.attn_norm.weight 0x282cd9ec0 0x2000
450 blk.37.attn_output.weight 0x282cdbec0 0x480000
451 blk.37.attn_q.weight 0x28315bec0 0x370000
452 blk.37.attn_q_norm.weight 0x2834cbec0 0x200
453 blk.37.attn_v.weight 0x2834cc0c0 0x90000
454 blk.37.ffn_down_exps.weight 0x28355c0c0 0x6c00000
455 blk.37.ffn_gate_exps.weight 0x28a15c0c0 0x5280000
456 blk.37.ffn_gate_inp.weight 0x28f3dc0c0 0x100000
457 blk.37.ffn_norm.weight 0x28f4dc0c0 0x2000
458 blk.37.ffn_up_exps.weight 0x28f4de0c0 0x5280000
459 blk.38.attn_k.weight 0x29475e0c0 0x6e000
460 blk.38.attn_k_norm.weight 0x2947cc0c0 0x200
461 blk.38.attn_norm.weight 0x2947cc2c0 0x2000
462 blk.38.attn_output.weight 0x2947ce2c0 0x480000
463 blk.38.attn_q.weight 0x294c4e2c0 0x370000
464 blk.38.attn_q_norm.weight 0x294fbe2c0 0x200
465 blk.38.attn_v.weight 0x294fbe4c0 0x90000
466 blk.38.ffn_down_exps.weight 0x29504e4c0 0x6c00000
467 blk.38.ffn_gate_exps.weight 0x29bc4e4c0 0x5280000
468 blk.38.ffn_gate_inp.weight 0x2a0ece4c0 0x100000
469 blk.38.ffn_norm.weight 0x2a0fce4c0 0x2000
470 blk.38.ffn_up_exps.weight 0x2a0fd04c0 0x5280000
471 blk.39.attn_k.weight 0x2a62504c0 0x6e000
472 blk.39.attn_k_norm.weight 0x2a62be4c0 0x200
473 blk.39.attn_norm.weight 0x2a62be6c0 0x2000
474 blk.39.attn_output.weight 0x2a62c06c0 0x480000
475 blk.39.attn_q.weight 0x2a67406c0 0x370000
476 blk.39.attn_q_norm.weight 0x2a6ab06c0 0x200
477 blk.39.attn_v.weight 0x2a6ab08c0 0x90000
478 blk.39.ffn_down_exps.weight 0x2a6b408c0 0x6c00000
479 blk.39.ffn_gate_exps.weight 0x2ad7408c0 0x5280000
480 blk.39.ffn_gate_inp.weight 0x2b29c08c0 0x100000
481 blk.39.ffn_norm.weight 0x2b2ac08c0 0x2000
482 blk.39.ffn_up_exps.weight 0x2b2ac28c0 0x5280000
483 blk.40.attn_k.weight 0x2b7d428c0 0x6e000
484 blk.40.attn_k_norm.weight 0x2b7db08c0 0x200
485 blk.40.attn_norm.weight 0x2b7db0ac0 0x2000
486 blk.40.attn_output.weight 0x2b7db2ac0 0x480000
487 blk.40.attn_q.weight 0x2b8232ac0 0x370000
488 blk.40.attn_q_norm.weight 0x2b85a2ac0 0x200
489 blk.40.attn_v.weight 0x2b85a2cc0 0x90000
490 blk.40.ffn_down_exps.weight 0x2b8632cc0 0x6c00000
491 blk.40.ffn_gate_exps.weight 0x2bf232cc0 0x5280000
492 blk.40.ffn_gate_inp.weight 0x2c44b2cc0 0x100000
493 blk.40.ffn_norm.weight 0x2c45b2cc0 0x2000
494 blk.40.ffn_up_exps.weight 0x2c45b4cc0 0x5280000
495 blk.41.attn_k.weight 0x2c9834cc0 0x6e000
496 blk.41.attn_k_norm.weight 0x2c98a2cc0 0x200
497 blk.41.attn_norm.weight 0x2c98a2ec0 0x2000
498 blk.41.attn_output.weight 0x2c98a4ec0 0x480000
499 blk.41.attn_q.weight 0x2c9d24ec0 0x370000
500 blk.41.attn_q_norm.weight 0x2ca094ec0 0x200
501 blk.41.attn_v.weight 0x2ca0950c0 0x90000
502 blk.41.ffn_down_exps.weight 0x2ca1250c0 0x6c00000
503 blk.41.ffn_gate_exps.weight 0x2d0d250c0 0x5280000
504 blk.41.ffn_gate_inp.weight 0x2d5fa50c0 0x100000
505 blk.41.ffn_norm.weight 0x2d60a50c0 0x2000
506 blk.41.ffn_up_exps.weight 0x2d60a70c0 0x5280000
507 blk.42.attn_k.weight 0x2db3270c0 0x6e000
508 blk.42.attn_k_norm.weight 0x2db3950c0 0x200
509 blk.42.attn_norm.weight 0x2db3952c0 0x2000
510 blk.42.attn_output.weight 0x2db3972c0 0x480000
511 blk.42.attn_q.weight 0x2db8172c0 0x370000
512 blk.42.attn_q_norm.weight 0x2dbb872c0 0x200
513 blk.42.attn_v.weight 0x2dbb874c0 0x90000
514 blk.42.ffn_down_exps.weight 0x2dbc174c0 0x6c00000
515 blk.42.ffn_gate_exps.weight 0x2e28174c0 0x5280000
516 blk.42.ffn_gate_inp.weight 0x2e7a974c0 0x100000
517 blk.42.ffn_norm.weight 0x2e7b974c0 0x2000
518 blk.42.ffn_up_exps.weight 0x2e7b994c0 0x5280000
519 blk.43.attn_k.weight 0x2ece194c0 0x6e000
520 blk.43.attn_k_norm.weight 0x2ece874c0 0x200
521 blk.43.attn_norm.weight 0x2ece876c0 0x2000
522 blk.43.attn_output.weight 0x2ece896c0 0x480000
523 blk.43.attn_q.weight 0x2ed3096c0 0x370000
524 blk.43.attn_q_norm.weight 0x2ed6796c0 0x200
525 blk.43.attn_v.weight 0x2ed6798c0 0x90000
526 blk.43.ffn_down_exps.weight 0x2ed7098c0 0x6c00000
527 blk.43.ffn_gate_exps.weight 0x2f43098c0 0x5280000
528 blk.43.ffn_gate_inp.weight 0x2f95898c0 0x100000
529 blk.43.ffn_norm.weight 0x2f96898c0 0x2000
530 blk.43.ffn_up_exps.weight 0x2f968b8c0 0x5280000
531 blk.44.attn_k.weight 0x2fe90b8c0 0x6e000
532 blk.44.attn_k_norm.weight 0x2fe9798c0 0x200
533 blk.44.attn_norm.weight 0x2fe979ac0 0x2000
534 blk.44.attn_output.weight 0x2fe97bac0 0x480000
535 blk.44.attn_q.weight 0x2fedfbac0 0x370000
536 blk.44.attn_q_norm.weight 0x2ff16bac0 0x200
537 blk.44.attn_v.weight 0x2ff16bcc0 0x90000
538 blk.44.ffn_down_exps.weight 0x2ff1fbcc0 0x6c00000
539 blk.44.ffn_gate_exps.weight 0x305dfbcc0 0x5280000
540 blk.44.ffn_gate_inp.weight 0x30b07bcc0 0x100000
541 blk.44.ffn_norm.weight 0x30b17bcc0 0x2000
542 blk.44.ffn_up_exps.weight 0x30b17dcc0 0x5280000
543 blk.45.attn_k.weight 0x3103fdcc0 0x6e000
544 blk.45.attn_k_norm.weight 0x31046bcc0 0x200
545 blk.45.attn_norm.weight 0x31046bec0 0x2000
546 blk.45.attn_output.weight 0x31046dec0 0x480000
547 blk.45.attn_q.weight 0x3108edec0 0x370000
548 blk.45.attn_q_norm.weight 0x310c5dec0 0x200
549 blk.45.attn_v.weight 0x310c5e0c0 0x90000
550 blk.45.ffn_down_exps.weight 0x310cee0c0 0x6c00000
551 blk.45.ffn_gate_exps.weight 0x3178ee0c0 0x5280000
552 blk.45.ffn_gate_inp.weight 0x31cb6e0c0 0x100000
553 blk.45.ffn_norm.weight 0x31cc6e0c0 0x2000
554 blk.45.ffn_up_exps.weight 0x31cc700c0 0x5280000
555 blk.46.attn_k.weight 0x321ef00c0 0x6e000
556 blk.46.attn_k_norm.weight 0x321f5e0c0 0x200
557 blk.46.attn_norm.weight 0x321f5e2c0 0x2000
558 blk.46.attn_output.weight 0x321f602c0 0x480000
559 blk.46.attn_q.weight 0x3223e02c0 0x370000
560 blk.46.attn_q_norm.weight 0x3227502c0 0x200
561 blk.46.attn_v.weight 0x3227504c0 0x90000
562 blk.46.ffn_down_exps.weight 0x3227e04c0 0x6c00000
563 blk.46.ffn_gate_exps.weight 0x3293e04c0 0x5280000
564 blk.46.ffn_gate_inp.weight 0x32e6604c0 0x100000
565 blk.46.ffn_norm.weight 0x32e7604c0 0x2000
566 blk.46.ffn_up_exps.weight 0x32e7624c0 0x5280000
567 blk.47.attn_k.weight 0x3339e24c0 0x6e000
568 blk.47.attn_k_norm.weight 0x333a504c0 0x200
569 blk.47.attn_norm.weight 0x333a506c0 0x2000
570 blk.47.attn_output.weight 0x333a526c0 0x480000
571 blk.47.attn_q.weight 0x333ed26c0 0x370000
572 blk.47.attn_q_norm.weight 0x3342426c0 0x200
573 blk.47.attn_v.weight 0x3342428c0 0x90000
574 blk.47.ffn_down_exps.weight 0x3342d28c0 0x6c00000
575 blk.47.ffn_gate_exps.weight 0x33aed28c0 0x5280000
576 blk.47.ffn_gate_inp.weight 0x3401528c0 0x100000
577 blk.47.ffn_norm.weight 0x3402528c0 0x2000
578 blk.47.ffn_up_exps.weight 0x3402548c0 0x5280000

Base Tensor Group : ~622M Elements

T_ID Tensor Layer Name Human Friendly Tensor Layer Name Elements Shape Type
0 output.weight Output (W) (~311M) 311164928 2048 x 151936 x 1 x 1 IQ3_S
1 output_norm.weight Output Normalization (W) ( ~2K) 2048 2048 x 1 x 1 x 1 F32
2 token_embd.weight Token Embedding (W) (~311M) 311164928 2048 x 151936 x 1 x 1 IQ3_S
  • Total elements in base: (~622M) 622331904
  • Percentage of total elements: 2.04%

Block 0 Tensor Group : ~623M Elements

T_ID Tensor Layer Name Human Friendly Tensor Layer Name Elements Shape Type
3 blk.0.attn_k.weight Block 0 Attention Key (W) ( ~1M) 1048576 2048 x 512 x 1 x 1 IQ3_XXS
4 blk.0.attn_k_norm.weight Block 0 Attn_K_Norm (W) ( 128) 128 128 x 1 x 1 x 1 F32
5 blk.0.attn_norm.weight Block 0 Attention Normalization (W) ( ~2K) 2048 2048 x 1 x 1 x 1 F32
6 blk.0.attn_output.weight Block 0 Attention Output (W) ( ~8M) 8388608 4096 x 2048 x 1 x 1 Q4_K
7 blk.0.attn_q.weight Block 0 Attention Query (W) ( ~8M) 8388608 2048 x 4096 x 1 x 1 IQ3_XXS
8 blk.0.attn_q_norm.weight Block 0 Attn_Q_Norm (W) ( 128) 128 128 x 1 x 1 x 1 F32
9 blk.0.attn_v.weight Block 0 Attention Value (W) ( ~1M) 1048576 2048 x 512 x 1 x 1 IQ3_S
10 blk.0.ffn_down_exps.weight Block 0 Ffn_Down_Exps (W) (~201M) 201326592 768 x 2048 x 128 x 1 IQ4_NL
11 blk.0.ffn_gate_exps.weight Block 0 Ffn_Gate_Exps (W) (~201M) 201326592 2048 x 768 x 128 x 1 IQ3_XXS
12 blk.0.ffn_gate_inp.weight Block 0 Expert-Routing Layer For The Feed-Forward Network In Mixture Of Expert Models (W) (~262K) 262144 2048 x 128 x 1 x 1 F32
13 blk.0.ffn_norm.weight Block 0 Feed-Forward Network Normalization (W) ( ~2K) 2048 2048 x 1 x 1 x 1 F32
14 blk.0.ffn_up_exps.weight Block 0 Ffn_Up_Exps (W) (~201M) 201326592 2048 x 768 x 128 x 1 IQ3_XXS
  • Total elements in blk.0: (~623M) 623120640
  • Percentage of total elements: 2.04%

Block 1 Tensor Group : ~623M Elements

T_ID Tensor Layer Name Human Friendly Tensor Layer Name Elements Shape Type
15 blk.1.attn_k.weight Block 1 Attention Key (W) ( ~1M) 1048576 2048 x 512 x 1 x 1 IQ3_XXS
16 blk.1.attn_k_norm.weight Block 1 Attn_K_Norm (W) ( 128) 128 128 x 1 x 1 x 1 F32
17 blk.1.attn_norm.weight Block 1 Attention Normalization (W) ( ~2K) 2048 2048 x 1 x 1 x 1 F32
18 blk.1.attn_output.weight Block 1 Attention Output (W) ( ~8M) 8388608 4096 x 2048 x 1 x 1 Q4_K
19 blk.1.attn_q.weight Block 1 Attention Query (W) ( ~8M) 8388608 2048 x 4096 x 1 x 1 IQ3_XXS
20 blk.1.attn_q_norm.weight Block 1 Attn_Q_Norm (W) ( 128) 128 128 x 1 x 1 x 1 F32
21 blk.1.attn_v.weight Block 1 Attention Value (W) ( ~1M) 1048576 2048 x 512 x 1 x 1 IQ3_S
22 blk.1.ffn_down_exps.weight Block 1 Ffn_Down_Exps (W) (~201M) 201326592 768 x 2048 x 128 x 1 IQ4_NL
23 blk.1.ffn_gate_exps.weight Block 1 Ffn_Gate_Exps (W) (~201M) 201326592 2048 x 768 x 128 x 1 IQ3_XXS
24 blk.1.ffn_gate_inp.weight Block 1 Expert-Routing Layer For The Feed-Forward Network In Mixture Of Expert Models (W) (~262K) 262144 2048 x 128 x 1 x 1 F32
25 blk.1.ffn_norm.weight Block 1 Feed-Forward Network Normalization (W) ( ~2K) 2048 2048 x 1 x 1 x 1 F32
26 blk.1.ffn_up_exps.weight Block 1 Ffn_Up_Exps (W) (~201M) 201326592 2048 x 768 x 128 x 1 IQ3_XXS
  • Total elements in blk.1: (~623M) 623120640
  • Percentage of total elements: 2.04%

Block 2 Tensor Group : ~623M Elements

T_ID Tensor Layer Name Human Friendly Tensor Layer Name Elements Shape Type
27 blk.2.attn_k.weight Block 2 Attention Key (W) ( ~1M) 1048576 2048 x 512 x 1 x 1 IQ3_XXS
28 blk.2.attn_k_norm.weight Block 2 Attn_K_Norm (W) ( 128) 128 128 x 1 x 1 x 1 F32
29 blk.2.attn_norm.weight Block 2 Attention Normalization (W) ( ~2K) 2048 2048 x 1 x 1 x 1 F32
30 blk.2.attn_output.weight Block 2 Attention Output (W) ( ~8M) 8388608 4096 x 2048 x 1 x 1 Q4_K
31 blk.2.attn_q.weight Block 2 Attention Query (W) ( ~8M) 8388608 2048 x 4096 x 1 x 1 IQ3_XXS
32 blk.2.attn_q_norm.weight Block 2 Attn_Q_Norm (W) ( 128) 128 128 x 1 x 1 x 1 F32
33 blk.2.attn_v.weight Block 2 Attention Value (W) ( ~1M) 1048576 2048 x 512 x 1 x 1 IQ3_S
34 blk.2.ffn_down_exps.weight Block 2 Ffn_Down_Exps (W) (~201M) 201326592 768 x 2048 x 128 x 1 IQ4_NL
35 blk.2.ffn_gate_exps.weight Block 2 Ffn_Gate_Exps (W) (~201M) 201326592 2048 x 768 x 128 x 1 IQ3_XXS
36 blk.2.ffn_gate_inp.weight Block 2 Expert-Routing Layer For The Feed-Forward Network In Mixture Of Expert Models (W) (~262K) 262144 2048 x 128 x 1 x 1 F32
37 blk.2.ffn_norm.weight Block 2 Feed-Forward Network Normalization (W) ( ~2K) 2048 2048 x 1 x 1 x 1 F32
38 blk.2.ffn_up_exps.weight Block 2 Ffn_Up_Exps (W) (~201M) 201326592 2048 x 768 x 128 x 1 IQ3_XXS
  • Total elements in blk.2: (~623M) 623120640
  • Percentage of total elements: 2.04%

Block 3 Tensor Group : ~623M Elements

T_ID Tensor Layer Name Human Friendly Tensor Layer Name Elements Shape Type
39 blk.3.attn_k.weight Block 3 Attention Key (W) ( ~1M) 1048576 2048 x 512 x 1 x 1 IQ3_XXS
40 blk.3.attn_k_norm.weight Block 3 Attn_K_Norm (W) ( 128) 128 128 x 1 x 1 x 1 F32
41 blk.3.attn_norm.weight Block 3 Attention Normalization (W) ( ~2K) 2048 2048 x 1 x 1 x 1 F32
42 blk.3.attn_output.weight Block 3 Attention Output (W) ( ~8M) 8388608 4096 x 2048 x 1 x 1 Q4_K
43 blk.3.attn_q.weight Block 3 Attention Query (W) ( ~8M) 8388608 2048 x 4096 x 1 x 1 IQ3_XXS
44 blk.3.attn_q_norm.weight Block 3 Attn_Q_Norm (W) ( 128) 128 128 x 1 x 1 x 1 F32
45 blk.3.attn_v.weight Block 3 Attention Value (W) ( ~1M) 1048576 2048 x 512 x 1 x 1 IQ3_S
46 blk.3.ffn_down_exps.weight Block 3 Ffn_Down_Exps (W) (~201M) 201326592 768 x 2048 x 128 x 1 IQ4_NL
47 blk.3.ffn_gate_exps.weight Block 3 Ffn_Gate_Exps (W) (~201M) 201326592 2048 x 768 x 128 x 1 IQ3_XXS
48 blk.3.ffn_gate_inp.weight Block 3 Expert-Routing Layer For The Feed-Forward Network In Mixture Of Expert Models (W) (~262K) 262144 2048 x 128 x 1 x 1 F32
49 blk.3.ffn_norm.weight Block 3 Feed-Forward Network Normalization (W) ( ~2K) 2048 2048 x 1 x 1 x 1 F32
50 blk.3.ffn_up_exps.weight Block 3 Ffn_Up_Exps (W) (~201M) 201326592 2048 x 768 x 128 x 1 IQ3_XXS
  • Total elements in blk.3: (~623M) 623120640
  • Percentage of total elements: 2.04%

Block 4 Tensor Group : ~623M Elements

T_ID Tensor Layer Name Human Friendly Tensor Layer Name Elements Shape Type
51 blk.4.attn_k.weight Block 4 Attention Key (W) ( ~1M) 1048576 2048 x 512 x 1 x 1 IQ3_XXS
52 blk.4.attn_k_norm.weight Block 4 Attn_K_Norm (W) ( 128) 128 128 x 1 x 1 x 1 F32
53 blk.4.attn_norm.weight Block 4 Attention Normalization (W) ( ~2K) 2048 2048 x 1 x 1 x 1 F32
54 blk.4.attn_output.weight Block 4 Attention Output (W) ( ~8M) 8388608 4096 x 2048 x 1 x 1 Q4_K
55 blk.4.attn_q.weight Block 4 Attention Query (W) ( ~8M) 8388608 2048 x 4096 x 1 x 1 IQ3_XXS
56 blk.4.attn_q_norm.weight Block 4 Attn_Q_Norm (W) ( 128) 128 128 x 1 x 1 x 1 F32
57 blk.4.attn_v.weight Block 4 Attention Value (W) ( ~1M) 1048576 2048 x 512 x 1 x 1 IQ3_S
58 blk.4.ffn_down_exps.weight Block 4 Ffn_Down_Exps (W) (~201M) 201326592 768 x 2048 x 128 x 1 IQ4_NL
59 blk.4.ffn_gate_exps.weight Block 4 Ffn_Gate_Exps (W) (~201M) 201326592 2048 x 768 x 128 x 1 IQ3_XXS
60 blk.4.ffn_gate_inp.weight Block 4 Expert-Routing Layer For The Feed-Forward Network In Mixture Of Expert Models (W) (~262K) 262144 2048 x 128 x 1 x 1 F32
61 blk.4.ffn_norm.weight Block 4 Feed-Forward Network Normalization (W) ( ~2K) 2048 2048 x 1 x 1 x 1 F32
62 blk.4.ffn_up_exps.weight Block 4 Ffn_Up_Exps (W) (~201M) 201326592 2048 x 768 x 128 x 1 IQ3_XXS
  • Total elements in blk.4: (~623M) 623120640
  • Percentage of total elements: 2.04%

Block 5 Tensor Group : ~623M Elements

T_ID Tensor Layer Name Human Friendly Tensor Layer Name Elements Shape Type
63 blk.5.attn_k.weight Block 5 Attention Key (W) ( ~1M) 1048576 2048 x 512 x 1 x 1 IQ3_XXS
64 blk.5.attn_k_norm.weight Block 5 Attn_K_Norm (W) ( 128) 128 128 x 1 x 1 x 1 F32
65 blk.5.attn_norm.weight Block 5 Attention Normalization (W) ( ~2K) 2048 2048 x 1 x 1 x 1 F32
66 blk.5.attn_output.weight Block 5 Attention Output (W) ( ~8M) 8388608 4096 x 2048 x 1 x 1 Q4_K
67 blk.5.attn_q.weight Block 5 Attention Query (W) ( ~8M) 8388608 2048 x 4096 x 1 x 1 IQ3_XXS
68 blk.5.attn_q_norm.weight Block 5 Attn_Q_Norm (W) ( 128) 128 128 x 1 x 1 x 1 F32
69 blk.5.attn_v.weight Block 5 Attention Value (W) ( ~1M) 1048576 2048 x 512 x 1 x 1 IQ3_S
70 blk.5.ffn_down_exps.weight Block 5 Ffn_Down_Exps (W) (~201M) 201326592 768 x 2048 x 128 x 1 IQ4_NL
71 blk.5.ffn_gate_exps.weight Block 5 Ffn_Gate_Exps (W) (~201M) 201326592 2048 x 768 x 128 x 1 IQ3_XXS
72 blk.5.ffn_gate_inp.weight Block 5 Expert-Routing Layer For The Feed-Forward Network In Mixture Of Expert Models (W) (~262K) 262144 2048 x 128 x 1 x 1 F32
73 blk.5.ffn_norm.weight Block 5 Feed-Forward Network Normalization (W) ( ~2K) 2048 2048 x 1 x 1 x 1 F32
74 blk.5.ffn_up_exps.weight Block 5 Ffn_Up_Exps (W) (~201M) 201326592 2048 x 768 x 128 x 1 IQ3_XXS
  • Total elements in blk.5: (~623M) 623120640
  • Percentage of total elements: 2.04%

Block 6 Tensor Group : ~623M Elements

T_ID Tensor Layer Name Human Friendly Tensor Layer Name Elements Shape Type
75 blk.6.attn_k.weight Block 6 Attention Key (W) ( ~1M) 1048576 2048 x 512 x 1 x 1 IQ3_XXS
76 blk.6.attn_k_norm.weight Block 6 Attn_K_Norm (W) ( 128) 128 128 x 1 x 1 x 1 F32
77 blk.6.attn_norm.weight Block 6 Attention Normalization (W) ( ~2K) 2048 2048 x 1 x 1 x 1 F32
78 blk.6.attn_output.weight Block 6 Attention Output (W) ( ~8M) 8388608 4096 x 2048 x 1 x 1 Q4_K
79 blk.6.attn_q.weight Block 6 Attention Query (W) ( ~8M) 8388608 2048 x 4096 x 1 x 1 IQ3_XXS
80 blk.6.attn_q_norm.weight Block 6 Attn_Q_Norm (W) ( 128) 128 128 x 1 x 1 x 1 F32
81 blk.6.attn_v.weight Block 6 Attention Value (W) ( ~1M) 1048576 2048 x 512 x 1 x 1 IQ3_S
82 blk.6.ffn_down_exps.weight Block 6 Ffn_Down_Exps (W) (~201M) 201326592 768 x 2048 x 128 x 1 IQ4_NL
83 blk.6.ffn_gate_exps.weight Block 6 Ffn_Gate_Exps (W) (~201M) 201326592 2048 x 768 x 128 x 1 IQ3_XXS
84 blk.6.ffn_gate_inp.weight Block 6 Expert-Routing Layer For The Feed-Forward Network In Mixture Of Expert Models (W) (~262K) 262144 2048 x 128 x 1 x 1 F32
85 blk.6.ffn_norm.weight Block 6 Feed-Forward Network Normalization (W) ( ~2K) 2048 2048 x 1 x 1 x 1 F32
86 blk.6.ffn_up_exps.weight Block 6 Ffn_Up_Exps (W) (~201M) 201326592 2048 x 768 x 128 x 1 IQ3_XXS
  • Total elements in blk.6: (~623M) 623120640
  • Percentage of total elements: 2.04%

Block 7 Tensor Group : ~623M Elements

T_ID Tensor Layer Name Human Friendly Tensor Layer Name Elements Shape Type
87 blk.7.attn_k.weight Block 7 Attention Key (W) ( ~1M) 1048576 2048 x 512 x 1 x 1 IQ3_XXS
88 blk.7.attn_k_norm.weight Block 7 Attn_K_Norm (W) ( 128) 128 128 x 1 x 1 x 1 F32
89 blk.7.attn_norm.weight Block 7 Attention Normalization (W) ( ~2K) 2048 2048 x 1 x 1 x 1 F32
90 blk.7.attn_output.weight Block 7 Attention Output (W) ( ~8M) 8388608 4096 x 2048 x 1 x 1 Q4_K
91 blk.7.attn_q.weight Block 7 Attention Query (W) ( ~8M) 8388608 2048 x 4096 x 1 x 1 IQ3_XXS
92 blk.7.attn_q_norm.weight Block 7 Attn_Q_Norm (W) ( 128) 128 128 x 1 x 1 x 1 F32
93 blk.7.attn_v.weight Block 7 Attention Value (W) ( ~1M) 1048576 2048 x 512 x 1 x 1 IQ3_S
94 blk.7.ffn_down_exps.weight Block 7 Ffn_Down_Exps (W) (~201M) 201326592 768 x 2048 x 128 x 1 IQ4_NL
95 blk.7.ffn_gate_exps.weight Block 7 Ffn_Gate_Exps (W) (~201M) 201326592 2048 x 768 x 128 x 1 IQ3_XXS
96 blk.7.ffn_gate_inp.weight Block 7 Expert-Routing Layer For The Feed-Forward Network In Mixture Of Expert Models (W) (~262K) 262144 2048 x 128 x 1 x 1 F32
97 blk.7.ffn_norm.weight Block 7 Feed-Forward Network Normalization (W) ( ~2K) 2048 2048 x 1 x 1 x 1 F32
98 blk.7.ffn_up_exps.weight Block 7 Ffn_Up_Exps (W) (~201M) 201326592 2048 x 768 x 128 x 1 IQ3_XXS
  • Total elements in blk.7: (~623M) 623120640
  • Percentage of total elements: 2.04%

Block 8 Tensor Group : ~623M Elements

T_ID Tensor Layer Name Human Friendly Tensor Layer Name Elements Shape Type
99 blk.8.attn_k.weight Block 8 Attention Key (W) ( ~1M) 1048576 2048 x 512 x 1 x 1 IQ3_XXS
100 blk.8.attn_k_norm.weight Block 8 Attn_K_Norm (W) ( 128) 128 128 x 1 x 1 x 1 F32
101 blk.8.attn_norm.weight Block 8 Attention Normalization (W) ( ~2K) 2048 2048 x 1 x 1 x 1 F32
102 blk.8.attn_output.weight Block 8 Attention Output (W) ( ~8M) 8388608 4096 x 2048 x 1 x 1 Q4_K
103 blk.8.attn_q.weight Block 8 Attention Query (W) ( ~8M) 8388608 2048 x 4096 x 1 x 1 IQ3_XXS
104 blk.8.attn_q_norm.weight Block 8 Attn_Q_Norm (W) ( 128) 128 128 x 1 x 1 x 1 F32
105 blk.8.attn_v.weight Block 8 Attention Value (W) ( ~1M) 1048576 2048 x 512 x 1 x 1 IQ3_S
106 blk.8.ffn_down_exps.weight Block 8 Ffn_Down_Exps (W) (~201M) 201326592 768 x 2048 x 128 x 1 IQ4_NL
107 blk.8.ffn_gate_exps.weight Block 8 Ffn_Gate_Exps (W) (~201M) 201326592 2048 x 768 x 128 x 1 IQ3_XXS
108 blk.8.ffn_gate_inp.weight Block 8 Expert-Routing Layer For The Feed-Forward Network In Mixture Of Expert Models (W) (~262K) 262144 2048 x 128 x 1 x 1 F32
109 blk.8.ffn_norm.weight Block 8 Feed-Forward Network Normalization (W) ( ~2K) 2048 2048 x 1 x 1 x 1 F32
110 blk.8.ffn_up_exps.weight Block 8 Ffn_Up_Exps (W) (~201M) 201326592 2048 x 768 x 128 x 1 IQ3_XXS
  • Total elements in blk.8: (~623M) 623120640
  • Percentage of total elements: 2.04%

Block 9 Tensor Group : ~623M Elements

T_ID Tensor Layer Name Human Friendly Tensor Layer Name Elements Shape Type
111 blk.9.attn_k.weight Block 9 Attention Key (W) ( ~1M) 1048576 2048 x 512 x 1 x 1 IQ3_XXS
112 blk.9.attn_k_norm.weight Block 9 Attn_K_Norm (W) ( 128) 128 128 x 1 x 1 x 1 F32
113 blk.9.attn_norm.weight Block 9 Attention Normalization (W) ( ~2K) 2048 2048 x 1 x 1 x 1 F32
114 blk.9.attn_output.weight Block 9 Attention Output (W) ( ~8M) 8388608 4096 x 2048 x 1 x 1 Q4_K
115 blk.9.attn_q.weight Block 9 Attention Query (W) ( ~8M) 8388608 2048 x 4096 x 1 x 1 IQ3_XXS
116 blk.9.attn_q_norm.weight Block 9 Attn_Q_Norm (W) ( 128) 128 128 x 1 x 1 x 1 F32
117 blk.9.attn_v.weight Block 9 Attention Value (W) ( ~1M) 1048576 2048 x 512 x 1 x 1 IQ3_S
118 blk.9.ffn_down_exps.weight Block 9 Ffn_Down_Exps (W) (~201M) 201326592 768 x 2048 x 128 x 1 IQ4_NL
119 blk.9.ffn_gate_exps.weight Block 9 Ffn_Gate_Exps (W) (~201M) 201326592 2048 x 768 x 128 x 1 IQ3_XXS
120 blk.9.ffn_gate_inp.weight Block 9 Expert-Routing Layer For The Feed-Forward Network In Mixture Of Expert Models (W) (~262K) 262144 2048 x 128 x 1 x 1 F32
121 blk.9.ffn_norm.weight Block 9 Feed-Forward Network Normalization (W) ( ~2K) 2048 2048 x 1 x 1 x 1 F32
122 blk.9.ffn_up_exps.weight Block 9 Ffn_Up_Exps (W) (~201M) 201326592 2048 x 768 x 128 x 1 IQ3_XXS
  • Total elements in blk.9: (~623M) 623120640
  • Percentage of total elements: 2.04%

Block 10 Tensor Group : ~623M Elements

T_ID Tensor Layer Name Human Friendly Tensor Layer Name Elements Shape Type
123 blk.10.attn_k.weight Block 10 Attention Key (W) ( ~1M) 1048576 2048 x 512 x 1 x 1 IQ3_XXS
124 blk.10.attn_k_norm.weight Block 10 Attn_K_Norm (W) ( 128) 128 128 x 1 x 1 x 1 F32
125 blk.10.attn_norm.weight Block 10 Attention Normalization (W) ( ~2K) 2048 2048 x 1 x 1 x 1 F32
126 blk.10.attn_output.weight Block 10 Attention Output (W) ( ~8M) 8388608 4096 x 2048 x 1 x 1 Q4_K
127 blk.10.attn_q.weight Block 10 Attention Query (W) ( ~8M) 8388608 2048 x 4096 x 1 x 1 IQ3_XXS
128 blk.10.attn_q_norm.weight Block 10 Attn_Q_Norm (W) ( 128) 128 128 x 1 x 1 x 1 F32
129 blk.10.attn_v.weight Block 10 Attention Value (W) ( ~1M) 1048576 2048 x 512 x 1 x 1 IQ3_S
130 blk.10.ffn_down_exps.weight Block 10 Ffn_Down_Exps (W) (~201M) 201326592 768 x 2048 x 128 x 1 IQ4_NL
131 blk.10.ffn_gate_exps.weight Block 10 Ffn_Gate_Exps (W) (~201M) 201326592 2048 x 768 x 128 x 1 IQ3_XXS
132 blk.10.ffn_gate_inp.weight Block 10 Expert-Routing Layer For The Feed-Forward Network In Mixture Of Expert Models (W) (~262K) 262144 2048 x 128 x 1 x 1 F32
133 blk.10.ffn_norm.weight Block 10 Feed-Forward Network Normalization (W) ( ~2K) 2048 2048 x 1 x 1 x 1 F32
134 blk.10.ffn_up_exps.weight Block 10 Ffn_Up_Exps (W) (~201M) 201326592 2048 x 768 x 128 x 1 IQ3_XXS
  • Total elements in blk.10: (~623M) 623120640
  • Percentage of total elements: 2.04%

Block 11 Tensor Group : ~623M Elements

T_ID Tensor Layer Name Human Friendly Tensor Layer Name Elements Shape Type
135 blk.11.attn_k.weight Block 11 Attention Key (W) ( ~1M) 1048576 2048 x 512 x 1 x 1 IQ3_XXS
136 blk.11.attn_k_norm.weight Block 11 Attn_K_Norm (W) ( 128) 128 128 x 1 x 1 x 1 F32
137 blk.11.attn_norm.weight Block 11 Attention Normalization (W) ( ~2K) 2048 2048 x 1 x 1 x 1 F32
138 blk.11.attn_output.weight Block 11 Attention Output (W) ( ~8M) 8388608 4096 x 2048 x 1 x 1 Q4_K
139 blk.11.attn_q.weight Block 11 Attention Query (W) ( ~8M) 8388608 2048 x 4096 x 1 x 1 IQ3_XXS
140 blk.11.attn_q_norm.weight Block 11 Attn_Q_Norm (W) ( 128) 128 128 x 1 x 1 x 1 F32
141 blk.11.attn_v.weight Block 11 Attention Value (W) ( ~1M) 1048576 2048 x 512 x 1 x 1 IQ3_S
142 blk.11.ffn_down_exps.weight Block 11 Ffn_Down_Exps (W) (~201M) 201326592 768 x 2048 x 128 x 1 IQ4_NL
143 blk.11.ffn_gate_exps.weight Block 11 Ffn_Gate_Exps (W) (~201M) 201326592 2048 x 768 x 128 x 1 IQ3_XXS
144 blk.11.ffn_gate_inp.weight Block 11 Expert-Routing Layer For The Feed-Forward Network In Mixture Of Expert Models (W) (~262K) 262144 2048 x 128 x 1 x 1 F32
145 blk.11.ffn_norm.weight Block 11 Feed-Forward Network Normalization (W) ( ~2K) 2048 2048 x 1 x 1 x 1 F32
146 blk.11.ffn_up_exps.weight Block 11 Ffn_Up_Exps (W) (~201M) 201326592 2048 x 768 x 128 x 1 IQ3_XXS
  • Total elements in blk.11: (~623M) 623120640
  • Percentage of total elements: 2.04%

Block 12 Tensor Group : ~623M Elements

T_ID Tensor Layer Name Human Friendly Tensor Layer Name Elements Shape Type
147 blk.12.attn_k.weight Block 12 Attention Key (W) ( ~1M) 1048576 2048 x 512 x 1 x 1 IQ3_XXS
148 blk.12.attn_k_norm.weight Block 12 Attn_K_Norm (W) ( 128) 128 128 x 1 x 1 x 1 F32
149 blk.12.attn_norm.weight Block 12 Attention Normalization (W) ( ~2K) 2048 2048 x 1 x 1 x 1 F32
150 blk.12.attn_output.weight Block 12 Attention Output (W) ( ~8M) 8388608 4096 x 2048 x 1 x 1 Q4_K
151 blk.12.attn_q.weight Block 12 Attention Query (W) ( ~8M) 8388608 2048 x 4096 x 1 x 1 IQ3_XXS
152 blk.12.attn_q_norm.weight Block 12 Attn_Q_Norm (W) ( 128) 128 128 x 1 x 1 x 1 F32
153 blk.12.attn_v.weight Block 12 Attention Value (W) ( ~1M) 1048576 2048 x 512 x 1 x 1 IQ3_S
154 blk.12.ffn_down_exps.weight Block 12 Ffn_Down_Exps (W) (~201M) 201326592 768 x 2048 x 128 x 1 IQ4_NL
155 blk.12.ffn_gate_exps.weight Block 12 Ffn_Gate_Exps (W) (~201M) 201326592 2048 x 768 x 128 x 1 IQ3_XXS
156 blk.12.ffn_gate_inp.weight Block 12 Expert-Routing Layer For The Feed-Forward Network In Mixture Of Expert Models (W) (~262K) 262144 2048 x 128 x 1 x 1 F32
157 blk.12.ffn_norm.weight Block 12 Feed-Forward Network Normalization (W) ( ~2K) 2048 2048 x 1 x 1 x 1 F32
158 blk.12.ffn_up_exps.weight Block 12 Ffn_Up_Exps (W) (~201M) 201326592 2048 x 768 x 128 x 1 IQ3_XXS
  • Total elements in blk.12: (~623M) 623120640
  • Percentage of total elements: 2.04%

Block 13 Tensor Group : ~623M Elements

T_ID Tensor Layer Name Human Friendly Tensor Layer Name Elements Shape Type
159 blk.13.attn_k.weight Block 13 Attention Key (W) ( ~1M) 1048576 2048 x 512 x 1 x 1 IQ3_XXS
160 blk.13.attn_k_norm.weight Block 13 Attn_K_Norm (W) ( 128) 128 128 x 1 x 1 x 1 F32
161 blk.13.attn_norm.weight Block 13 Attention Normalization (W) ( ~2K) 2048 2048 x 1 x 1 x 1 F32
162 blk.13.attn_output.weight Block 13 Attention Output (W) ( ~8M) 8388608 4096 x 2048 x 1 x 1 Q4_K
163 blk.13.attn_q.weight Block 13 Attention Query (W) ( ~8M) 8388608 2048 x 4096 x 1 x 1 IQ3_XXS
164 blk.13.attn_q_norm.weight Block 13 Attn_Q_Norm (W) ( 128) 128 128 x 1 x 1 x 1 F32
165 blk.13.attn_v.weight Block 13 Attention Value (W) ( ~1M) 1048576 2048 x 512 x 1 x 1 IQ3_S
166 blk.13.ffn_down_exps.weight Block 13 Ffn_Down_Exps (W) (~201M) 201326592 768 x 2048 x 128 x 1 IQ4_NL
167 blk.13.ffn_gate_exps.weight Block 13 Ffn_Gate_Exps (W) (~201M) 201326592 2048 x 768 x 128 x 1 IQ3_S
168 blk.13.ffn_gate_inp.weight Block 13 Expert-Routing Layer For The Feed-Forward Network In Mixture Of Expert Models (W) (~262K) 262144 2048 x 128 x 1 x 1 F32
169 blk.13.ffn_norm.weight Block 13 Feed-Forward Network Normalization (W) ( ~2K) 2048 2048 x 1 x 1 x 1 F32
170 blk.13.ffn_up_exps.weight Block 13 Ffn_Up_Exps (W) (~201M) 201326592 2048 x 768 x 128 x 1 IQ3_S
  • Total elements in blk.13: (~623M) 623120640
  • Percentage of total elements: 2.04%

Block 14 Tensor Group : ~623M Elements

T_ID Tensor Layer Name Human Friendly Tensor Layer Name Elements Shape Type
171 blk.14.attn_k.weight Block 14 Attention Key (W) ( ~1M) 1048576 2048 x 512 x 1 x 1 IQ3_XXS
172 blk.14.attn_k_norm.weight Block 14 Attn_K_Norm (W) ( 128) 128 128 x 1 x 1 x 1 F32
173 blk.14.attn_norm.weight Block 14 Attention Normalization (W) ( ~2K) 2048 2048 x 1 x 1 x 1 F32
174 blk.14.attn_output.weight Block 14 Attention Output (W) ( ~8M) 8388608 4096 x 2048 x 1 x 1 Q4_K
175 blk.14.attn_q.weight Block 14 Attention Query (W) ( ~8M) 8388608 2048 x 4096 x 1 x 1 IQ3_XXS
176 blk.14.attn_q_norm.weight Block 14 Attn_Q_Norm (W) ( 128) 128 128 x 1 x 1 x 1 F32
177 blk.14.attn_v.weight Block 14 Attention Value (W) ( ~1M) 1048576 2048 x 512 x 1 x 1 IQ3_S
178 blk.14.ffn_down_exps.weight Block 14 Ffn_Down_Exps (W) (~201M) 201326592 768 x 2048 x 128 x 1 IQ4_NL
179 blk.14.ffn_gate_exps.weight Block 14 Ffn_Gate_Exps (W) (~201M) 201326592 2048 x 768 x 128 x 1 IQ3_XXS
180 blk.14.ffn_gate_inp.weight Block 14 Expert-Routing Layer For The Feed-Forward Network In Mixture Of Expert Models (W) (~262K) 262144 2048 x 128 x 1 x 1 F32
181 blk.14.ffn_norm.weight Block 14 Feed-Forward Network Normalization (W) ( ~2K) 2048 2048 x 1 x 1 x 1 F32
182 blk.14.ffn_up_exps.weight Block 14 Ffn_Up_Exps (W) (~201M) 201326592 2048 x 768 x 128 x 1 IQ3_XXS
  • Total elements in blk.14: (~623M) 623120640
  • Percentage of total elements: 2.04%

Block 15 Tensor Group : ~623M Elements

T_ID Tensor Layer Name Human Friendly Tensor Layer Name Elements Shape Type
183 blk.15.attn_k.weight Block 15 Attention Key (W) ( ~1M) 1048576 2048 x 512 x 1 x 1 IQ3_XXS
184 blk.15.attn_k_norm.weight Block 15 Attn_K_Norm (W) ( 128) 128 128 x 1 x 1 x 1 F32
185 blk.15.attn_norm.weight Block 15 Attention Normalization (W) ( ~2K) 2048 2048 x 1 x 1 x 1 F32
186 blk.15.attn_output.weight Block 15 Attention Output (W) ( ~8M) 8388608 4096 x 2048 x 1 x 1 Q4_K
187 blk.15.attn_q.weight Block 15 Attention Query (W) ( ~8M) 8388608 2048 x 4096 x 1 x 1 IQ3_XXS
188 blk.15.attn_q_norm.weight Block 15 Attn_Q_Norm (W) ( 128) 128 128 x 1 x 1 x 1 F32
189 blk.15.attn_v.weight Block 15 Attention Value (W) ( ~1M) 1048576 2048 x 512 x 1 x 1 IQ3_S
190 blk.15.ffn_down_exps.weight Block 15 Ffn_Down_Exps (W) (~201M) 201326592 768 x 2048 x 128 x 1 IQ4_NL
191 blk.15.ffn_gate_exps.weight Block 15 Ffn_Gate_Exps (W) (~201M) 201326592 2048 x 768 x 128 x 1 IQ3_S
192 blk.15.ffn_gate_inp.weight Block 15 Expert-Routing Layer For The Feed-Forward Network In Mixture Of Expert Models (W) (~262K) 262144 2048 x 128 x 1 x 1 F32
193 blk.15.ffn_norm.weight Block 15 Feed-Forward Network Normalization (W) ( ~2K) 2048 2048 x 1 x 1 x 1 F32
194 blk.15.ffn_up_exps.weight Block 15 Ffn_Up_Exps (W) (~201M) 201326592 2048 x 768 x 128 x 1 IQ3_S
  • Total elements in blk.15: (~623M) 623120640
  • Percentage of total elements: 2.04%

Block 16 Tensor Group : ~623M Elements

T_ID Tensor Layer Name Human Friendly Tensor Layer Name Elements Shape Type
195 blk.16.attn_k.weight Block 16 Attention Key (W) ( ~1M) 1048576 2048 x 512 x 1 x 1 IQ3_XXS
196 blk.16.attn_k_norm.weight Block 16 Attn_K_Norm (W) ( 128) 128 128 x 1 x 1 x 1 F32
197 blk.16.attn_norm.weight Block 16 Attention Normalization (W) ( ~2K) 2048 2048 x 1 x 1 x 1 F32
198 blk.16.attn_output.weight Block 16 Attention Output (W) ( ~8M) 8388608 4096 x 2048 x 1 x 1 Q4_K
199 blk.16.attn_q.weight Block 16 Attention Query (W) ( ~8M) 8388608 2048 x 4096 x 1 x 1 IQ3_XXS
200 blk.16.attn_q_norm.weight Block 16 Attn_Q_Norm (W) ( 128) 128 128 x 1 x 1 x 1 F32
201 blk.16.attn_v.weight Block 16 Attention Value (W) ( ~1M) 1048576 2048 x 512 x 1 x 1 IQ3_S
202 blk.16.ffn_down_exps.weight Block 16 Ffn_Down_Exps (W) (~201M) 201326592 768 x 2048 x 128 x 1 IQ4_NL
203 blk.16.ffn_gate_exps.weight Block 16 Ffn_Gate_Exps (W) (~201M) 201326592 2048 x 768 x 128 x 1 IQ3_XXS
204 blk.16.ffn_gate_inp.weight Block 16 Expert-Routing Layer For The Feed-Forward Network In Mixture Of Expert Models (W) (~262K) 262144 2048 x 128 x 1 x 1 F32
205 blk.16.ffn_norm.weight Block 16 Feed-Forward Network Normalization (W) ( ~2K) 2048 2048 x 1 x 1 x 1 F32
206 blk.16.ffn_up_exps.weight Block 16 Ffn_Up_Exps (W) (~201M) 201326592 2048 x 768 x 128 x 1 IQ3_XXS
  • Total elements in blk.16: (~623M) 623120640
  • Percentage of total elements: 2.04%

Block 17 Tensor Group : ~623M Elements

T_ID Tensor Layer Name Human Friendly Tensor Layer Name Elements Shape Type
207 blk.17.attn_k.weight Block 17 Attention Key (W) ( ~1M) 1048576 2048 x 512 x 1 x 1 IQ3_XXS
208 blk.17.attn_k_norm.weight Block 17 Attn_K_Norm (W) ( 128) 128 128 x 1 x 1 x 1 F32
209 blk.17.attn_norm.weight Block 17 Attention Normalization (W) ( ~2K) 2048 2048 x 1 x 1 x 1 F32
210 blk.17.attn_output.weight Block 17 Attention Output (W) ( ~8M) 8388608 4096 x 2048 x 1 x 1 Q4_K
211 blk.17.attn_q.weight Block 17 Attention Query (W) ( ~8M) 8388608 2048 x 4096 x 1 x 1 IQ3_XXS
212 blk.17.attn_q_norm.weight Block 17 Attn_Q_Norm (W) ( 128) 128 128 x 1 x 1 x 1 F32
213 blk.17.attn_v.weight Block 17 Attention Value (W) ( ~1M) 1048576 2048 x 512 x 1 x 1 IQ3_S
214 blk.17.ffn_down_exps.weight Block 17 Ffn_Down_Exps (W) (~201M) 201326592 768 x 2048 x 128 x 1 IQ4_NL
215 blk.17.ffn_gate_exps.weight Block 17 Ffn_Gate_Exps (W) (~201M) 201326592 2048 x 768 x 128 x 1 IQ3_XXS
216 blk.17.ffn_gate_inp.weight Block 17 Expert-Routing Layer For The Feed-Forward Network In Mixture Of Expert Models (W) (~262K) 262144 2048 x 128 x 1 x 1 F32
217 blk.17.ffn_norm.weight Block 17 Feed-Forward Network Normalization (W) ( ~2K) 2048 2048 x 1 x 1 x 1 F32
218 blk.17.ffn_up_exps.weight Block 17 Ffn_Up_Exps (W) (~201M) 201326592 2048 x 768 x 128 x 1 IQ3_XXS
  • Total elements in blk.17: (~623M) 623120640
  • Percentage of total elements: 2.04%

Block 18 Tensor Group : ~623M Elements

T_ID Tensor Layer Name Human Friendly Tensor Layer Name Elements Shape Type
219 blk.18.attn_k.weight Block 18 Attention Key (W) ( ~1M) 1048576 2048 x 512 x 1 x 1 IQ3_XXS
220 blk.18.attn_k_norm.weight Block 18 Attn_K_Norm (W) ( 128) 128 128 x 1 x 1 x 1 F32
221 blk.18.attn_norm.weight Block 18 Attention Normalization (W) ( ~2K) 2048 2048 x 1 x 1 x 1 F32
222 blk.18.attn_output.weight Block 18 Attention Output (W) ( ~8M) 8388608 4096 x 2048 x 1 x 1 Q4_K
223 blk.18.attn_q.weight Block 18 Attention Query (W) ( ~8M) 8388608 2048 x 4096 x 1 x 1 IQ3_XXS
224 blk.18.attn_q_norm.weight Block 18 Attn_Q_Norm (W) ( 128) 128 128 x 1 x 1 x 1 F32
225 blk.18.attn_v.weight Block 18 Attention Value (W) ( ~1M) 1048576 2048 x 512 x 1 x 1 IQ3_S
226 blk.18.ffn_down_exps.weight Block 18 Ffn_Down_Exps (W) (~201M) 201326592 768 x 2048 x 128 x 1 IQ4_NL
227 blk.18.ffn_gate_exps.weight Block 18 Ffn_Gate_Exps (W) (~201M) 201326592 2048 x 768 x 128 x 1 IQ3_XXS
228 blk.18.ffn_gate_inp.weight Block 18 Expert-Routing Layer For The Feed-Forward Network In Mixture Of Expert Models (W) (~262K) 262144 2048 x 128 x 1 x 1 F32
229 blk.18.ffn_norm.weight Block 18 Feed-Forward Network Normalization (W) ( ~2K) 2048 2048 x 1 x 1 x 1 F32
230 blk.18.ffn_up_exps.weight Block 18 Ffn_Up_Exps (W) (~201M) 201326592 2048 x 768 x 128 x 1 IQ3_XXS
  • Total elements in blk.18: (~623M) 623120640
  • Percentage of total elements: 2.04%

Block 19 Tensor Group : ~623M Elements

T_ID Tensor Layer Name Human Friendly Tensor Layer Name Elements Shape Type
231 blk.19.attn_k.weight Block 19 Attention Key (W) ( ~1M) 1048576 2048 x 512 x 1 x 1 IQ3_XXS
232 blk.19.attn_k_norm.weight Block 19 Attn_K_Norm (W) ( 128) 128 128 x 1 x 1 x 1 F32
233 blk.19.attn_norm.weight Block 19 Attention Normalization (W) ( ~2K) 2048 2048 x 1 x 1 x 1 F32
234 blk.19.attn_output.weight Block 19 Attention Output (W) ( ~8M) 8388608 4096 x 2048 x 1 x 1 Q4_K
235 blk.19.attn_q.weight Block 19 Attention Query (W) ( ~8M) 8388608 2048 x 4096 x 1 x 1 IQ3_XXS
236 blk.19.attn_q_norm.weight Block 19 Attn_Q_Norm (W) ( 128) 128 128 x 1 x 1 x 1 F32
237 blk.19.attn_v.weight Block 19 Attention Value (W) ( ~1M) 1048576 2048 x 512 x 1 x 1 IQ3_S
238 blk.19.ffn_down_exps.weight Block 19 Ffn_Down_Exps (W) (~201M) 201326592 768 x 2048 x 128 x 1 IQ4_NL
239 blk.19.ffn_gate_exps.weight Block 19 Ffn_Gate_Exps (W) (~201M) 201326592 2048 x 768 x 128 x 1 IQ3_XXS
240 blk.19.ffn_gate_inp.weight Block 19 Expert-Routing Layer For The Feed-Forward Network In Mixture Of Expert Models (W) (~262K) 262144 2048 x 128 x 1 x 1 F32
241 blk.19.ffn_norm.weight Block 19 Feed-Forward Network Normalization (W) ( ~2K) 2048 2048 x 1 x 1 x 1 F32
242 blk.19.ffn_up_exps.weight Block 19 Ffn_Up_Exps (W) (~201M) 201326592 2048 x 768 x 128 x 1 IQ3_XXS
  • Total elements in blk.19: (~623M) 623120640
  • Percentage of total elements: 2.04%

Block 20 Tensor Group : ~623M Elements

T_ID Tensor Layer Name Human Friendly Tensor Layer Name Elements Shape Type
243 blk.20.attn_k.weight Block 20 Attention Key (W) ( ~1M) 1048576 2048 x 512 x 1 x 1 IQ3_XXS
244 blk.20.attn_k_norm.weight Block 20 Attn_K_Norm (W) ( 128) 128 128 x 1 x 1 x 1 F32
245 blk.20.attn_norm.weight Block 20 Attention Normalization (W) ( ~2K) 2048 2048 x 1 x 1 x 1 F32
246 blk.20.attn_output.weight Block 20 Attention Output (W) ( ~8M) 8388608 4096 x 2048 x 1 x 1 Q4_K
247 blk.20.attn_q.weight Block 20 Attention Query (W) ( ~8M) 8388608 2048 x 4096 x 1 x 1 IQ3_XXS
248 blk.20.attn_q_norm.weight Block 20 Attn_Q_Norm (W) ( 128) 128 128 x 1 x 1 x 1 F32
249 blk.20.attn_v.weight Block 20 Attention Value (W) ( ~1M) 1048576 2048 x 512 x 1 x 1 IQ3_S
250 blk.20.ffn_down_exps.weight Block 20 Ffn_Down_Exps (W) (~201M) 201326592 768 x 2048 x 128 x 1 IQ4_NL
251 blk.20.ffn_gate_exps.weight Block 20 Ffn_Gate_Exps (W) (~201M) 201326592 2048 x 768 x 128 x 1 IQ3_XXS
252 blk.20.ffn_gate_inp.weight Block 20 Expert-Routing Layer For The Feed-Forward Network In Mixture Of Expert Models (W) (~262K) 262144 2048 x 128 x 1 x 1 F32
253 blk.20.ffn_norm.weight Block 20 Feed-Forward Network Normalization (W) ( ~2K) 2048 2048 x 1 x 1 x 1 F32
254 blk.20.ffn_up_exps.weight Block 20 Ffn_Up_Exps (W) (~201M) 201326592 2048 x 768 x 128 x 1 IQ3_XXS
  • Total elements in blk.20: (~623M) 623120640
  • Percentage of total elements: 2.04%

Block 21 Tensor Group : ~623M Elements

T_ID Tensor Layer Name Human Friendly Tensor Layer Name Elements Shape Type
255 blk.21.attn_k.weight Block 21 Attention Key (W) ( ~1M) 1048576 2048 x 512 x 1 x 1 IQ3_XXS
256 blk.21.attn_k_norm.weight Block 21 Attn_K_Norm (W) ( 128) 128 128 x 1 x 1 x 1 F32
257 blk.21.attn_norm.weight Block 21 Attention Normalization (W) ( ~2K) 2048 2048 x 1 x 1 x 1 F32
258 blk.21.attn_output.weight Block 21 Attention Output (W) ( ~8M) 8388608 4096 x 2048 x 1 x 1 Q4_K
259 blk.21.attn_q.weight Block 21 Attention Query (W) ( ~8M) 8388608 2048 x 4096 x 1 x 1 IQ3_XXS
260 blk.21.attn_q_norm.weight Block 21 Attn_Q_Norm (W) ( 128) 128 128 x 1 x 1 x 1 F32
261 blk.21.attn_v.weight Block 21 Attention Value (W) ( ~1M) 1048576 2048 x 512 x 1 x 1 IQ3_S
262 blk.21.ffn_down_exps.weight Block 21 Ffn_Down_Exps (W) (~201M) 201326592 768 x 2048 x 128 x 1 IQ4_NL
263 blk.21.ffn_gate_exps.weight Block 21 Ffn_Gate_Exps (W) (~201M) 201326592 2048 x 768 x 128 x 1 IQ3_XXS
264 blk.21.ffn_gate_inp.weight Block 21 Expert-Routing Layer For The Feed-Forward Network In Mixture Of Expert Models (W) (~262K) 262144 2048 x 128 x 1 x 1 F32
265 blk.21.ffn_norm.weight Block 21 Feed-Forward Network Normalization (W) ( ~2K) 2048 2048 x 1 x 1 x 1 F32
266 blk.21.ffn_up_exps.weight Block 21 Ffn_Up_Exps (W) (~201M) 201326592 2048 x 768 x 128 x 1 IQ3_XXS
  • Total elements in blk.21: (~623M) 623120640
  • Percentage of total elements: 2.04%

Block 22 Tensor Group : ~623M Elements

T_ID Tensor Layer Name Human Friendly Tensor Layer Name Elements Shape Type
267 blk.22.attn_k.weight Block 22 Attention Key (W) ( ~1M) 1048576 2048 x 512 x 1 x 1 IQ3_XXS
268 blk.22.attn_k_norm.weight Block 22 Attn_K_Norm (W) ( 128) 128 128 x 1 x 1 x 1 F32
269 blk.22.attn_norm.weight Block 22 Attention Normalization (W) ( ~2K) 2048 2048 x 1 x 1 x 1 F32
270 blk.22.attn_output.weight Block 22 Attention Output (W) ( ~8M) 8388608 4096 x 2048 x 1 x 1 Q4_K
271 blk.22.attn_q.weight Block 22 Attention Query (W) ( ~8M) 8388608 2048 x 4096 x 1 x 1 IQ3_XXS
272 blk.22.attn_q_norm.weight Block 22 Attn_Q_Norm (W) ( 128) 128 128 x 1 x 1 x 1 F32
273 blk.22.attn_v.weight Block 22 Attention Value (W) ( ~1M) 1048576 2048 x 512 x 1 x 1 IQ3_S
274 blk.22.ffn_down_exps.weight Block 22 Ffn_Down_Exps (W) (~201M) 201326592 768 x 2048 x 128 x 1 IQ4_NL
275 blk.22.ffn_gate_exps.weight Block 22 Ffn_Gate_Exps (W) (~201M) 201326592 2048 x 768 x 128 x 1 IQ3_XXS
276 blk.22.ffn_gate_inp.weight Block 22 Expert-Routing Layer For The Feed-Forward Network In Mixture Of Expert Models (W) (~262K) 262144 2048 x 128 x 1 x 1 F32
277 blk.22.ffn_norm.weight Block 22 Feed-Forward Network Normalization (W) ( ~2K) 2048 2048 x 1 x 1 x 1 F32
278 blk.22.ffn_up_exps.weight Block 22 Ffn_Up_Exps (W) (~201M) 201326592 2048 x 768 x 128 x 1 IQ3_XXS
  • Total elements in blk.22: (~623M) 623120640
  • Percentage of total elements: 2.04%

Block 23 Tensor Group : ~623M Elements

T_ID Tensor Layer Name Human Friendly Tensor Layer Name Elements Shape Type
279 blk.23.attn_k.weight Block 23 Attention Key (W) ( ~1M) 1048576 2048 x 512 x 1 x 1 IQ3_XXS
280 blk.23.attn_k_norm.weight Block 23 Attn_K_Norm (W) ( 128) 128 128 x 1 x 1 x 1 F32
281 blk.23.attn_norm.weight Block 23 Attention Normalization (W) ( ~2K) 2048 2048 x 1 x 1 x 1 F32
282 blk.23.attn_output.weight Block 23 Attention Output (W) ( ~8M) 8388608 4096 x 2048 x 1 x 1 Q4_K
283 blk.23.attn_q.weight Block 23 Attention Query (W) ( ~8M) 8388608 2048 x 4096 x 1 x 1 IQ3_XXS
284 blk.23.attn_q_norm.weight Block 23 Attn_Q_Norm (W) ( 128) 128 128 x 1 x 1 x 1 F32
285 blk.23.attn_v.weight Block 23 Attention Value (W) ( ~1M) 1048576 2048 x 512 x 1 x 1 IQ3_S
286 blk.23.ffn_down_exps.weight Block 23 Ffn_Down_Exps (W) (~201M) 201326592 768 x 2048 x 128 x 1 IQ4_NL
287 blk.23.ffn_gate_exps.weight Block 23 Ffn_Gate_Exps (W) (~201M) 201326592 2048 x 768 x 128 x 1 IQ3_XXS
288 blk.23.ffn_gate_inp.weight Block 23 Expert-Routing Layer For The Feed-Forward Network In Mixture Of Expert Models (W) (~262K) 262144 2048 x 128 x 1 x 1 F32
289 blk.23.ffn_norm.weight Block 23 Feed-Forward Network Normalization (W) ( ~2K) 2048 2048 x 1 x 1 x 1 F32
290 blk.23.ffn_up_exps.weight Block 23 Ffn_Up_Exps (W) (~201M) 201326592 2048 x 768 x 128 x 1 IQ3_XXS
  • Total elements in blk.23: (~623M) 623120640
  • Percentage of total elements: 2.04%

Block 24 Tensor Group : ~623M Elements

T_ID Tensor Layer Name Human Friendly Tensor Layer Name Elements Shape Type
291 blk.24.attn_k.weight Block 24 Attention Key (W) ( ~1M) 1048576 2048 x 512 x 1 x 1 IQ3_S
292 blk.24.attn_k_norm.weight Block 24 Attn_K_Norm (W) ( 128) 128 128 x 1 x 1 x 1 F32
293 blk.24.attn_norm.weight Block 24 Attention Normalization (W) ( ~2K) 2048 2048 x 1 x 1 x 1 F32
294 blk.24.attn_output.weight Block 24 Attention Output (W) ( ~8M) 8388608 4096 x 2048 x 1 x 1 Q4_K
295 blk.24.attn_q.weight Block 24 Attention Query (W) ( ~8M) 8388608 2048 x 4096 x 1 x 1 IQ3_S
296 blk.24.attn_q_norm.weight Block 24 Attn_Q_Norm (W) ( 128) 128 128 x 1 x 1 x 1 F32
297 blk.24.attn_v.weight Block 24 Attention Value (W) ( ~1M) 1048576 2048 x 512 x 1 x 1 IQ4_NL
298 blk.24.ffn_down_exps.weight Block 24 Ffn_Down_Exps (W) (~201M) 201326592 768 x 2048 x 128 x 1 IQ4_NL
299 blk.24.ffn_gate_exps.weight Block 24 Ffn_Gate_Exps (W) (~201M) 201326592 2048 x 768 x 128 x 1 IQ3_XXS
300 blk.24.ffn_gate_inp.weight Block 24 Expert-Routing Layer For The Feed-Forward Network In Mixture Of Expert Models (W) (~262K) 262144 2048 x 128 x 1 x 1 F32
301 blk.24.ffn_norm.weight Block 24 Feed-Forward Network Normalization (W) ( ~2K) 2048 2048 x 1 x 1 x 1 F32
302 blk.24.ffn_up_exps.weight Block 24 Ffn_Up_Exps (W) (~201M) 201326592 2048 x 768 x 128 x 1 IQ3_XXS
  • Total elements in blk.24: (~623M) 623120640
  • Percentage of total elements: 2.04%

Block 25 Tensor Group : ~623M Elements

T_ID Tensor Layer Name Human Friendly Tensor Layer Name Elements Shape Type
303 blk.25.attn_k.weight Block 25 Attention Key (W) ( ~1M) 1048576 2048 x 512 x 1 x 1 IQ3_S
304 blk.25.attn_k_norm.weight Block 25 Attn_K_Norm (W) ( 128) 128 128 x 1 x 1 x 1 F32
305 blk.25.attn_norm.weight Block 25 Attention Normalization (W) ( ~2K) 2048 2048 x 1 x 1 x 1 F32
306 blk.25.attn_output.weight Block 25 Attention Output (W) ( ~8M) 8388608 4096 x 2048 x 1 x 1 Q4_K
307 blk.25.attn_q.weight Block 25 Attention Query (W) ( ~8M) 8388608 2048 x 4096 x 1 x 1 IQ3_S
308 blk.25.attn_q_norm.weight Block 25 Attn_Q_Norm (W) ( 128) 128 128 x 1 x 1 x 1 F32
309 blk.25.attn_v.weight Block 25 Attention Value (W) ( ~1M) 1048576 2048 x 512 x 1 x 1 IQ4_NL
310 blk.25.ffn_down_exps.weight Block 25 Ffn_Down_Exps (W) (~201M) 201326592 768 x 2048 x 128 x 1 IQ4_NL
311 blk.25.ffn_gate_exps.weight Block 25 Ffn_Gate_Exps (W) (~201M) 201326592 2048 x 768 x 128 x 1 IQ3_S
312 blk.25.ffn_gate_inp.weight Block 25 Expert-Routing Layer For The Feed-Forward Network In Mixture Of Expert Models (W) (~262K) 262144 2048 x 128 x 1 x 1 F32
313 blk.25.ffn_norm.weight Block 25 Feed-Forward Network Normalization (W) ( ~2K) 2048 2048 x 1 x 1 x 1 F32
314 blk.25.ffn_up_exps.weight Block 25 Ffn_Up_Exps (W) (~201M) 201326592 2048 x 768 x 128 x 1 IQ3_S
  • Total elements in blk.25: (~623M) 623120640
  • Percentage of total elements: 2.04%

Block 26 Tensor Group : ~623M Elements

T_ID Tensor Layer Name Human Friendly Tensor Layer Name Elements Shape Type
315 blk.26.attn_k.weight Block 26 Attention Key (W) ( ~1M) 1048576 2048 x 512 x 1 x 1 IQ3_S
316 blk.26.attn_k_norm.weight Block 26 Attn_K_Norm (W) ( 128) 128 128 x 1 x 1 x 1 F32
317 blk.26.attn_norm.weight Block 26 Attention Normalization (W) ( ~2K) 2048 2048 x 1 x 1 x 1 F32
318 blk.26.attn_output.weight Block 26 Attention Output (W) ( ~8M) 8388608 4096 x 2048 x 1 x 1 Q4_K
319 blk.26.attn_q.weight Block 26 Attention Query (W) ( ~8M) 8388608 2048 x 4096 x 1 x 1 IQ3_S
320 blk.26.attn_q_norm.weight Block 26 Attn_Q_Norm (W) ( 128) 128 128 x 1 x 1 x 1 F32
321 blk.26.attn_v.weight Block 26 Attention Value (W) ( ~1M) 1048576 2048 x 512 x 1 x 1 IQ4_NL
322 blk.26.ffn_down_exps.weight Block 26 Ffn_Down_Exps (W) (~201M) 201326592 768 x 2048 x 128 x 1 IQ4_NL
323 blk.26.ffn_gate_exps.weight Block 26 Ffn_Gate_Exps (W) (~201M) 201326592 2048 x 768 x 128 x 1 IQ3_XXS
324 blk.26.ffn_gate_inp.weight Block 26 Expert-Routing Layer For The Feed-Forward Network In Mixture Of Expert Models (W) (~262K) 262144 2048 x 128 x 1 x 1 F32
325 blk.26.ffn_norm.weight Block 26 Feed-Forward Network Normalization (W) ( ~2K) 2048 2048 x 1 x 1 x 1 F32
326 blk.26.ffn_up_exps.weight Block 26 Ffn_Up_Exps (W) (~201M) 201326592 2048 x 768 x 128 x 1 IQ3_XXS
  • Total elements in blk.26: (~623M) 623120640
  • Percentage of total elements: 2.04%

Block 27 Tensor Group : ~623M Elements

T_ID Tensor Layer Name Human Friendly Tensor Layer Name Elements Shape Type
327 blk.27.attn_k.weight Block 27 Attention Key (W) ( ~1M) 1048576 2048 x 512 x 1 x 1 IQ3_S
328 blk.27.attn_k_norm.weight Block 27 Attn_K_Norm (W) ( 128) 128 128 x 1 x 1 x 1 F32
329 blk.27.attn_norm.weight Block 27 Attention Normalization (W) ( ~2K) 2048 2048 x 1 x 1 x 1 F32
330 blk.27.attn_output.weight Block 27 Attention Output (W) ( ~8M) 8388608 4096 x 2048 x 1 x 1 Q4_K
331 blk.27.attn_q.weight Block 27 Attention Query (W) ( ~8M) 8388608 2048 x 4096 x 1 x 1 IQ3_S
332 blk.27.attn_q_norm.weight Block 27 Attn_Q_Norm (W) ( 128) 128 128 x 1 x 1 x 1 F32
333 blk.27.attn_v.weight Block 27 Attention Value (W) ( ~1M) 1048576 2048 x 512 x 1 x 1 IQ4_NL
334 blk.27.ffn_down_exps.weight Block 27 Ffn_Down_Exps (W) (~201M) 201326592 768 x 2048 x 128 x 1 IQ4_NL
335 blk.27.ffn_gate_exps.weight Block 27 Ffn_Gate_Exps (W) (~201M) 201326592 2048 x 768 x 128 x 1 IQ3_S
336 blk.27.ffn_gate_inp.weight Block 27 Expert-Routing Layer For The Feed-Forward Network In Mixture Of Expert Models (W) (~262K) 262144 2048 x 128 x 1 x 1 F32
337 blk.27.ffn_norm.weight Block 27 Feed-Forward Network Normalization (W) ( ~2K) 2048 2048 x 1 x 1 x 1 F32
338 blk.27.ffn_up_exps.weight Block 27 Ffn_Up_Exps (W) (~201M) 201326592 2048 x 768 x 128 x 1 IQ3_S
  • Total elements in blk.27: (~623M) 623120640
  • Percentage of total elements: 2.04%

Block 28 Tensor Group : ~623M Elements

T_ID Tensor Layer Name Human Friendly Tensor Layer Name Elements Shape Type
339 blk.28.attn_k.weight Block 28 Attention Key (W) ( ~1M) 1048576 2048 x 512 x 1 x 1 IQ3_S
340 blk.28.attn_k_norm.weight Block 28 Attn_K_Norm (W) ( 128) 128 128 x 1 x 1 x 1 F32
341 blk.28.attn_norm.weight Block 28 Attention Normalization (W) ( ~2K) 2048 2048 x 1 x 1 x 1 F32
342 blk.28.attn_output.weight Block 28 Attention Output (W) ( ~8M) 8388608 4096 x 2048 x 1 x 1 Q4_K
343 blk.28.attn_q.weight Block 28 Attention Query (W) ( ~8M) 8388608 2048 x 4096 x 1 x 1 IQ3_S
344 blk.28.attn_q_norm.weight Block 28 Attn_Q_Norm (W) ( 128) 128 128 x 1 x 1 x 1 F32
345 blk.28.attn_v.weight Block 28 Attention Value (W) ( ~1M) 1048576 2048 x 512 x 1 x 1 IQ4_NL
346 blk.28.ffn_down_exps.weight Block 28 Ffn_Down_Exps (W) (~201M) 201326592 768 x 2048 x 128 x 1 IQ4_NL
347 blk.28.ffn_gate_exps.weight Block 28 Ffn_Gate_Exps (W) (~201M) 201326592 2048 x 768 x 128 x 1 IQ3_S
348 blk.28.ffn_gate_inp.weight Block 28 Expert-Routing Layer For The Feed-Forward Network In Mixture Of Expert Models (W) (~262K) 262144 2048 x 128 x 1 x 1 F32
349 blk.28.ffn_norm.weight Block 28 Feed-Forward Network Normalization (W) ( ~2K) 2048 2048 x 1 x 1 x 1 F32
350 blk.28.ffn_up_exps.weight Block 28 Ffn_Up_Exps (W) (~201M) 201326592 2048 x 768 x 128 x 1 IQ3_S
  • Total elements in blk.28: (~623M) 623120640
  • Percentage of total elements: 2.04%

Block 29 Tensor Group : ~623M Elements

T_ID Tensor Layer Name Human Friendly Tensor Layer Name Elements Shape Type
351 blk.29.attn_k.weight Block 29 Attention Key (W) ( ~1M) 1048576 2048 x 512 x 1 x 1 IQ3_S
352 blk.29.attn_k_norm.weight Block 29 Attn_K_Norm (W) ( 128) 128 128 x 1 x 1 x 1 F32
353 blk.29.attn_norm.weight Block 29 Attention Normalization (W) ( ~2K) 2048 2048 x 1 x 1 x 1 F32
354 blk.29.attn_output.weight Block 29 Attention Output (W) ( ~8M) 8388608 4096 x 2048 x 1 x 1 Q4_K
355 blk.29.attn_q.weight Block 29 Attention Query (W) ( ~8M) 8388608 2048 x 4096 x 1 x 1 IQ3_S
356 blk.29.attn_q_norm.weight Block 29 Attn_Q_Norm (W) ( 128) 128 128 x 1 x 1 x 1 F32
357 blk.29.attn_v.weight Block 29 Attention Value (W) ( ~1M) 1048576 2048 x 512 x 1 x 1 IQ4_NL
358 blk.29.ffn_down_exps.weight Block 29 Ffn_Down_Exps (W) (~201M) 201326592 768 x 2048 x 128 x 1 IQ4_NL
359 blk.29.ffn_gate_exps.weight Block 29 Ffn_Gate_Exps (W) (~201M) 201326592 2048 x 768 x 128 x 1 IQ3_S
360 blk.29.ffn_gate_inp.weight Block 29 Expert-Routing Layer For The Feed-Forward Network In Mixture Of Expert Models (W) (~262K) 262144 2048 x 128 x 1 x 1 F32
361 blk.29.ffn_norm.weight Block 29 Feed-Forward Network Normalization (W) ( ~2K) 2048 2048 x 1 x 1 x 1 F32
362 blk.29.ffn_up_exps.weight Block 29 Ffn_Up_Exps (W) (~201M) 201326592 2048 x 768 x 128 x 1 IQ3_S
  • Total elements in blk.29: (~623M) 623120640
  • Percentage of total elements: 2.04%

Block 30 Tensor Group : ~623M Elements

T_ID Tensor Layer Name Human Friendly Tensor Layer Name Elements Shape Type
363 blk.30.attn_k.weight Block 30 Attention Key (W) ( ~1M) 1048576 2048 x 512 x 1 x 1 IQ3_S
364 blk.30.attn_k_norm.weight Block 30 Attn_K_Norm (W) ( 128) 128 128 x 1 x 1 x 1 F32
365 blk.30.attn_norm.weight Block 30 Attention Normalization (W) ( ~2K) 2048 2048 x 1 x 1 x 1 F32
366 blk.30.attn_output.weight Block 30 Attention Output (W) ( ~8M) 8388608 4096 x 2048 x 1 x 1 Q4_K
367 blk.30.attn_q.weight Block 30 Attention Query (W) ( ~8M) 8388608 2048 x 4096 x 1 x 1 IQ3_S
368 blk.30.attn_q_norm.weight Block 30 Attn_Q_Norm (W) ( 128) 128 128 x 1 x 1 x 1 F32
369 blk.30.attn_v.weight Block 30 Attention Value (W) ( ~1M) 1048576 2048 x 512 x 1 x 1 IQ4_NL
370 blk.30.ffn_down_exps.weight Block 30 Ffn_Down_Exps (W) (~201M) 201326592 768 x 2048 x 128 x 1 IQ4_NL
371 blk.30.ffn_gate_exps.weight Block 30 Ffn_Gate_Exps (W) (~201M) 201326592 2048 x 768 x 128 x 1 IQ3_S
372 blk.30.ffn_gate_inp.weight Block 30 Expert-Routing Layer For The Feed-Forward Network In Mixture Of Expert Models (W) (~262K) 262144 2048 x 128 x 1 x 1 F32
373 blk.30.ffn_norm.weight Block 30 Feed-Forward Network Normalization (W) ( ~2K) 2048 2048 x 1 x 1 x 1 F32
374 blk.30.ffn_up_exps.weight Block 30 Ffn_Up_Exps (W) (~201M) 201326592 2048 x 768 x 128 x 1 IQ3_S
  • Total elements in blk.30: (~623M) 623120640
  • Percentage of total elements: 2.04%

Block 31 Tensor Group : ~623M Elements

T_ID Tensor Layer Name Human Friendly Tensor Layer Name Elements Shape Type
375 blk.31.attn_k.weight Block 31 Attention Key (W) ( ~1M) 1048576 2048 x 512 x 1 x 1 IQ3_S
376 blk.31.attn_k_norm.weight Block 31 Attn_K_Norm (W) ( 128) 128 128 x 1 x 1 x 1 F32
377 blk.31.attn_norm.weight Block 31 Attention Normalization (W) ( ~2K) 2048 2048 x 1 x 1 x 1 F32
378 blk.31.attn_output.weight Block 31 Attention Output (W) ( ~8M) 8388608 4096 x 2048 x 1 x 1 Q4_K
379 blk.31.attn_q.weight Block 31 Attention Query (W) ( ~8M) 8388608 2048 x 4096 x 1 x 1 IQ3_S
380 blk.31.attn_q_norm.weight Block 31 Attn_Q_Norm (W) ( 128) 128 128 x 1 x 1 x 1 F32
381 blk.31.attn_v.weight Block 31 Attention Value (W) ( ~1M) 1048576 2048 x 512 x 1 x 1 IQ4_NL
382 blk.31.ffn_down_exps.weight Block 31 Ffn_Down_Exps (W) (~201M) 201326592 768 x 2048 x 128 x 1 IQ4_NL
383 blk.31.ffn_gate_exps.weight Block 31 Ffn_Gate_Exps (W) (~201M) 201326592 2048 x 768 x 128 x 1 IQ3_S
384 blk.31.ffn_gate_inp.weight Block 31 Expert-Routing Layer For The Feed-Forward Network In Mixture Of Expert Models (W) (~262K) 262144 2048 x 128 x 1 x 1 F32
385 blk.31.ffn_norm.weight Block 31 Feed-Forward Network Normalization (W) ( ~2K) 2048 2048 x 1 x 1 x 1 F32
386 blk.31.ffn_up_exps.weight Block 31 Ffn_Up_Exps (W) (~201M) 201326592 2048 x 768 x 128 x 1 IQ3_S
  • Total elements in blk.31: (~623M) 623120640
  • Percentage of total elements: 2.04%

Block 32 Tensor Group : ~623M Elements

T_ID Tensor Layer Name Human Friendly Tensor Layer Name Elements Shape Type
387 blk.32.attn_k.weight Block 32 Attention Key (W) ( ~1M) 1048576 2048 x 512 x 1 x 1 IQ3_S
388 blk.32.attn_k_norm.weight Block 32 Attn_K_Norm (W) ( 128) 128 128 x 1 x 1 x 1 F32
389 blk.32.attn_norm.weight Block 32 Attention Normalization (W) ( ~2K) 2048 2048 x 1 x 1 x 1 F32
390 blk.32.attn_output.weight Block 32 Attention Output (W) ( ~8M) 8388608 4096 x 2048 x 1 x 1 Q4_K
391 blk.32.attn_q.weight Block 32 Attention Query (W) ( ~8M) 8388608 2048 x 4096 x 1 x 1 IQ3_S
392 blk.32.attn_q_norm.weight Block 32 Attn_Q_Norm (W) ( 128) 128 128 x 1 x 1 x 1 F32
393 blk.32.attn_v.weight Block 32 Attention Value (W) ( ~1M) 1048576 2048 x 512 x 1 x 1 IQ4_NL
394 blk.32.ffn_down_exps.weight Block 32 Ffn_Down_Exps (W) (~201M) 201326592 768 x 2048 x 128 x 1 IQ4_NL
395 blk.32.ffn_gate_exps.weight Block 32 Ffn_Gate_Exps (W) (~201M) 201326592 2048 x 768 x 128 x 1 IQ3_S
396 blk.32.ffn_gate_inp.weight Block 32 Expert-Routing Layer For The Feed-Forward Network In Mixture Of Expert Models (W) (~262K) 262144 2048 x 128 x 1 x 1 F32
397 blk.32.ffn_norm.weight Block 32 Feed-Forward Network Normalization (W) ( ~2K) 2048 2048 x 1 x 1 x 1 F32
398 blk.32.ffn_up_exps.weight Block 32 Ffn_Up_Exps (W) (~201M) 201326592 2048 x 768 x 128 x 1 IQ3_S
  • Total elements in blk.32: (~623M) 623120640
  • Percentage of total elements: 2.04%

Block 33 Tensor Group : ~623M Elements

T_ID Tensor Layer Name Human Friendly Tensor Layer Name Elements Shape Type
399 blk.33.attn_k.weight Block 33 Attention Key (W) ( ~1M) 1048576 2048 x 512 x 1 x 1 IQ3_S
400 blk.33.attn_k_norm.weight Block 33 Attn_K_Norm (W) ( 128) 128 128 x 1 x 1 x 1 F32
401 blk.33.attn_norm.weight Block 33 Attention Normalization (W) ( ~2K) 2048 2048 x 1 x 1 x 1 F32
402 blk.33.attn_output.weight Block 33 Attention Output (W) ( ~8M) 8388608 4096 x 2048 x 1 x 1 Q4_K
403 blk.33.attn_q.weight Block 33 Attention Query (W) ( ~8M) 8388608 2048 x 4096 x 1 x 1 IQ3_S
404 blk.33.attn_q_norm.weight Block 33 Attn_Q_Norm (W) ( 128) 128 128 x 1 x 1 x 1 F32
405 blk.33.attn_v.weight Block 33 Attention Value (W) ( ~1M) 1048576 2048 x 512 x 1 x 1 IQ4_NL
406 blk.33.ffn_down_exps.weight Block 33 Ffn_Down_Exps (W) (~201M) 201326592 768 x 2048 x 128 x 1 IQ4_NL
407 blk.33.ffn_gate_exps.weight Block 33 Ffn_Gate_Exps (W) (~201M) 201326592 2048 x 768 x 128 x 1 IQ3_S
408 blk.33.ffn_gate_inp.weight Block 33 Expert-Routing Layer For The Feed-Forward Network In Mixture Of Expert Models (W) (~262K) 262144 2048 x 128 x 1 x 1 F32
409 blk.33.ffn_norm.weight Block 33 Feed-Forward Network Normalization (W) ( ~2K) 2048 2048 x 1 x 1 x 1 F32
410 blk.33.ffn_up_exps.weight Block 33 Ffn_Up_Exps (W) (~201M) 201326592 2048 x 768 x 128 x 1 IQ3_S
  • Total elements in blk.33: (~623M) 623120640
  • Percentage of total elements: 2.04%

Block 34 Tensor Group : ~623M Elements

T_ID Tensor Layer Name Human Friendly Tensor Layer Name Elements Shape Type
411 blk.34.attn_k.weight Block 34 Attention Key (W) ( ~1M) 1048576 2048 x 512 x 1 x 1 IQ3_S
412 blk.34.attn_k_norm.weight Block 34 Attn_K_Norm (W) ( 128) 128 128 x 1 x 1 x 1 F32
413 blk.34.attn_norm.weight Block 34 Attention Normalization (W) ( ~2K) 2048 2048 x 1 x 1 x 1 F32
414 blk.34.attn_output.weight Block 34 Attention Output (W) ( ~8M) 8388608 4096 x 2048 x 1 x 1 Q4_K
415 blk.34.attn_q.weight Block 34 Attention Query (W) ( ~8M) 8388608 2048 x 4096 x 1 x 1 IQ3_S
416 blk.34.attn_q_norm.weight Block 34 Attn_Q_Norm (W) ( 128) 128 128 x 1 x 1 x 1 F32
417 blk.34.attn_v.weight Block 34 Attention Value (W) ( ~1M) 1048576 2048 x 512 x 1 x 1 IQ4_NL
418 blk.34.ffn_down_exps.weight Block 34 Ffn_Down_Exps (W) (~201M) 201326592 768 x 2048 x 128 x 1 IQ4_NL
419 blk.34.ffn_gate_exps.weight Block 34 Ffn_Gate_Exps (W) (~201M) 201326592 2048 x 768 x 128 x 1 IQ3_S
420 blk.34.ffn_gate_inp.weight Block 34 Expert-Routing Layer For The Feed-Forward Network In Mixture Of Expert Models (W) (~262K) 262144 2048 x 128 x 1 x 1 F32
421 blk.34.ffn_norm.weight Block 34 Feed-Forward Network Normalization (W) ( ~2K) 2048 2048 x 1 x 1 x 1 F32
422 blk.34.ffn_up_exps.weight Block 34 Ffn_Up_Exps (W) (~201M) 201326592 2048 x 768 x 128 x 1 IQ3_S
  • Total elements in blk.34: (~623M) 623120640
  • Percentage of total elements: 2.04%

Block 35 Tensor Group : ~623M Elements

T_ID Tensor Layer Name Human Friendly Tensor Layer Name Elements Shape Type
423 blk.35.attn_k.weight Block 35 Attention Key (W) ( ~1M) 1048576 2048 x 512 x 1 x 1 IQ3_S
424 blk.35.attn_k_norm.weight Block 35 Attn_K_Norm (W) ( 128) 128 128 x 1 x 1 x 1 F32
425 blk.35.attn_norm.weight Block 35 Attention Normalization (W) ( ~2K) 2048 2048 x 1 x 1 x 1 F32
426 blk.35.attn_output.weight Block 35 Attention Output (W) ( ~8M) 8388608 4096 x 2048 x 1 x 1 Q4_K
427 blk.35.attn_q.weight Block 35 Attention Query (W) ( ~8M) 8388608 2048 x 4096 x 1 x 1 IQ3_S
428 blk.35.attn_q_norm.weight Block 35 Attn_Q_Norm (W) ( 128) 128 128 x 1 x 1 x 1 F32
429 blk.35.attn_v.weight Block 35 Attention Value (W) ( ~1M) 1048576 2048 x 512 x 1 x 1 IQ4_NL
430 blk.35.ffn_down_exps.weight Block 35 Ffn_Down_Exps (W) (~201M) 201326592 768 x 2048 x 128 x 1 IQ4_NL
431 blk.35.ffn_gate_exps.weight Block 35 Ffn_Gate_Exps (W) (~201M) 201326592 2048 x 768 x 128 x 1 IQ3_S
432 blk.35.ffn_gate_inp.weight Block 35 Expert-Routing Layer For The Feed-Forward Network In Mixture Of Expert Models (W) (~262K) 262144 2048 x 128 x 1 x 1 F32
433 blk.35.ffn_norm.weight Block 35 Feed-Forward Network Normalization (W) ( ~2K) 2048 2048 x 1 x 1 x 1 F32
434 blk.35.ffn_up_exps.weight Block 35 Ffn_Up_Exps (W) (~201M) 201326592 2048 x 768 x 128 x 1 IQ3_S
  • Total elements in blk.35: (~623M) 623120640
  • Percentage of total elements: 2.04%

Block 36 Tensor Group : ~623M Elements

T_ID Tensor Layer Name Human Friendly Tensor Layer Name Elements Shape Type
435 blk.36.attn_k.weight Block 36 Attention Key (W) ( ~1M) 1048576 2048 x 512 x 1 x 1 IQ3_S
436 blk.36.attn_k_norm.weight Block 36 Attn_K_Norm (W) ( 128) 128 128 x 1 x 1 x 1 F32
437 blk.36.attn_norm.weight Block 36 Attention Normalization (W) ( ~2K) 2048 2048 x 1 x 1 x 1 F32
438 blk.36.attn_output.weight Block 36 Attention Output (W) ( ~8M) 8388608 4096 x 2048 x 1 x 1 Q4_K
439 blk.36.attn_q.weight Block 36 Attention Query (W) ( ~8M) 8388608 2048 x 4096 x 1 x 1 IQ3_S
440 blk.36.attn_q_norm.weight Block 36 Attn_Q_Norm (W) ( 128) 128 128 x 1 x 1 x 1 F32
441 blk.36.attn_v.weight Block 36 Attention Value (W) ( ~1M) 1048576 2048 x 512 x 1 x 1 IQ4_NL
442 blk.36.ffn_down_exps.weight Block 36 Ffn_Down_Exps (W) (~201M) 201326592 768 x 2048 x 128 x 1 IQ4_NL
443 blk.36.ffn_gate_exps.weight Block 36 Ffn_Gate_Exps (W) (~201M) 201326592 2048 x 768 x 128 x 1 IQ3_S
444 blk.36.ffn_gate_inp.weight Block 36 Expert-Routing Layer For The Feed-Forward Network In Mixture Of Expert Models (W) (~262K) 262144 2048 x 128 x 1 x 1 F32
445 blk.36.ffn_norm.weight Block 36 Feed-Forward Network Normalization (W) ( ~2K) 2048 2048 x 1 x 1 x 1 F32
446 blk.36.ffn_up_exps.weight Block 36 Ffn_Up_Exps (W) (~201M) 201326592 2048 x 768 x 128 x 1 IQ3_S
  • Total elements in blk.36: (~623M) 623120640
  • Percentage of total elements: 2.04%

Block 37 Tensor Group : ~623M Elements

T_ID Tensor Layer Name Human Friendly Tensor Layer Name Elements Shape Type
447 blk.37.attn_k.weight Block 37 Attention Key (W) ( ~1M) 1048576 2048 x 512 x 1 x 1 IQ3_S
448 blk.37.attn_k_norm.weight Block 37 Attn_K_Norm (W) ( 128) 128 128 x 1 x 1 x 1 F32
449 blk.37.attn_norm.weight Block 37 Attention Normalization (W) ( ~2K) 2048 2048 x 1 x 1 x 1 F32
450 blk.37.attn_output.weight Block 37 Attention Output (W) ( ~8M) 8388608 4096 x 2048 x 1 x 1 Q4_K
451 blk.37.attn_q.weight Block 37 Attention Query (W) ( ~8M) 8388608 2048 x 4096 x 1 x 1 IQ3_S
452 blk.37.attn_q_norm.weight Block 37 Attn_Q_Norm (W) ( 128) 128 128 x 1 x 1 x 1 F32
453 blk.37.attn_v.weight Block 37 Attention Value (W) ( ~1M) 1048576 2048 x 512 x 1 x 1 IQ4_NL
454 blk.37.ffn_down_exps.weight Block 37 Ffn_Down_Exps (W) (~201M) 201326592 768 x 2048 x 128 x 1 IQ4_NL
455 blk.37.ffn_gate_exps.weight Block 37 Ffn_Gate_Exps (W) (~201M) 201326592 2048 x 768 x 128 x 1 IQ3_S
456 blk.37.ffn_gate_inp.weight Block 37 Expert-Routing Layer For The Feed-Forward Network In Mixture Of Expert Models (W) (~262K) 262144 2048 x 128 x 1 x 1 F32
457 blk.37.ffn_norm.weight Block 37 Feed-Forward Network Normalization (W) ( ~2K) 2048 2048 x 1 x 1 x 1 F32
458 blk.37.ffn_up_exps.weight Block 37 Ffn_Up_Exps (W) (~201M) 201326592 2048 x 768 x 128 x 1 IQ3_S
  • Total elements in blk.37: (~623M) 623120640
  • Percentage of total elements: 2.04%

Block 38 Tensor Group : ~623M Elements

T_ID Tensor Layer Name Human Friendly Tensor Layer Name Elements Shape Type
459 blk.38.attn_k.weight Block 38 Attention Key (W) ( ~1M) 1048576 2048 x 512 x 1 x 1 IQ3_S
460 blk.38.attn_k_norm.weight Block 38 Attn_K_Norm (W) ( 128) 128 128 x 1 x 1 x 1 F32
461 blk.38.attn_norm.weight Block 38 Attention Normalization (W) ( ~2K) 2048 2048 x 1 x 1 x 1 F32
462 blk.38.attn_output.weight Block 38 Attention Output (W) ( ~8M) 8388608 4096 x 2048 x 1 x 1 Q4_K
463 blk.38.attn_q.weight Block 38 Attention Query (W) ( ~8M) 8388608 2048 x 4096 x 1 x 1 IQ3_S
464 blk.38.attn_q_norm.weight Block 38 Attn_Q_Norm (W) ( 128) 128 128 x 1 x 1 x 1 F32
465 blk.38.attn_v.weight Block 38 Attention Value (W) ( ~1M) 1048576 2048 x 512 x 1 x 1 IQ4_NL
466 blk.38.ffn_down_exps.weight Block 38 Ffn_Down_Exps (W) (~201M) 201326592 768 x 2048 x 128 x 1 IQ4_NL
467 blk.38.ffn_gate_exps.weight Block 38 Ffn_Gate_Exps (W) (~201M) 201326592 2048 x 768 x 128 x 1 IQ3_S
468 blk.38.ffn_gate_inp.weight Block 38 Expert-Routing Layer For The Feed-Forward Network In Mixture Of Expert Models (W) (~262K) 262144 2048 x 128 x 1 x 1 F32
469 blk.38.ffn_norm.weight Block 38 Feed-Forward Network Normalization (W) ( ~2K) 2048 2048 x 1 x 1 x 1 F32
470 blk.38.ffn_up_exps.weight Block 38 Ffn_Up_Exps (W) (~201M) 201326592 2048 x 768 x 128 x 1 IQ3_S
  • Total elements in blk.38: (~623M) 623120640
  • Percentage of total elements: 2.04%

Block 39 Tensor Group : ~623M Elements

T_ID Tensor Layer Name Human Friendly Tensor Layer Name Elements Shape Type
471 blk.39.attn_k.weight Block 39 Attention Key (W) ( ~1M) 1048576 2048 x 512 x 1 x 1 IQ3_S
472 blk.39.attn_k_norm.weight Block 39 Attn_K_Norm (W) ( 128) 128 128 x 1 x 1 x 1 F32
473 blk.39.attn_norm.weight Block 39 Attention Normalization (W) ( ~2K) 2048 2048 x 1 x 1 x 1 F32
474 blk.39.attn_output.weight Block 39 Attention Output (W) ( ~8M) 8388608 4096 x 2048 x 1 x 1 Q4_K
475 blk.39.attn_q.weight Block 39 Attention Query (W) ( ~8M) 8388608 2048 x 4096 x 1 x 1 IQ3_S
476 blk.39.attn_q_norm.weight Block 39 Attn_Q_Norm (W) ( 128) 128 128 x 1 x 1 x 1 F32
477 blk.39.attn_v.weight Block 39 Attention Value (W) ( ~1M) 1048576 2048 x 512 x 1 x 1 IQ4_NL
478 blk.39.ffn_down_exps.weight Block 39 Ffn_Down_Exps (W) (~201M) 201326592 768 x 2048 x 128 x 1 IQ4_NL
479 blk.39.ffn_gate_exps.weight Block 39 Ffn_Gate_Exps (W) (~201M) 201326592 2048 x 768 x 128 x 1 IQ3_S
480 blk.39.ffn_gate_inp.weight Block 39 Expert-Routing Layer For The Feed-Forward Network In Mixture Of Expert Models (W) (~262K) 262144 2048 x 128 x 1 x 1 F32
481 blk.39.ffn_norm.weight Block 39 Feed-Forward Network Normalization (W) ( ~2K) 2048 2048 x 1 x 1 x 1 F32
482 blk.39.ffn_up_exps.weight Block 39 Ffn_Up_Exps (W) (~201M) 201326592 2048 x 768 x 128 x 1 IQ3_S
  • Total elements in blk.39: (~623M) 623120640
  • Percentage of total elements: 2.04%

Block 40 Tensor Group : ~623M Elements

T_ID Tensor Layer Name Human Friendly Tensor Layer Name Elements Shape Type
483 blk.40.attn_k.weight Block 40 Attention Key (W) ( ~1M) 1048576 2048 x 512 x 1 x 1 IQ3_S
484 blk.40.attn_k_norm.weight Block 40 Attn_K_Norm (W) ( 128) 128 128 x 1 x 1 x 1 F32
485 blk.40.attn_norm.weight Block 40 Attention Normalization (W) ( ~2K) 2048 2048 x 1 x 1 x 1 F32
486 blk.40.attn_output.weight Block 40 Attention Output (W) ( ~8M) 8388608 4096 x 2048 x 1 x 1 Q4_K
487 blk.40.attn_q.weight Block 40 Attention Query (W) ( ~8M) 8388608 2048 x 4096 x 1 x 1 IQ3_S
488 blk.40.attn_q_norm.weight Block 40 Attn_Q_Norm (W) ( 128) 128 128 x 1 x 1 x 1 F32
489 blk.40.attn_v.weight Block 40 Attention Value (W) ( ~1M) 1048576 2048 x 512 x 1 x 1 IQ4_NL
490 blk.40.ffn_down_exps.weight Block 40 Ffn_Down_Exps (W) (~201M) 201326592 768 x 2048 x 128 x 1 IQ4_NL
491 blk.40.ffn_gate_exps.weight Block 40 Ffn_Gate_Exps (W) (~201M) 201326592 2048 x 768 x 128 x 1 IQ3_S
492 blk.40.ffn_gate_inp.weight Block 40 Expert-Routing Layer For The Feed-Forward Network In Mixture Of Expert Models (W) (~262K) 262144 2048 x 128 x 1 x 1 F32
493 blk.40.ffn_norm.weight Block 40 Feed-Forward Network Normalization (W) ( ~2K) 2048 2048 x 1 x 1 x 1 F32
494 blk.40.ffn_up_exps.weight Block 40 Ffn_Up_Exps (W) (~201M) 201326592 2048 x 768 x 128 x 1 IQ3_S
  • Total elements in blk.40: (~623M) 623120640
  • Percentage of total elements: 2.04%

Block 41 Tensor Group : ~623M Elements

T_ID Tensor Layer Name Human Friendly Tensor Layer Name Elements Shape Type
495 blk.41.attn_k.weight Block 41 Attention Key (W) ( ~1M) 1048576 2048 x 512 x 1 x 1 IQ3_S
496 blk.41.attn_k_norm.weight Block 41 Attn_K_Norm (W) ( 128) 128 128 x 1 x 1 x 1 F32
497 blk.41.attn_norm.weight Block 41 Attention Normalization (W) ( ~2K) 2048 2048 x 1 x 1 x 1 F32
498 blk.41.attn_output.weight Block 41 Attention Output (W) ( ~8M) 8388608 4096 x 2048 x 1 x 1 Q4_K
499 blk.41.attn_q.weight Block 41 Attention Query (W) ( ~8M) 8388608 2048 x 4096 x 1 x 1 IQ3_S
500 blk.41.attn_q_norm.weight Block 41 Attn_Q_Norm (W) ( 128) 128 128 x 1 x 1 x 1 F32
501 blk.41.attn_v.weight Block 41 Attention Value (W) ( ~1M) 1048576 2048 x 512 x 1 x 1 IQ4_NL
502 blk.41.ffn_down_exps.weight Block 41 Ffn_Down_Exps (W) (~201M) 201326592 768 x 2048 x 128 x 1 IQ4_NL
503 blk.41.ffn_gate_exps.weight Block 41 Ffn_Gate_Exps (W) (~201M) 201326592 2048 x 768 x 128 x 1 IQ3_S
504 blk.41.ffn_gate_inp.weight Block 41 Expert-Routing Layer For The Feed-Forward Network In Mixture Of Expert Models (W) (~262K) 262144 2048 x 128 x 1 x 1 F32
505 blk.41.ffn_norm.weight Block 41 Feed-Forward Network Normalization (W) ( ~2K) 2048 2048 x 1 x 1 x 1 F32
506 blk.41.ffn_up_exps.weight Block 41 Ffn_Up_Exps (W) (~201M) 201326592 2048 x 768 x 128 x 1 IQ3_S
  • Total elements in blk.41: (~623M) 623120640
  • Percentage of total elements: 2.04%

Block 42 Tensor Group : ~623M Elements

T_ID Tensor Layer Name Human Friendly Tensor Layer Name Elements Shape Type
507 blk.42.attn_k.weight Block 42 Attention Key (W) ( ~1M) 1048576 2048 x 512 x 1 x 1 IQ3_S
508 blk.42.attn_k_norm.weight Block 42 Attn_K_Norm (W) ( 128) 128 128 x 1 x 1 x 1 F32
509 blk.42.attn_norm.weight Block 42 Attention Normalization (W) ( ~2K) 2048 2048 x 1 x 1 x 1 F32
510 blk.42.attn_output.weight Block 42 Attention Output (W) ( ~8M) 8388608 4096 x 2048 x 1 x 1 Q4_K
511 blk.42.attn_q.weight Block 42 Attention Query (W) ( ~8M) 8388608 2048 x 4096 x 1 x 1 IQ3_S
512 blk.42.attn_q_norm.weight Block 42 Attn_Q_Norm (W) ( 128) 128 128 x 1 x 1 x 1 F32
513 blk.42.attn_v.weight Block 42 Attention Value (W) ( ~1M) 1048576 2048 x 512 x 1 x 1 IQ4_NL
514 blk.42.ffn_down_exps.weight Block 42 Ffn_Down_Exps (W) (~201M) 201326592 768 x 2048 x 128 x 1 IQ4_NL
515 blk.42.ffn_gate_exps.weight Block 42 Ffn_Gate_Exps (W) (~201M) 201326592 2048 x 768 x 128 x 1 IQ3_S
516 blk.42.ffn_gate_inp.weight Block 42 Expert-Routing Layer For The Feed-Forward Network In Mixture Of Expert Models (W) (~262K) 262144 2048 x 128 x 1 x 1 F32
517 blk.42.ffn_norm.weight Block 42 Feed-Forward Network Normalization (W) ( ~2K) 2048 2048 x 1 x 1 x 1 F32
518 blk.42.ffn_up_exps.weight Block 42 Ffn_Up_Exps (W) (~201M) 201326592 2048 x 768 x 128 x 1 IQ3_S
  • Total elements in blk.42: (~623M) 623120640
  • Percentage of total elements: 2.04%

Block 43 Tensor Group : ~623M Elements

T_ID Tensor Layer Name Human Friendly Tensor Layer Name Elements Shape Type
519 blk.43.attn_k.weight Block 43 Attention Key (W) ( ~1M) 1048576 2048 x 512 x 1 x 1 IQ3_S
520 blk.43.attn_k_norm.weight Block 43 Attn_K_Norm (W) ( 128) 128 128 x 1 x 1 x 1 F32
521 blk.43.attn_norm.weight Block 43 Attention Normalization (W) ( ~2K) 2048 2048 x 1 x 1 x 1 F32
522 blk.43.attn_output.weight Block 43 Attention Output (W) ( ~8M) 8388608 4096 x 2048 x 1 x 1 Q4_K
523 blk.43.attn_q.weight Block 43 Attention Query (W) ( ~8M) 8388608 2048 x 4096 x 1 x 1 IQ3_S
524 blk.43.attn_q_norm.weight Block 43 Attn_Q_Norm (W) ( 128) 128 128 x 1 x 1 x 1 F32
525 blk.43.attn_v.weight Block 43 Attention Value (W) ( ~1M) 1048576 2048 x 512 x 1 x 1 IQ4_NL
526 blk.43.ffn_down_exps.weight Block 43 Ffn_Down_Exps (W) (~201M) 201326592 768 x 2048 x 128 x 1 IQ4_NL
527 blk.43.ffn_gate_exps.weight Block 43 Ffn_Gate_Exps (W) (~201M) 201326592 2048 x 768 x 128 x 1 IQ3_S
528 blk.43.ffn_gate_inp.weight Block 43 Expert-Routing Layer For The Feed-Forward Network In Mixture Of Expert Models (W) (~262K) 262144 2048 x 128 x 1 x 1 F32
529 blk.43.ffn_norm.weight Block 43 Feed-Forward Network Normalization (W) ( ~2K) 2048 2048 x 1 x 1 x 1 F32
530 blk.43.ffn_up_exps.weight Block 43 Ffn_Up_Exps (W) (~201M) 201326592 2048 x 768 x 128 x 1 IQ3_S
  • Total elements in blk.43: (~623M) 623120640
  • Percentage of total elements: 2.04%

Block 44 Tensor Group : ~623M Elements

T_ID Tensor Layer Name Human Friendly Tensor Layer Name Elements Shape Type
531 blk.44.attn_k.weight Block 44 Attention Key (W) ( ~1M) 1048576 2048 x 512 x 1 x 1 IQ3_S
532 blk.44.attn_k_norm.weight Block 44 Attn_K_Norm (W) ( 128) 128 128 x 1 x 1 x 1 F32
533 blk.44.attn_norm.weight Block 44 Attention Normalization (W) ( ~2K) 2048 2048 x 1 x 1 x 1 F32
534 blk.44.attn_output.weight Block 44 Attention Output (W) ( ~8M) 8388608 4096 x 2048 x 1 x 1 Q4_K
535 blk.44.attn_q.weight Block 44 Attention Query (W) ( ~8M) 8388608 2048 x 4096 x 1 x 1 IQ3_S
536 blk.44.attn_q_norm.weight Block 44 Attn_Q_Norm (W) ( 128) 128 128 x 1 x 1 x 1 F32
537 blk.44.attn_v.weight Block 44 Attention Value (W) ( ~1M) 1048576 2048 x 512 x 1 x 1 IQ4_NL
538 blk.44.ffn_down_exps.weight Block 44 Ffn_Down_Exps (W) (~201M) 201326592 768 x 2048 x 128 x 1 IQ4_NL
539 blk.44.ffn_gate_exps.weight Block 44 Ffn_Gate_Exps (W) (~201M) 201326592 2048 x 768 x 128 x 1 IQ3_S
540 blk.44.ffn_gate_inp.weight Block 44 Expert-Routing Layer For The Feed-Forward Network In Mixture Of Expert Models (W) (~262K) 262144 2048 x 128 x 1 x 1 F32
541 blk.44.ffn_norm.weight Block 44 Feed-Forward Network Normalization (W) ( ~2K) 2048 2048 x 1 x 1 x 1 F32
542 blk.44.ffn_up_exps.weight Block 44 Ffn_Up_Exps (W) (~201M) 201326592 2048 x 768 x 128 x 1 IQ3_S
  • Total elements in blk.44: (~623M) 623120640
  • Percentage of total elements: 2.04%

Block 45 Tensor Group : ~623M Elements

T_ID Tensor Layer Name Human Friendly Tensor Layer Name Elements Shape Type
543 blk.45.attn_k.weight Block 45 Attention Key (W) ( ~1M) 1048576 2048 x 512 x 1 x 1 IQ3_S
544 blk.45.attn_k_norm.weight Block 45 Attn_K_Norm (W) ( 128) 128 128 x 1 x 1 x 1 F32
545 blk.45.attn_norm.weight Block 45 Attention Normalization (W) ( ~2K) 2048 2048 x 1 x 1 x 1 F32
546 blk.45.attn_output.weight Block 45 Attention Output (W) ( ~8M) 8388608 4096 x 2048 x 1 x 1 Q4_K
547 blk.45.attn_q.weight Block 45 Attention Query (W) ( ~8M) 8388608 2048 x 4096 x 1 x 1 IQ3_S
548 blk.45.attn_q_norm.weight Block 45 Attn_Q_Norm (W) ( 128) 128 128 x 1 x 1 x 1 F32
549 blk.45.attn_v.weight Block 45 Attention Value (W) ( ~1M) 1048576 2048 x 512 x 1 x 1 IQ4_NL
550 blk.45.ffn_down_exps.weight Block 45 Ffn_Down_Exps (W) (~201M) 201326592 768 x 2048 x 128 x 1 IQ4_NL
551 blk.45.ffn_gate_exps.weight Block 45 Ffn_Gate_Exps (W) (~201M) 201326592 2048 x 768 x 128 x 1 IQ3_S
552 blk.45.ffn_gate_inp.weight Block 45 Expert-Routing Layer For The Feed-Forward Network In Mixture Of Expert Models (W) (~262K) 262144 2048 x 128 x 1 x 1 F32
553 blk.45.ffn_norm.weight Block 45 Feed-Forward Network Normalization (W) ( ~2K) 2048 2048 x 1 x 1 x 1 F32
554 blk.45.ffn_up_exps.weight Block 45 Ffn_Up_Exps (W) (~201M) 201326592 2048 x 768 x 128 x 1 IQ3_S
  • Total elements in blk.45: (~623M) 623120640
  • Percentage of total elements: 2.04%

Block 46 Tensor Group : ~623M Elements

T_ID Tensor Layer Name Human Friendly Tensor Layer Name Elements Shape Type
555 blk.46.attn_k.weight Block 46 Attention Key (W) ( ~1M) 1048576 2048 x 512 x 1 x 1 IQ3_S
556 blk.46.attn_k_norm.weight Block 46 Attn_K_Norm (W) ( 128) 128 128 x 1 x 1 x 1 F32
557 blk.46.attn_norm.weight Block 46 Attention Normalization (W) ( ~2K) 2048 2048 x 1 x 1 x 1 F32
558 blk.46.attn_output.weight Block 46 Attention Output (W) ( ~8M) 8388608 4096 x 2048 x 1 x 1 Q4_K
559 blk.46.attn_q.weight Block 46 Attention Query (W) ( ~8M) 8388608 2048 x 4096 x 1 x 1 IQ3_S
560 blk.46.attn_q_norm.weight Block 46 Attn_Q_Norm (W) ( 128) 128 128 x 1 x 1 x 1 F32
561 blk.46.attn_v.weight Block 46 Attention Value (W) ( ~1M) 1048576 2048 x 512 x 1 x 1 IQ4_NL
562 blk.46.ffn_down_exps.weight Block 46 Ffn_Down_Exps (W) (~201M) 201326592 768 x 2048 x 128 x 1 IQ4_NL
563 blk.46.ffn_gate_exps.weight Block 46 Ffn_Gate_Exps (W) (~201M) 201326592 2048 x 768 x 128 x 1 IQ3_S
564 blk.46.ffn_gate_inp.weight Block 46 Expert-Routing Layer For The Feed-Forward Network In Mixture Of Expert Models (W) (~262K) 262144 2048 x 128 x 1 x 1 F32
565 blk.46.ffn_norm.weight Block 46 Feed-Forward Network Normalization (W) ( ~2K) 2048 2048 x 1 x 1 x 1 F32
566 blk.46.ffn_up_exps.weight Block 46 Ffn_Up_Exps (W) (~201M) 201326592 2048 x 768 x 128 x 1 IQ3_S
  • Total elements in blk.46: (~623M) 623120640
  • Percentage of total elements: 2.04%

Block 47 Tensor Group : ~623M Elements

T_ID Tensor Layer Name Human Friendly Tensor Layer Name Elements Shape Type
567 blk.47.attn_k.weight Block 47 Attention Key (W) ( ~1M) 1048576 2048 x 512 x 1 x 1 IQ3_S
568 blk.47.attn_k_norm.weight Block 47 Attn_K_Norm (W) ( 128) 128 128 x 1 x 1 x 1 F32
569 blk.47.attn_norm.weight Block 47 Attention Normalization (W) ( ~2K) 2048 2048 x 1 x 1 x 1 F32
570 blk.47.attn_output.weight Block 47 Attention Output (W) ( ~8M) 8388608 4096 x 2048 x 1 x 1 Q4_K
571 blk.47.attn_q.weight Block 47 Attention Query (W) ( ~8M) 8388608 2048 x 4096 x 1 x 1 IQ3_S
572 blk.47.attn_q_norm.weight Block 47 Attn_Q_Norm (W) ( 128) 128 128 x 1 x 1 x 1 F32
573 blk.47.attn_v.weight Block 47 Attention Value (W) ( ~1M) 1048576 2048 x 512 x 1 x 1 IQ4_NL
574 blk.47.ffn_down_exps.weight Block 47 Ffn_Down_Exps (W) (~201M) 201326592 768 x 2048 x 128 x 1 IQ4_NL
575 blk.47.ffn_gate_exps.weight Block 47 Ffn_Gate_Exps (W) (~201M) 201326592 2048 x 768 x 128 x 1 IQ3_S
576 blk.47.ffn_gate_inp.weight Block 47 Expert-Routing Layer For The Feed-Forward Network In Mixture Of Expert Models (W) (~262K) 262144 2048 x 128 x 1 x 1 F32
577 blk.47.ffn_norm.weight Block 47 Feed-Forward Network Normalization (W) ( ~2K) 2048 2048 x 1 x 1 x 1 F32
578 blk.47.ffn_up_exps.weight Block 47 Ffn_Up_Exps (W) (~201M) 201326592 2048 x 768 x 128 x 1 IQ3_S
  • Total elements in blk.47: (~623M) 623120640
  • Percentage of total elements: 2.04%