Files
gemma-3-12b-it-pruned-GGUF/scores/gemma-3-12b-it-IQ3_M.md
ModelHub XC 66ebbdcd29 初始化项目,由ModelHub XC社区提供模型
Model: eaddario/gemma-3-12b-it-pruned-GGUF
Source: Original Platform
2026-07-21 18:50:10 +08:00

166 KiB

gemma-3-12b-it-IQ3_M.gguf - GGUF Internal File Dump

  • Endian: LITTLE endian

Key Value Metadata Store

There are 48 key-value pairs in this file

POS TYPE Count Key Value
1 UINT32 1 GGUF.version 3
2 UINT64 1 GGUF.tensor_count 600
3 UINT64 1 GGUF.kv_count 45
4 STRING 1 general.architecture gemma3
5 STRING 1 general.type model
6 STRING 1 general.name Gemma 3 12b It
7 STRING 1 general.finetune it
8 STRING 1 general.basename gemma-3
9 STRING 1 general.size_label 12B
10 STRING 1 general.license gemma
11 UINT32 1 general.base_model.count 1
12 STRING 1 general.base_model.0.name Gemma 3 12b Pt
13 STRING 1 general.base_model.0.organization Google
14 STRING 1 general.base_model.0.repo_url https://huggingface.co/google/gemma-3-12b-pt
15 [STRING] 1 general.tags [ image-text-to-text ]
16 UINT32 1 gemma3.context_length 131072
17 UINT32 1 gemma3.embedding_length 3840
18 UINT32 1 gemma3.feed_forward_length 15360
19 UINT32 1 gemma3.attention.head_count 16
20 FLOAT32 1 gemma3.attention.layer_norm_rms_epsilon 1e-06
21 UINT32 1 gemma3.attention.key_length 256
22 UINT32 1 gemma3.attention.value_length 256
23 FLOAT32 1 gemma3.rope.freq_base 1000000.0
24 UINT32 1 gemma3.attention.sliding_window 1024
25 UINT32 1 gemma3.attention.head_count_kv 8
26 STRING 1 gemma3.rope.scaling.type linear
27 FLOAT32 1 gemma3.rope.scaling.factor 8.0
28 STRING 1 tokenizer.ggml.model llama
29 STRING 1 tokenizer.ggml.pre default
30 [STRING] 262144 tokenizer.ggml.tokens [ <pad>, <eos>, <bos>, <unk>, <mask>, ... ]
31 [FLOAT32] 262144 tokenizer.ggml.scores [ -1000.0, -1000.0, -1000.0, -1000.0, -1000.0, -1000.0, -1000.0, ... ]
32 [INT32] 262144 tokenizer.ggml.token_type [ 3, 3, 3, 3, 3, 4, 3, ... ]
33 UINT32 1 tokenizer.ggml.bos_token_id 2
34 UINT32 1 tokenizer.ggml.eos_token_id 1
35 UINT32 1 tokenizer.ggml.unknown_token_id 3
36 UINT32 1 tokenizer.ggml.padding_token_id 0
37 BOOL 1 tokenizer.ggml.add_bos_token True
38 BOOL 1 tokenizer.ggml.add_eos_token False
39 STRING 1 tokenizer.chat_template {{ bos_token }}{%- if message..._turn>model'}}{%- endif -%}
40 BOOL 1 tokenizer.ggml.add_space_prefix False
41 UINT32 1 general.quantization_version 2
42 UINT32 1 general.file_type 27
43 BOOL 1 general.pruned True
44 UINT32 1 gemma3.block_count 46
45 STRING 1 quantize.imatrix.file ./imatrix/imatrix-gemma-3-12b-it-small.dat
46 STRING 1 quantize.imatrix.dataset ../../datasets/imatrix/combined_eur_small.txt
47 INT32 1 quantize.imatrix.entries_count 336
48 INT32 1 quantize.imatrix.chunks_count 3226

Tensors Overview ~11B Elements

Total number of elements in all tensors: 11317490432 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_norm.weight 0x63ee20 0x3c00
1 token_embd.weight 0x642a20 0x19c80000
2 blk.0.attn_k.weight 0x1a2c2a20 0x339000
3 blk.0.attn_k_norm.weight 0x1a5fba20 0x400
4 blk.0.attn_norm.weight 0x1a5fbe20 0x3c00
5 blk.0.attn_output.weight 0x1a5ffa20 0x870000
6 blk.0.attn_q.weight 0x1ae6fa20 0x672000
7 blk.0.attn_q_norm.weight 0x1b4e1a20 0x400
8 blk.0.attn_v.weight 0x1b4e1e20 0x438000
9 blk.0.ffn_down.weight 0x1b919e20 0x1fa4000
10 blk.0.ffn_gate.weight 0x1d8bde20 0x182b800
11 blk.0.ffn_norm.weight 0x1f0e9620 0x3c00
12 blk.0.ffn_up.weight 0x1f0ed220 0x182b800
13 blk.0.post_attention_norm.weight 0x20918a20 0x3c00
14 blk.0.post_ffw_norm.weight 0x2091c620 0x3c00
15 blk.1.attn_k.weight 0x20920220 0x339000
16 blk.1.attn_k_norm.weight 0x20c59220 0x400
17 blk.1.attn_norm.weight 0x20c59620 0x3c00
18 blk.1.attn_output.weight 0x20c5d220 0x870000
19 blk.1.attn_q.weight 0x214cd220 0x672000
20 blk.1.attn_q_norm.weight 0x21b3f220 0x400
21 blk.1.attn_v.weight 0x21b3f620 0x438000
22 blk.1.ffn_down.weight 0x21f77620 0x1fa4000
23 blk.1.ffn_gate.weight 0x23f1b620 0x182b800
24 blk.1.ffn_norm.weight 0x25746e20 0x3c00
25 blk.1.ffn_up.weight 0x2574aa20 0x182b800
26 blk.1.post_attention_norm.weight 0x26f76220 0x3c00
27 blk.1.post_ffw_norm.weight 0x26f79e20 0x3c00
28 blk.2.attn_k.weight 0x26f7da20 0x339000
29 blk.2.attn_k_norm.weight 0x272b6a20 0x400
30 blk.2.attn_norm.weight 0x272b6e20 0x3c00
31 blk.2.attn_output.weight 0x272baa20 0x870000
32 blk.2.attn_q.weight 0x27b2aa20 0x672000
33 blk.2.attn_q_norm.weight 0x2819ca20 0x400
34 blk.2.attn_v.weight 0x2819ce20 0x438000
35 blk.2.ffn_down.weight 0x285d4e20 0x1fa4000
36 blk.2.ffn_gate.weight 0x2a578e20 0x182b800
37 blk.2.ffn_norm.weight 0x2bda4620 0x3c00
38 blk.2.ffn_up.weight 0x2bda8220 0x182b800
39 blk.2.post_attention_norm.weight 0x2d5d3a20 0x3c00
40 blk.2.post_ffw_norm.weight 0x2d5d7620 0x3c00
41 blk.3.attn_k.weight 0x2d5db220 0x339000
42 blk.3.attn_k_norm.weight 0x2d914220 0x400
43 blk.3.attn_norm.weight 0x2d914620 0x3c00
44 blk.3.attn_output.weight 0x2d918220 0x870000
45 blk.3.attn_q.weight 0x2e188220 0x672000
46 blk.3.attn_q_norm.weight 0x2e7fa220 0x400
47 blk.3.attn_v.weight 0x2e7fa620 0x438000
48 blk.3.ffn_down.weight 0x2ec32620 0x1fa4000
49 blk.3.ffn_gate.weight 0x30bd6620 0x182b800
50 blk.3.ffn_norm.weight 0x32401e20 0x3c00
51 blk.3.ffn_up.weight 0x32405a20 0x182b800
52 blk.3.post_attention_norm.weight 0x33c31220 0x3c00
53 blk.3.post_ffw_norm.weight 0x33c34e20 0x3c00
54 blk.4.attn_k.weight 0x33c38a20 0x339000
55 blk.4.attn_k_norm.weight 0x33f71a20 0x400
56 blk.4.attn_norm.weight 0x33f71e20 0x3c00
57 blk.4.attn_output.weight 0x33f75a20 0x870000
58 blk.4.attn_q.weight 0x347e5a20 0x672000
59 blk.4.attn_q_norm.weight 0x34e57a20 0x400
60 blk.4.attn_v.weight 0x34e57e20 0x438000
61 blk.4.ffn_down.weight 0x3528fe20 0x1fa4000
62 blk.4.ffn_gate.weight 0x37233e20 0x182b800
63 blk.4.ffn_norm.weight 0x38a5f620 0x3c00
64 blk.4.ffn_up.weight 0x38a63220 0x182b800
65 blk.4.post_attention_norm.weight 0x3a28ea20 0x3c00
66 blk.4.post_ffw_norm.weight 0x3a292620 0x3c00
67 blk.5.attn_k.weight 0x3a296220 0x339000
68 blk.5.attn_k_norm.weight 0x3a5cf220 0x400
69 blk.5.attn_norm.weight 0x3a5cf620 0x3c00
70 blk.5.attn_output.weight 0x3a5d3220 0x870000
71 blk.5.attn_q.weight 0x3ae43220 0x672000
72 blk.5.attn_q_norm.weight 0x3b4b5220 0x400
73 blk.5.attn_v.weight 0x3b4b5620 0x438000
74 blk.5.ffn_down.weight 0x3b8ed620 0x1fa4000
75 blk.5.ffn_gate.weight 0x3d891620 0x182b800
76 blk.5.ffn_norm.weight 0x3f0bce20 0x3c00
77 blk.5.ffn_up.weight 0x3f0c0a20 0x182b800
78 blk.5.post_attention_norm.weight 0x408ec220 0x3c00
79 blk.5.post_ffw_norm.weight 0x408efe20 0x3c00
80 blk.6.attn_k.weight 0x408f3a20 0x339000
81 blk.6.attn_k_norm.weight 0x40c2ca20 0x400
82 blk.6.attn_norm.weight 0x40c2ce20 0x3c00
83 blk.6.attn_output.weight 0x40c30a20 0x870000
84 blk.6.attn_q.weight 0x414a0a20 0x672000
85 blk.6.attn_q_norm.weight 0x41b12a20 0x400
86 blk.6.attn_v.weight 0x41b12e20 0x438000
87 blk.6.ffn_down.weight 0x41f4ae20 0x1fa4000
88 blk.6.ffn_gate.weight 0x43eeee20 0x182b800
89 blk.6.ffn_norm.weight 0x4571a620 0x3c00
90 blk.6.ffn_up.weight 0x4571e220 0x182b800
91 blk.6.post_attention_norm.weight 0x46f49a20 0x3c00
92 blk.6.post_ffw_norm.weight 0x46f4d620 0x3c00
93 blk.7.attn_k.weight 0x46f51220 0x339000
94 blk.7.attn_k_norm.weight 0x4728a220 0x400
95 blk.7.attn_norm.weight 0x4728a620 0x3c00
96 blk.7.attn_output.weight 0x4728e220 0x870000
97 blk.7.attn_q.weight 0x47afe220 0x672000
98 blk.7.attn_q_norm.weight 0x48170220 0x400
99 blk.7.attn_v.weight 0x48170620 0x438000
100 blk.7.ffn_down.weight 0x485a8620 0x1fa4000
101 blk.7.ffn_gate.weight 0x4a54c620 0x182b800
102 blk.7.ffn_norm.weight 0x4bd77e20 0x3c00
103 blk.7.ffn_up.weight 0x4bd7ba20 0x182b800
104 blk.7.post_attention_norm.weight 0x4d5a7220 0x3c00
105 blk.7.post_ffw_norm.weight 0x4d5aae20 0x3c00
106 blk.8.attn_k.weight 0x4d5aea20 0x339000
107 blk.8.attn_k_norm.weight 0x4d8e7a20 0x400
108 blk.8.attn_norm.weight 0x4d8e7e20 0x3c00
109 blk.8.attn_output.weight 0x4d8eba20 0x870000
110 blk.8.attn_q.weight 0x4e15ba20 0x672000
111 blk.8.attn_q_norm.weight 0x4e7cda20 0x400
112 blk.8.attn_v.weight 0x4e7cde20 0x438000
113 blk.8.ffn_down.weight 0x4ec05e20 0x1fa4000
114 blk.8.ffn_gate.weight 0x50ba9e20 0x182b800
115 blk.8.ffn_norm.weight 0x523d5620 0x3c00
116 blk.8.ffn_up.weight 0x523d9220 0x182b800
117 blk.8.post_attention_norm.weight 0x53c04a20 0x3c00
118 blk.8.post_ffw_norm.weight 0x53c08620 0x3c00
119 blk.9.attn_k.weight 0x53c0c220 0x339000
120 blk.9.attn_k_norm.weight 0x53f45220 0x400
121 blk.9.attn_norm.weight 0x53f45620 0x3c00
122 blk.9.attn_output.weight 0x53f49220 0x870000
123 blk.9.attn_q.weight 0x547b9220 0x672000
124 blk.9.attn_q_norm.weight 0x54e2b220 0x400
125 blk.9.attn_v.weight 0x54e2b620 0x438000
126 blk.9.ffn_down.weight 0x55263620 0x1fa4000
127 blk.9.ffn_gate.weight 0x57207620 0x182b800
128 blk.9.ffn_norm.weight 0x58a32e20 0x3c00
129 blk.9.ffn_up.weight 0x58a36a20 0x182b800
130 blk.9.post_attention_norm.weight 0x5a262220 0x3c00
131 blk.9.post_ffw_norm.weight 0x5a265e20 0x3c00
132 blk.10.attn_k.weight 0x5a269a20 0x339000
133 blk.10.attn_k_norm.weight 0x5a5a2a20 0x400
134 blk.10.attn_norm.weight 0x5a5a2e20 0x3c00
135 blk.10.attn_output.weight 0x5a5a6a20 0x870000
136 blk.10.attn_q.weight 0x5ae16a20 0x672000
137 blk.10.attn_q_norm.weight 0x5b488a20 0x400
138 blk.10.attn_v.weight 0x5b488e20 0x438000
139 blk.10.ffn_down.weight 0x5b8c0e20 0x1fa4000
140 blk.10.ffn_gate.weight 0x5d864e20 0x182b800
141 blk.10.ffn_norm.weight 0x5f090620 0x3c00
142 blk.10.ffn_up.weight 0x5f094220 0x182b800
143 blk.10.post_attention_norm.weight 0x608bfa20 0x3c00
144 blk.10.post_ffw_norm.weight 0x608c3620 0x3c00
145 blk.11.attn_k.weight 0x608c7220 0x2df000
146 blk.11.attn_k_norm.weight 0x60ba6220 0x400
147 blk.11.attn_norm.weight 0x60ba6620 0x3c00
148 blk.11.attn_output.weight 0x60baa220 0x870000
149 blk.11.attn_q.weight 0x6141a220 0x5be000
150 blk.11.attn_q_norm.weight 0x619d8220 0x400
151 blk.11.attn_v.weight 0x619d8620 0x339000
152 blk.11.ffn_down.weight 0x61d11620 0x1fa4000
153 blk.11.ffn_gate.weight 0x63cb5620 0x1588800
154 blk.11.ffn_norm.weight 0x6523de20 0x3c00
155 blk.11.ffn_up.weight 0x65241a20 0x1588800
156 blk.11.post_attention_norm.weight 0x667ca220 0x3c00
157 blk.11.post_ffw_norm.weight 0x667cde20 0x3c00
158 blk.12.attn_k.weight 0x667d1a20 0x2df000
159 blk.12.attn_k_norm.weight 0x66ab0a20 0x400
160 blk.12.attn_norm.weight 0x66ab0e20 0x3c00
161 blk.12.attn_output.weight 0x66ab4a20 0x870000
162 blk.12.attn_q.weight 0x67324a20 0x5be000
163 blk.12.attn_q_norm.weight 0x678e2a20 0x400
164 blk.12.attn_v.weight 0x678e2e20 0x339000
165 blk.12.ffn_down.weight 0x67c1be20 0x1fa4000
166 blk.12.ffn_gate.weight 0x69bbfe20 0x1588800
167 blk.12.ffn_norm.weight 0x6b148620 0x3c00
168 blk.12.ffn_up.weight 0x6b14c220 0x1588800
169 blk.12.post_attention_norm.weight 0x6c6d4a20 0x3c00
170 blk.12.post_ffw_norm.weight 0x6c6d8620 0x3c00
171 blk.13.attn_k.weight 0x6c6dc220 0x2df000
172 blk.13.attn_k_norm.weight 0x6c9bb220 0x400
173 blk.13.attn_norm.weight 0x6c9bb620 0x3c00
174 blk.13.attn_output.weight 0x6c9bf220 0x870000
175 blk.13.attn_q.weight 0x6d22f220 0x5be000
176 blk.13.attn_q_norm.weight 0x6d7ed220 0x400
177 blk.13.attn_v.weight 0x6d7ed620 0x339000
178 blk.13.ffn_down.weight 0x6db26620 0x1fa4000
179 blk.13.ffn_gate.weight 0x6faca620 0x1588800
180 blk.13.ffn_norm.weight 0x71052e20 0x3c00
181 blk.13.ffn_up.weight 0x71056a20 0x1588800
182 blk.13.post_attention_norm.weight 0x725df220 0x3c00
183 blk.13.post_ffw_norm.weight 0x725e2e20 0x3c00
184 blk.14.attn_k.weight 0x725e6a20 0x2df000
185 blk.14.attn_k_norm.weight 0x728c5a20 0x400
186 blk.14.attn_norm.weight 0x728c5e20 0x3c00
187 blk.14.attn_output.weight 0x728c9a20 0x870000
188 blk.14.attn_q.weight 0x73139a20 0x5be000
189 blk.14.attn_q_norm.weight 0x736f7a20 0x400
190 blk.14.attn_v.weight 0x736f7e20 0x339000
191 blk.14.ffn_down.weight 0x73a30e20 0x1fa4000
192 blk.14.ffn_gate.weight 0x759d4e20 0x1588800
193 blk.14.ffn_norm.weight 0x76f5d620 0x3c00
194 blk.14.ffn_up.weight 0x76f61220 0x1588800
195 blk.14.post_attention_norm.weight 0x784e9a20 0x3c00
196 blk.14.post_ffw_norm.weight 0x784ed620 0x3c00
197 blk.15.attn_k.weight 0x784f1220 0x2df000
198 blk.15.attn_k_norm.weight 0x787d0220 0x400
199 blk.15.attn_norm.weight 0x787d0620 0x3c00
200 blk.15.attn_output.weight 0x787d4220 0x870000
201 blk.15.attn_q.weight 0x79044220 0x5be000
202 blk.15.attn_q_norm.weight 0x79602220 0x400
203 blk.15.attn_v.weight 0x79602620 0x339000
204 blk.15.ffn_down.weight 0x7993b620 0x1fa4000
205 blk.15.ffn_gate.weight 0x7b8df620 0x1588800
206 blk.15.ffn_norm.weight 0x7ce67e20 0x3c00
207 blk.15.ffn_up.weight 0x7ce6ba20 0x1588800
208 blk.15.post_attention_norm.weight 0x7e3f4220 0x3c00
209 blk.15.post_ffw_norm.weight 0x7e3f7e20 0x3c00
210 blk.16.attn_k.weight 0x7e3fba20 0x2df000
211 blk.16.attn_k_norm.weight 0x7e6daa20 0x400
212 blk.16.attn_norm.weight 0x7e6dae20 0x3c00
213 blk.16.attn_output.weight 0x7e6dea20 0x870000
214 blk.16.attn_q.weight 0x7ef4ea20 0x5be000
215 blk.16.attn_q_norm.weight 0x7f50ca20 0x400
216 blk.16.attn_v.weight 0x7f50ce20 0x339000
217 blk.16.ffn_down.weight 0x7f845e20 0x1fa4000
218 blk.16.ffn_gate.weight 0x817e9e20 0x1588800
219 blk.16.ffn_norm.weight 0x82d72620 0x3c00
220 blk.16.ffn_up.weight 0x82d76220 0x1588800
221 blk.16.post_attention_norm.weight 0x842fea20 0x3c00
222 blk.16.post_ffw_norm.weight 0x84302620 0x3c00
223 blk.17.attn_k.weight 0x84306220 0x2df000
224 blk.17.attn_k_norm.weight 0x845e5220 0x400
225 blk.17.attn_norm.weight 0x845e5620 0x3c00
226 blk.17.attn_output.weight 0x845e9220 0x870000
227 blk.17.attn_q.weight 0x84e59220 0x5be000
228 blk.17.attn_q_norm.weight 0x85417220 0x400
229 blk.17.attn_v.weight 0x85417620 0x339000
230 blk.17.ffn_down.weight 0x85750620 0x1fa4000
231 blk.17.ffn_gate.weight 0x876f4620 0x1588800
232 blk.17.ffn_norm.weight 0x88c7ce20 0x3c00
233 blk.17.ffn_up.weight 0x88c80a20 0x1588800
234 blk.17.post_attention_norm.weight 0x8a209220 0x3c00
235 blk.17.post_ffw_norm.weight 0x8a20ce20 0x3c00
236 blk.18.attn_k.weight 0x8a210a20 0x2df000
237 blk.18.attn_k_norm.weight 0x8a4efa20 0x400
238 blk.18.attn_norm.weight 0x8a4efe20 0x3c00
239 blk.18.attn_output.weight 0x8a4f3a20 0x870000
240 blk.18.attn_q.weight 0x8ad63a20 0x5be000
241 blk.18.attn_q_norm.weight 0x8b321a20 0x400
242 blk.18.attn_v.weight 0x8b321e20 0x339000
243 blk.18.ffn_down.weight 0x8b65ae20 0x1fa4000
244 blk.18.ffn_gate.weight 0x8d5fee20 0x1588800
245 blk.18.ffn_norm.weight 0x8eb87620 0x3c00
246 blk.18.ffn_up.weight 0x8eb8b220 0x1588800
247 blk.18.post_attention_norm.weight 0x90113a20 0x3c00
248 blk.18.post_ffw_norm.weight 0x90117620 0x3c00
249 blk.19.attn_k.weight 0x9011b220 0x2df000
250 blk.19.attn_k_norm.weight 0x903fa220 0x400
251 blk.19.attn_norm.weight 0x903fa620 0x3c00
252 blk.19.attn_output.weight 0x903fe220 0x870000
253 blk.19.attn_q.weight 0x90c6e220 0x5be000
254 blk.19.attn_q_norm.weight 0x9122c220 0x400
255 blk.19.attn_v.weight 0x9122c620 0x339000
256 blk.19.ffn_down.weight 0x91565620 0x1fa4000
257 blk.19.ffn_gate.weight 0x93509620 0x1588800
258 blk.19.ffn_norm.weight 0x94a91e20 0x3c00
259 blk.19.ffn_up.weight 0x94a95a20 0x1588800
260 blk.19.post_attention_norm.weight 0x9601e220 0x3c00
261 blk.19.post_ffw_norm.weight 0x96021e20 0x3c00
262 blk.20.attn_k.weight 0x96025a20 0x2df000
263 blk.20.attn_k_norm.weight 0x96304a20 0x400
264 blk.20.attn_norm.weight 0x96304e20 0x3c00
265 blk.20.attn_output.weight 0x96308a20 0x870000
266 blk.20.attn_q.weight 0x96b78a20 0x5be000
267 blk.20.attn_q_norm.weight 0x97136a20 0x400
268 blk.20.attn_v.weight 0x97136e20 0x339000
269 blk.20.ffn_down.weight 0x9746fe20 0x1fa4000
270 blk.20.ffn_gate.weight 0x99413e20 0x1588800
271 blk.20.ffn_norm.weight 0x9a99c620 0x3c00
272 blk.20.ffn_up.weight 0x9a9a0220 0x1588800
273 blk.20.post_attention_norm.weight 0x9bf28a20 0x3c00
274 blk.20.post_ffw_norm.weight 0x9bf2c620 0x3c00
275 blk.21.attn_k.weight 0x9bf30220 0x2df000
276 blk.21.attn_k_norm.weight 0x9c20f220 0x400
277 blk.21.attn_norm.weight 0x9c20f620 0x3c00
278 blk.21.attn_output.weight 0x9c213220 0x870000
279 blk.21.attn_q.weight 0x9ca83220 0x5be000
280 blk.21.attn_q_norm.weight 0x9d041220 0x400
281 blk.21.attn_v.weight 0x9d041620 0x339000
282 blk.21.ffn_down.weight 0x9d37a620 0x1fa4000
283 blk.21.ffn_gate.weight 0x9f31e620 0x1588800
284 blk.21.ffn_norm.weight 0xa08a6e20 0x3c00
285 blk.21.ffn_up.weight 0xa08aaa20 0x1588800
286 blk.21.post_attention_norm.weight 0xa1e33220 0x3c00
287 blk.21.post_ffw_norm.weight 0xa1e36e20 0x3c00
288 blk.22.attn_k.weight 0xa1e3aa20 0x2df000
289 blk.22.attn_k_norm.weight 0xa2119a20 0x400
290 blk.22.attn_norm.weight 0xa2119e20 0x3c00
291 blk.22.attn_output.weight 0xa211da20 0x870000
292 blk.22.attn_q.weight 0xa298da20 0x5be000
293 blk.22.attn_q_norm.weight 0xa2f4ba20 0x400
294 blk.22.attn_v.weight 0xa2f4be20 0x339000
295 blk.22.ffn_down.weight 0xa3284e20 0x1fa4000
296 blk.22.ffn_gate.weight 0xa5228e20 0x1588800
297 blk.22.ffn_norm.weight 0xa67b1620 0x3c00
298 blk.22.ffn_up.weight 0xa67b5220 0x1588800
299 blk.22.post_attention_norm.weight 0xa7d3da20 0x3c00
300 blk.22.post_ffw_norm.weight 0xa7d41620 0x3c00
301 blk.23.attn_k.weight 0xa7d45220 0x2df000
302 blk.23.attn_k_norm.weight 0xa8024220 0x400
303 blk.23.attn_norm.weight 0xa8024620 0x3c00
304 blk.23.attn_output.weight 0xa8028220 0x870000
305 blk.23.attn_q.weight 0xa8898220 0x5be000
306 blk.23.attn_q_norm.weight 0xa8e56220 0x400
307 blk.23.attn_v.weight 0xa8e56620 0x339000
308 blk.23.ffn_down.weight 0xa918f620 0x1fa4000
309 blk.23.ffn_gate.weight 0xab133620 0x1588800
310 blk.23.ffn_norm.weight 0xac6bbe20 0x3c00
311 blk.23.ffn_up.weight 0xac6bfa20 0x1588800
312 blk.23.post_attention_norm.weight 0xadc48220 0x3c00
313 blk.23.post_ffw_norm.weight 0xadc4be20 0x3c00
314 blk.24.attn_k.weight 0xadc4fa20 0x339000
315 blk.24.attn_k_norm.weight 0xadf88a20 0x400
316 blk.24.attn_norm.weight 0xadf88e20 0x3c00
317 blk.24.attn_output.weight 0xadf8ca20 0x870000
318 blk.24.attn_q.weight 0xae7fca20 0x672000
319 blk.24.attn_q_norm.weight 0xaee6ea20 0x400
320 blk.24.attn_v.weight 0xaee6ee20 0x438000
321 blk.24.ffn_down.weight 0xaf2a6e20 0x1fa4000
322 blk.24.ffn_gate.weight 0xb124ae20 0x182b800
323 blk.24.ffn_norm.weight 0xb2a76620 0x3c00
324 blk.24.ffn_up.weight 0xb2a7a220 0x182b800
325 blk.24.post_attention_norm.weight 0xb42a5a20 0x3c00
326 blk.24.post_ffw_norm.weight 0xb42a9620 0x3c00
327 blk.25.attn_k.weight 0xb42ad220 0x2df000
328 blk.25.attn_k_norm.weight 0xb458c220 0x400
329 blk.25.attn_norm.weight 0xb458c620 0x3c00
330 blk.25.attn_output.weight 0xb4590220 0x870000
331 blk.25.attn_q.weight 0xb4e00220 0x5be000
332 blk.25.attn_q_norm.weight 0xb53be220 0x400
333 blk.25.attn_v.weight 0xb53be620 0x339000
334 blk.25.ffn_down.weight 0xb56f7620 0x1fa4000
335 blk.25.ffn_gate.weight 0xb769b620 0x1588800
336 blk.25.ffn_norm.weight 0xb8c23e20 0x3c00
337 blk.25.ffn_up.weight 0xb8c27a20 0x1588800
338 blk.25.post_attention_norm.weight 0xba1b0220 0x3c00
339 blk.25.post_ffw_norm.weight 0xba1b3e20 0x3c00
340 blk.26.attn_k.weight 0xba1b7a20 0x2df000
341 blk.26.attn_k_norm.weight 0xba496a20 0x400
342 blk.26.attn_norm.weight 0xba496e20 0x3c00
343 blk.26.attn_output.weight 0xba49aa20 0x870000
344 blk.26.attn_q.weight 0xbad0aa20 0x5be000
345 blk.26.attn_q_norm.weight 0xbb2c8a20 0x400
346 blk.26.attn_v.weight 0xbb2c8e20 0x339000
347 blk.26.ffn_down.weight 0xbb601e20 0x1fa4000
348 blk.26.ffn_gate.weight 0xbd5a5e20 0x1588800
349 blk.26.ffn_norm.weight 0xbeb2e620 0x3c00
350 blk.26.ffn_up.weight 0xbeb32220 0x1588800
351 blk.26.post_attention_norm.weight 0xc00baa20 0x3c00
352 blk.26.post_ffw_norm.weight 0xc00be620 0x3c00
353 blk.27.attn_k.weight 0xc00c2220 0x2df000
354 blk.27.attn_k_norm.weight 0xc03a1220 0x400
355 blk.27.attn_norm.weight 0xc03a1620 0x3c00
356 blk.27.attn_output.weight 0xc03a5220 0x870000
357 blk.27.attn_q.weight 0xc0c15220 0x5be000
358 blk.27.attn_q_norm.weight 0xc11d3220 0x400
359 blk.27.attn_v.weight 0xc11d3620 0x339000
360 blk.27.ffn_down.weight 0xc150c620 0x1fa4000
361 blk.27.ffn_gate.weight 0xc34b0620 0x1588800
362 blk.27.ffn_norm.weight 0xc4a38e20 0x3c00
363 blk.27.ffn_up.weight 0xc4a3ca20 0x1588800
364 blk.27.post_attention_norm.weight 0xc5fc5220 0x3c00
365 blk.27.post_ffw_norm.weight 0xc5fc8e20 0x3c00
366 blk.28.attn_k.weight 0xc5fcca20 0x339000
367 blk.28.attn_k_norm.weight 0xc6305a20 0x400
368 blk.28.attn_norm.weight 0xc6305e20 0x3c00
369 blk.28.attn_output.weight 0xc6309a20 0x870000
370 blk.28.attn_q.weight 0xc6b79a20 0x672000
371 blk.28.attn_q_norm.weight 0xc71eba20 0x400
372 blk.28.attn_v.weight 0xc71ebe20 0x438000
373 blk.28.ffn_down.weight 0xc7623e20 0x1fa4000
374 blk.28.ffn_gate.weight 0xc95c7e20 0x182b800
375 blk.28.ffn_norm.weight 0xcadf3620 0x3c00
376 blk.28.ffn_up.weight 0xcadf7220 0x182b800
377 blk.28.post_attention_norm.weight 0xcc622a20 0x3c00
378 blk.28.post_ffw_norm.weight 0xcc626620 0x3c00
379 blk.29.attn_k.weight 0xcc62a220 0x2df000
380 blk.29.attn_k_norm.weight 0xcc909220 0x400
381 blk.29.attn_norm.weight 0xcc909620 0x3c00
382 blk.29.attn_output.weight 0xcc90d220 0x870000
383 blk.29.attn_q.weight 0xcd17d220 0x5be000
384 blk.29.attn_q_norm.weight 0xcd73b220 0x400
385 blk.29.attn_v.weight 0xcd73b620 0x339000
386 blk.29.ffn_down.weight 0xcda74620 0x1fa4000
387 blk.29.ffn_gate.weight 0xcfa18620 0x1588800
388 blk.29.ffn_norm.weight 0xd0fa0e20 0x3c00
389 blk.29.ffn_up.weight 0xd0fa4a20 0x1588800
390 blk.29.post_attention_norm.weight 0xd252d220 0x3c00
391 blk.29.post_ffw_norm.weight 0xd2530e20 0x3c00
392 blk.30.attn_k.weight 0xd2534a20 0x2df000
393 blk.30.attn_k_norm.weight 0xd2813a20 0x400
394 blk.30.attn_norm.weight 0xd2813e20 0x3c00
395 blk.30.attn_output.weight 0xd2817a20 0x870000
396 blk.30.attn_q.weight 0xd3087a20 0x5be000
397 blk.30.attn_q_norm.weight 0xd3645a20 0x400
398 blk.30.attn_v.weight 0xd3645e20 0x339000
399 blk.30.ffn_down.weight 0xd397ee20 0x1fa4000
400 blk.30.ffn_gate.weight 0xd5922e20 0x1588800
401 blk.30.ffn_norm.weight 0xd6eab620 0x3c00
402 blk.30.ffn_up.weight 0xd6eaf220 0x1588800
403 blk.30.post_attention_norm.weight 0xd8437a20 0x3c00
404 blk.30.post_ffw_norm.weight 0xd843b620 0x3c00
405 blk.31.attn_k.weight 0xd843f220 0x339000
406 blk.31.attn_k_norm.weight 0xd8778220 0x400
407 blk.31.attn_norm.weight 0xd8778620 0x3c00
408 blk.31.attn_output.weight 0xd877c220 0x870000
409 blk.31.attn_q.weight 0xd8fec220 0x672000
410 blk.31.attn_q_norm.weight 0xd965e220 0x400
411 blk.31.attn_v.weight 0xd965e620 0x438000
412 blk.31.ffn_down.weight 0xd9a96620 0x1fa4000
413 blk.31.ffn_gate.weight 0xdba3a620 0x182b800
414 blk.31.ffn_norm.weight 0xdd265e20 0x3c00
415 blk.31.ffn_up.weight 0xdd269a20 0x182b800
416 blk.31.post_attention_norm.weight 0xdea95220 0x3c00
417 blk.31.post_ffw_norm.weight 0xdea98e20 0x3c00
418 blk.32.attn_k.weight 0xdea9ca20 0x339000
419 blk.32.attn_k_norm.weight 0xdedd5a20 0x400
420 blk.32.attn_norm.weight 0xdedd5e20 0x3c00
421 blk.32.attn_output.weight 0xdedd9a20 0x870000
422 blk.32.attn_q.weight 0xdf649a20 0x672000
423 blk.32.attn_q_norm.weight 0xdfcbba20 0x400
424 blk.32.attn_v.weight 0xdfcbbe20 0x438000
425 blk.32.ffn_down.weight 0xe00f3e20 0x1fa4000
426 blk.32.ffn_gate.weight 0xe2097e20 0x182b800
427 blk.32.ffn_norm.weight 0xe38c3620 0x3c00
428 blk.32.ffn_up.weight 0xe38c7220 0x182b800
429 blk.32.post_attention_norm.weight 0xe50f2a20 0x3c00
430 blk.32.post_ffw_norm.weight 0xe50f6620 0x3c00
431 blk.33.attn_k.weight 0xe50fa220 0x339000
432 blk.33.attn_k_norm.weight 0xe5433220 0x400
433 blk.33.attn_norm.weight 0xe5433620 0x3c00
434 blk.33.attn_output.weight 0xe5437220 0x870000
435 blk.33.attn_q.weight 0xe5ca7220 0x672000
436 blk.33.attn_q_norm.weight 0xe6319220 0x400
437 blk.33.attn_v.weight 0xe6319620 0x438000
438 blk.33.ffn_down.weight 0xe6751620 0x1fa4000
439 blk.33.ffn_gate.weight 0xe86f5620 0x182b800
440 blk.33.ffn_norm.weight 0xe9f20e20 0x3c00
441 blk.33.ffn_up.weight 0xe9f24a20 0x182b800
442 blk.33.post_attention_norm.weight 0xeb750220 0x3c00
443 blk.33.post_ffw_norm.weight 0xeb753e20 0x3c00
444 blk.34.attn_k.weight 0xeb757a20 0x339000
445 blk.34.attn_k_norm.weight 0xeba90a20 0x400
446 blk.34.attn_norm.weight 0xeba90e20 0x3c00
447 blk.34.attn_output.weight 0xeba94a20 0x870000
448 blk.34.attn_q.weight 0xec304a20 0x672000
449 blk.34.attn_q_norm.weight 0xec976a20 0x400
450 blk.34.attn_v.weight 0xec976e20 0x438000
451 blk.34.ffn_down.weight 0xecdaee20 0x1fa4000
452 blk.34.ffn_gate.weight 0xeed52e20 0x182b800
453 blk.34.ffn_norm.weight 0xf057e620 0x3c00
454 blk.34.ffn_up.weight 0xf0582220 0x182b800
455 blk.34.post_attention_norm.weight 0xf1dada20 0x3c00
456 blk.34.post_ffw_norm.weight 0xf1db1620 0x3c00
457 blk.35.attn_k.weight 0xf1db5220 0x2df000
458 blk.35.attn_k_norm.weight 0xf2094220 0x400
459 blk.35.attn_norm.weight 0xf2094620 0x3c00
460 blk.35.attn_output.weight 0xf2098220 0x870000
461 blk.35.attn_q.weight 0xf2908220 0x5be000
462 blk.35.attn_q_norm.weight 0xf2ec6220 0x400
463 blk.35.attn_v.weight 0xf2ec6620 0x339000
464 blk.35.ffn_down.weight 0xf31ff620 0x1fa4000
465 blk.35.ffn_gate.weight 0xf51a3620 0x1588800
466 blk.35.ffn_norm.weight 0xf672be20 0x3c00
467 blk.35.ffn_up.weight 0xf672fa20 0x1588800
468 blk.35.post_attention_norm.weight 0xf7cb8220 0x3c00
469 blk.35.post_ffw_norm.weight 0xf7cbbe20 0x3c00
470 blk.36.attn_k.weight 0xf7cbfa20 0x339000
471 blk.36.attn_k_norm.weight 0xf7ff8a20 0x400
472 blk.36.attn_norm.weight 0xf7ff8e20 0x3c00
473 blk.36.attn_output.weight 0xf7ffca20 0x870000
474 blk.36.attn_q.weight 0xf886ca20 0x672000
475 blk.36.attn_q_norm.weight 0xf8edea20 0x400
476 blk.36.attn_v.weight 0xf8edee20 0x438000
477 blk.36.ffn_down.weight 0xf9316e20 0x1fa4000
478 blk.36.ffn_gate.weight 0xfb2bae20 0x182b800
479 blk.36.ffn_norm.weight 0xfcae6620 0x3c00
480 blk.36.ffn_up.weight 0xfcaea220 0x182b800
481 blk.36.post_attention_norm.weight 0xfe315a20 0x3c00
482 blk.36.post_ffw_norm.weight 0xfe319620 0x3c00
483 blk.37.attn_k.weight 0xfe31d220 0x339000
484 blk.37.attn_k_norm.weight 0xfe656220 0x400
485 blk.37.attn_norm.weight 0xfe656620 0x3c00
486 blk.37.attn_output.weight 0xfe65a220 0x870000
487 blk.37.attn_q.weight 0xfeeca220 0x672000
488 blk.37.attn_q_norm.weight 0xff53c220 0x400
489 blk.37.attn_v.weight 0xff53c620 0x438000
490 blk.37.ffn_down.weight 0xff974620 0x1fa4000
491 blk.37.ffn_gate.weight 0x101918620 0x182b800
492 blk.37.ffn_norm.weight 0x103143e20 0x3c00
493 blk.37.ffn_up.weight 0x103147a20 0x182b800
494 blk.37.post_attention_norm.weight 0x104973220 0x3c00
495 blk.37.post_ffw_norm.weight 0x104976e20 0x3c00
496 blk.38.attn_k.weight 0x10497aa20 0x339000
497 blk.38.attn_k_norm.weight 0x104cb3a20 0x400
498 blk.38.attn_norm.weight 0x104cb3e20 0x3c00
499 blk.38.attn_output.weight 0x104cb7a20 0x870000
500 blk.38.attn_q.weight 0x105527a20 0x672000
501 blk.38.attn_q_norm.weight 0x105b99a20 0x400
502 blk.38.attn_v.weight 0x105b99e20 0x438000
503 blk.38.ffn_down.weight 0x105fd1e20 0x1fa4000
504 blk.38.ffn_gate.weight 0x107f75e20 0x182b800
505 blk.38.ffn_norm.weight 0x1097a1620 0x3c00
506 blk.38.ffn_up.weight 0x1097a5220 0x182b800
507 blk.38.post_attention_norm.weight 0x10afd0a20 0x3c00
508 blk.38.post_ffw_norm.weight 0x10afd4620 0x3c00
509 blk.39.attn_k.weight 0x10afd8220 0x339000
510 blk.39.attn_k_norm.weight 0x10b311220 0x400
511 blk.39.attn_norm.weight 0x10b311620 0x3c00
512 blk.39.attn_output.weight 0x10b315220 0x870000
513 blk.39.attn_q.weight 0x10bb85220 0x672000
514 blk.39.attn_q_norm.weight 0x10c1f7220 0x400
515 blk.39.attn_v.weight 0x10c1f7620 0x438000
516 blk.39.ffn_down.weight 0x10c62f620 0x1fa4000
517 blk.39.ffn_gate.weight 0x10e5d3620 0x182b800
518 blk.39.ffn_norm.weight 0x10fdfee20 0x3c00
519 blk.39.ffn_up.weight 0x10fe02a20 0x182b800
520 blk.39.post_attention_norm.weight 0x11162e220 0x3c00
521 blk.39.post_ffw_norm.weight 0x111631e20 0x3c00
522 blk.40.attn_k.weight 0x111635a20 0x339000
523 blk.40.attn_k_norm.weight 0x11196ea20 0x400
524 blk.40.attn_norm.weight 0x11196ee20 0x3c00
525 blk.40.attn_output.weight 0x111972a20 0x870000
526 blk.40.attn_q.weight 0x1121e2a20 0x672000
527 blk.40.attn_q_norm.weight 0x112854a20 0x400
528 blk.40.attn_v.weight 0x112854e20 0x438000
529 blk.40.ffn_down.weight 0x112c8ce20 0x1fa4000
530 blk.40.ffn_gate.weight 0x114c30e20 0x182b800
531 blk.40.ffn_norm.weight 0x11645c620 0x3c00
532 blk.40.ffn_up.weight 0x116460220 0x182b800
533 blk.40.post_attention_norm.weight 0x117c8ba20 0x3c00
534 blk.40.post_ffw_norm.weight 0x117c8f620 0x3c00
535 blk.41.attn_k.weight 0x117c93220 0x2df000
536 blk.41.attn_k_norm.weight 0x117f72220 0x400
537 blk.41.attn_norm.weight 0x117f72620 0x3c00
538 blk.41.attn_output.weight 0x117f76220 0x870000
539 blk.41.attn_q.weight 0x1187e6220 0x5be000
540 blk.41.attn_q_norm.weight 0x118da4220 0x400
541 blk.41.attn_v.weight 0x118da4620 0x339000
542 blk.41.ffn_down.weight 0x1190dd620 0x1fa4000
543 blk.41.ffn_gate.weight 0x11b081620 0x1588800
544 blk.41.ffn_norm.weight 0x11c609e20 0x3c00
545 blk.41.ffn_up.weight 0x11c60da20 0x1588800
546 blk.41.post_attention_norm.weight 0x11db96220 0x3c00
547 blk.41.post_ffw_norm.weight 0x11db99e20 0x3c00
548 blk.42.attn_k.weight 0x11db9da20 0x2df000
549 blk.42.attn_k_norm.weight 0x11de7ca20 0x400
550 blk.42.attn_norm.weight 0x11de7ce20 0x3c00
551 blk.42.attn_output.weight 0x11de80a20 0x870000
552 blk.42.attn_q.weight 0x11e6f0a20 0x5be000
553 blk.42.attn_q_norm.weight 0x11ecaea20 0x400
554 blk.42.attn_v.weight 0x11ecaee20 0x339000
555 blk.42.ffn_down.weight 0x11efe7e20 0x1fa4000
556 blk.42.ffn_gate.weight 0x120f8be20 0x1588800
557 blk.42.ffn_norm.weight 0x122514620 0x3c00
558 blk.42.ffn_up.weight 0x122518220 0x1588800
559 blk.42.post_attention_norm.weight 0x123aa0a20 0x3c00
560 blk.42.post_ffw_norm.weight 0x123aa4620 0x3c00
561 blk.43.attn_k.weight 0x123aa8220 0x2df000
562 blk.43.attn_k_norm.weight 0x123d87220 0x400
563 blk.43.attn_norm.weight 0x123d87620 0x3c00
564 blk.43.attn_output.weight 0x123d8b220 0x870000
565 blk.43.attn_q.weight 0x1245fb220 0x5be000
566 blk.43.attn_q_norm.weight 0x124bb9220 0x400
567 blk.43.attn_v.weight 0x124bb9620 0x339000
568 blk.43.ffn_down.weight 0x124ef2620 0x1fa4000
569 blk.43.ffn_gate.weight 0x126e96620 0x1588800
570 blk.43.ffn_norm.weight 0x12841ee20 0x3c00
571 blk.43.ffn_up.weight 0x128422a20 0x1588800
572 blk.43.post_attention_norm.weight 0x1299ab220 0x3c00
573 blk.43.post_ffw_norm.weight 0x1299aee20 0x3c00
574 blk.44.attn_k.weight 0x1299b2a20 0x339000
575 blk.44.attn_k_norm.weight 0x129ceba20 0x400
576 blk.44.attn_norm.weight 0x129cebe20 0x3c00
577 blk.44.attn_output.weight 0x129cefa20 0x870000
578 blk.44.attn_q.weight 0x12a55fa20 0x672000
579 blk.44.attn_q_norm.weight 0x12abd1a20 0x400
580 blk.44.attn_v.weight 0x12abd1e20 0x438000
581 blk.44.ffn_down.weight 0x12b009e20 0x1fa4000
582 blk.44.ffn_gate.weight 0x12cfade20 0x182b800
583 blk.44.ffn_norm.weight 0x12e7d9620 0x3c00
584 blk.44.ffn_up.weight 0x12e7dd220 0x182b800
585 blk.44.post_attention_norm.weight 0x130008a20 0x3c00
586 blk.44.post_ffw_norm.weight 0x13000c620 0x3c00
587 blk.45.attn_k.weight 0x130010220 0x339000
588 blk.45.attn_k_norm.weight 0x130349220 0x400
589 blk.45.attn_norm.weight 0x130349620 0x3c00
590 blk.45.attn_output.weight 0x13034d220 0x870000
591 blk.45.attn_q.weight 0x130bbd220 0x672000
592 blk.45.attn_q_norm.weight 0x13122f220 0x400
593 blk.45.attn_v.weight 0x13122f620 0x438000
594 blk.45.ffn_down.weight 0x131667620 0x1fa4000
595 blk.45.ffn_gate.weight 0x13360b620 0x182b800
596 blk.45.ffn_norm.weight 0x134e36e20 0x3c00
597 blk.45.ffn_up.weight 0x134e3aa20 0x182b800
598 blk.45.post_attention_norm.weight 0x136666220 0x3c00
599 blk.45.post_ffw_norm.weight 0x136669e20 0x3c00

Base Tensor Group : ~1B Elements

T_ID Tensor Layer Name Human Friendly Tensor Layer Name Elements Shape Type
0 output_norm.weight Output Normalization (W) (~4K) 3840 3840 x 1 x 1 x 1 F32
1 token_embd.weight Token Embedding (W) (~1B) 1006632960 3840 x 262144 x 1 x 1 IQ3_S
  • Total elements in base: ( ~1B) 1006636800
  • Percentage of total elements: 8.89%

Block 0 Tensor Group : ~224M Elements

T_ID Tensor Layer Name Human Friendly Tensor Layer Name Elements Shape Type
2 blk.0.attn_k.weight Block 0 Attention Key (W) ( ~8M) 7864320 3840 x 2048 x 1 x 1 IQ3_S
3 blk.0.attn_k_norm.weight Block 0 Attn_K_Norm (W) ( 256) 256 256 x 1 x 1 x 1 F32
4 blk.0.attn_norm.weight Block 0 Attention Normalization (W) ( ~4K) 3840 3840 x 1 x 1 x 1 F32
5 blk.0.attn_output.weight Block 0 Attention Output (W) (~16M) 15728640 4096 x 3840 x 1 x 1 Q4_K
6 blk.0.attn_q.weight Block 0 Attention Query (W) (~16M) 15728640 3840 x 4096 x 1 x 1 IQ3_S
7 blk.0.attn_q_norm.weight Block 0 Attn_Q_Norm (W) ( 256) 256 256 x 1 x 1 x 1 F32
8 blk.0.attn_v.weight Block 0 Attention Value (W) ( ~8M) 7864320 3840 x 2048 x 1 x 1 IQ4_NL
9 blk.0.ffn_down.weight Block 0 Feed-Forward Network "Down" (W) (~59M) 58982400 15360 x 3840 x 1 x 1 IQ4_NL
10 blk.0.ffn_gate.weight Block 0 Feed-Forward Network "Gate" (W) (~59M) 58982400 3840 x 15360 x 1 x 1 IQ3_S
11 blk.0.ffn_norm.weight Block 0 Feed-Forward Network Normalization (W) ( ~4K) 3840 3840 x 1 x 1 x 1 F32
12 blk.0.ffn_up.weight Block 0 Feed-Forward Network "Up" (W) (~59M) 58982400 3840 x 15360 x 1 x 1 IQ3_S
13 blk.0.post_attention_norm.weight Block 0 Post_Attention_Norm (W) ( ~4K) 3840 3840 x 1 x 1 x 1 F32
14 blk.0.post_ffw_norm.weight Block 0 Post_Ffw_Norm (W) ( ~4K) 3840 3840 x 1 x 1 x 1 F32
  • Total elements in blk.0: (~224M) 224148992
  • Percentage of total elements: 1.98%

Block 1 Tensor Group : ~224M 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) ( ~8M) 7864320 3840 x 2048 x 1 x 1 IQ3_S
16 blk.1.attn_k_norm.weight Block 1 Attn_K_Norm (W) ( 256) 256 256 x 1 x 1 x 1 F32
17 blk.1.attn_norm.weight Block 1 Attention Normalization (W) ( ~4K) 3840 3840 x 1 x 1 x 1 F32
18 blk.1.attn_output.weight Block 1 Attention Output (W) (~16M) 15728640 4096 x 3840 x 1 x 1 Q4_K
19 blk.1.attn_q.weight Block 1 Attention Query (W) (~16M) 15728640 3840 x 4096 x 1 x 1 IQ3_S
20 blk.1.attn_q_norm.weight Block 1 Attn_Q_Norm (W) ( 256) 256 256 x 1 x 1 x 1 F32
21 blk.1.attn_v.weight Block 1 Attention Value (W) ( ~8M) 7864320 3840 x 2048 x 1 x 1 IQ4_NL
22 blk.1.ffn_down.weight Block 1 Feed-Forward Network "Down" (W) (~59M) 58982400 15360 x 3840 x 1 x 1 IQ4_NL
23 blk.1.ffn_gate.weight Block 1 Feed-Forward Network "Gate" (W) (~59M) 58982400 3840 x 15360 x 1 x 1 IQ3_S
24 blk.1.ffn_norm.weight Block 1 Feed-Forward Network Normalization (W) ( ~4K) 3840 3840 x 1 x 1 x 1 F32
25 blk.1.ffn_up.weight Block 1 Feed-Forward Network "Up" (W) (~59M) 58982400 3840 x 15360 x 1 x 1 IQ3_S
26 blk.1.post_attention_norm.weight Block 1 Post_Attention_Norm (W) ( ~4K) 3840 3840 x 1 x 1 x 1 F32
27 blk.1.post_ffw_norm.weight Block 1 Post_Ffw_Norm (W) ( ~4K) 3840 3840 x 1 x 1 x 1 F32
  • Total elements in blk.1: (~224M) 224148992
  • Percentage of total elements: 1.98%

Block 2 Tensor Group : ~224M Elements

T_ID Tensor Layer Name Human Friendly Tensor Layer Name Elements Shape Type
28 blk.2.attn_k.weight Block 2 Attention Key (W) ( ~8M) 7864320 3840 x 2048 x 1 x 1 IQ3_S
29 blk.2.attn_k_norm.weight Block 2 Attn_K_Norm (W) ( 256) 256 256 x 1 x 1 x 1 F32
30 blk.2.attn_norm.weight Block 2 Attention Normalization (W) ( ~4K) 3840 3840 x 1 x 1 x 1 F32
31 blk.2.attn_output.weight Block 2 Attention Output (W) (~16M) 15728640 4096 x 3840 x 1 x 1 Q4_K
32 blk.2.attn_q.weight Block 2 Attention Query (W) (~16M) 15728640 3840 x 4096 x 1 x 1 IQ3_S
33 blk.2.attn_q_norm.weight Block 2 Attn_Q_Norm (W) ( 256) 256 256 x 1 x 1 x 1 F32
34 blk.2.attn_v.weight Block 2 Attention Value (W) ( ~8M) 7864320 3840 x 2048 x 1 x 1 IQ4_NL
35 blk.2.ffn_down.weight Block 2 Feed-Forward Network "Down" (W) (~59M) 58982400 15360 x 3840 x 1 x 1 IQ4_NL
36 blk.2.ffn_gate.weight Block 2 Feed-Forward Network "Gate" (W) (~59M) 58982400 3840 x 15360 x 1 x 1 IQ3_S
37 blk.2.ffn_norm.weight Block 2 Feed-Forward Network Normalization (W) ( ~4K) 3840 3840 x 1 x 1 x 1 F32
38 blk.2.ffn_up.weight Block 2 Feed-Forward Network "Up" (W) (~59M) 58982400 3840 x 15360 x 1 x 1 IQ3_S
39 blk.2.post_attention_norm.weight Block 2 Post_Attention_Norm (W) ( ~4K) 3840 3840 x 1 x 1 x 1 F32
40 blk.2.post_ffw_norm.weight Block 2 Post_Ffw_Norm (W) ( ~4K) 3840 3840 x 1 x 1 x 1 F32
  • Total elements in blk.2: (~224M) 224148992
  • Percentage of total elements: 1.98%

Block 3 Tensor Group : ~224M Elements

T_ID Tensor Layer Name Human Friendly Tensor Layer Name Elements Shape Type
41 blk.3.attn_k.weight Block 3 Attention Key (W) ( ~8M) 7864320 3840 x 2048 x 1 x 1 IQ3_S
42 blk.3.attn_k_norm.weight Block 3 Attn_K_Norm (W) ( 256) 256 256 x 1 x 1 x 1 F32
43 blk.3.attn_norm.weight Block 3 Attention Normalization (W) ( ~4K) 3840 3840 x 1 x 1 x 1 F32
44 blk.3.attn_output.weight Block 3 Attention Output (W) (~16M) 15728640 4096 x 3840 x 1 x 1 Q4_K
45 blk.3.attn_q.weight Block 3 Attention Query (W) (~16M) 15728640 3840 x 4096 x 1 x 1 IQ3_S
46 blk.3.attn_q_norm.weight Block 3 Attn_Q_Norm (W) ( 256) 256 256 x 1 x 1 x 1 F32
47 blk.3.attn_v.weight Block 3 Attention Value (W) ( ~8M) 7864320 3840 x 2048 x 1 x 1 IQ4_NL
48 blk.3.ffn_down.weight Block 3 Feed-Forward Network "Down" (W) (~59M) 58982400 15360 x 3840 x 1 x 1 IQ4_NL
49 blk.3.ffn_gate.weight Block 3 Feed-Forward Network "Gate" (W) (~59M) 58982400 3840 x 15360 x 1 x 1 IQ3_S
50 blk.3.ffn_norm.weight Block 3 Feed-Forward Network Normalization (W) ( ~4K) 3840 3840 x 1 x 1 x 1 F32
51 blk.3.ffn_up.weight Block 3 Feed-Forward Network "Up" (W) (~59M) 58982400 3840 x 15360 x 1 x 1 IQ3_S
52 blk.3.post_attention_norm.weight Block 3 Post_Attention_Norm (W) ( ~4K) 3840 3840 x 1 x 1 x 1 F32
53 blk.3.post_ffw_norm.weight Block 3 Post_Ffw_Norm (W) ( ~4K) 3840 3840 x 1 x 1 x 1 F32
  • Total elements in blk.3: (~224M) 224148992
  • Percentage of total elements: 1.98%

Block 4 Tensor Group : ~224M Elements

T_ID Tensor Layer Name Human Friendly Tensor Layer Name Elements Shape Type
54 blk.4.attn_k.weight Block 4 Attention Key (W) ( ~8M) 7864320 3840 x 2048 x 1 x 1 IQ3_S
55 blk.4.attn_k_norm.weight Block 4 Attn_K_Norm (W) ( 256) 256 256 x 1 x 1 x 1 F32
56 blk.4.attn_norm.weight Block 4 Attention Normalization (W) ( ~4K) 3840 3840 x 1 x 1 x 1 F32
57 blk.4.attn_output.weight Block 4 Attention Output (W) (~16M) 15728640 4096 x 3840 x 1 x 1 Q4_K
58 blk.4.attn_q.weight Block 4 Attention Query (W) (~16M) 15728640 3840 x 4096 x 1 x 1 IQ3_S
59 blk.4.attn_q_norm.weight Block 4 Attn_Q_Norm (W) ( 256) 256 256 x 1 x 1 x 1 F32
60 blk.4.attn_v.weight Block 4 Attention Value (W) ( ~8M) 7864320 3840 x 2048 x 1 x 1 IQ4_NL
61 blk.4.ffn_down.weight Block 4 Feed-Forward Network "Down" (W) (~59M) 58982400 15360 x 3840 x 1 x 1 IQ4_NL
62 blk.4.ffn_gate.weight Block 4 Feed-Forward Network "Gate" (W) (~59M) 58982400 3840 x 15360 x 1 x 1 IQ3_S
63 blk.4.ffn_norm.weight Block 4 Feed-Forward Network Normalization (W) ( ~4K) 3840 3840 x 1 x 1 x 1 F32
64 blk.4.ffn_up.weight Block 4 Feed-Forward Network "Up" (W) (~59M) 58982400 3840 x 15360 x 1 x 1 IQ3_S
65 blk.4.post_attention_norm.weight Block 4 Post_Attention_Norm (W) ( ~4K) 3840 3840 x 1 x 1 x 1 F32
66 blk.4.post_ffw_norm.weight Block 4 Post_Ffw_Norm (W) ( ~4K) 3840 3840 x 1 x 1 x 1 F32
  • Total elements in blk.4: (~224M) 224148992
  • Percentage of total elements: 1.98%

Block 5 Tensor Group : ~224M Elements

T_ID Tensor Layer Name Human Friendly Tensor Layer Name Elements Shape Type
67 blk.5.attn_k.weight Block 5 Attention Key (W) ( ~8M) 7864320 3840 x 2048 x 1 x 1 IQ3_S
68 blk.5.attn_k_norm.weight Block 5 Attn_K_Norm (W) ( 256) 256 256 x 1 x 1 x 1 F32
69 blk.5.attn_norm.weight Block 5 Attention Normalization (W) ( ~4K) 3840 3840 x 1 x 1 x 1 F32
70 blk.5.attn_output.weight Block 5 Attention Output (W) (~16M) 15728640 4096 x 3840 x 1 x 1 Q4_K
71 blk.5.attn_q.weight Block 5 Attention Query (W) (~16M) 15728640 3840 x 4096 x 1 x 1 IQ3_S
72 blk.5.attn_q_norm.weight Block 5 Attn_Q_Norm (W) ( 256) 256 256 x 1 x 1 x 1 F32
73 blk.5.attn_v.weight Block 5 Attention Value (W) ( ~8M) 7864320 3840 x 2048 x 1 x 1 IQ4_NL
74 blk.5.ffn_down.weight Block 5 Feed-Forward Network "Down" (W) (~59M) 58982400 15360 x 3840 x 1 x 1 IQ4_NL
75 blk.5.ffn_gate.weight Block 5 Feed-Forward Network "Gate" (W) (~59M) 58982400 3840 x 15360 x 1 x 1 IQ3_S
76 blk.5.ffn_norm.weight Block 5 Feed-Forward Network Normalization (W) ( ~4K) 3840 3840 x 1 x 1 x 1 F32
77 blk.5.ffn_up.weight Block 5 Feed-Forward Network "Up" (W) (~59M) 58982400 3840 x 15360 x 1 x 1 IQ3_S
78 blk.5.post_attention_norm.weight Block 5 Post_Attention_Norm (W) ( ~4K) 3840 3840 x 1 x 1 x 1 F32
79 blk.5.post_ffw_norm.weight Block 5 Post_Ffw_Norm (W) ( ~4K) 3840 3840 x 1 x 1 x 1 F32
  • Total elements in blk.5: (~224M) 224148992
  • Percentage of total elements: 1.98%

Block 6 Tensor Group : ~224M Elements

T_ID Tensor Layer Name Human Friendly Tensor Layer Name Elements Shape Type
80 blk.6.attn_k.weight Block 6 Attention Key (W) ( ~8M) 7864320 3840 x 2048 x 1 x 1 IQ3_S
81 blk.6.attn_k_norm.weight Block 6 Attn_K_Norm (W) ( 256) 256 256 x 1 x 1 x 1 F32
82 blk.6.attn_norm.weight Block 6 Attention Normalization (W) ( ~4K) 3840 3840 x 1 x 1 x 1 F32
83 blk.6.attn_output.weight Block 6 Attention Output (W) (~16M) 15728640 4096 x 3840 x 1 x 1 Q4_K
84 blk.6.attn_q.weight Block 6 Attention Query (W) (~16M) 15728640 3840 x 4096 x 1 x 1 IQ3_S
85 blk.6.attn_q_norm.weight Block 6 Attn_Q_Norm (W) ( 256) 256 256 x 1 x 1 x 1 F32
86 blk.6.attn_v.weight Block 6 Attention Value (W) ( ~8M) 7864320 3840 x 2048 x 1 x 1 IQ4_NL
87 blk.6.ffn_down.weight Block 6 Feed-Forward Network "Down" (W) (~59M) 58982400 15360 x 3840 x 1 x 1 IQ4_NL
88 blk.6.ffn_gate.weight Block 6 Feed-Forward Network "Gate" (W) (~59M) 58982400 3840 x 15360 x 1 x 1 IQ3_S
89 blk.6.ffn_norm.weight Block 6 Feed-Forward Network Normalization (W) ( ~4K) 3840 3840 x 1 x 1 x 1 F32
90 blk.6.ffn_up.weight Block 6 Feed-Forward Network "Up" (W) (~59M) 58982400 3840 x 15360 x 1 x 1 IQ3_S
91 blk.6.post_attention_norm.weight Block 6 Post_Attention_Norm (W) ( ~4K) 3840 3840 x 1 x 1 x 1 F32
92 blk.6.post_ffw_norm.weight Block 6 Post_Ffw_Norm (W) ( ~4K) 3840 3840 x 1 x 1 x 1 F32
  • Total elements in blk.6: (~224M) 224148992
  • Percentage of total elements: 1.98%

Block 7 Tensor Group : ~224M Elements

T_ID Tensor Layer Name Human Friendly Tensor Layer Name Elements Shape Type
93 blk.7.attn_k.weight Block 7 Attention Key (W) ( ~8M) 7864320 3840 x 2048 x 1 x 1 IQ3_S
94 blk.7.attn_k_norm.weight Block 7 Attn_K_Norm (W) ( 256) 256 256 x 1 x 1 x 1 F32
95 blk.7.attn_norm.weight Block 7 Attention Normalization (W) ( ~4K) 3840 3840 x 1 x 1 x 1 F32
96 blk.7.attn_output.weight Block 7 Attention Output (W) (~16M) 15728640 4096 x 3840 x 1 x 1 Q4_K
97 blk.7.attn_q.weight Block 7 Attention Query (W) (~16M) 15728640 3840 x 4096 x 1 x 1 IQ3_S
98 blk.7.attn_q_norm.weight Block 7 Attn_Q_Norm (W) ( 256) 256 256 x 1 x 1 x 1 F32
99 blk.7.attn_v.weight Block 7 Attention Value (W) ( ~8M) 7864320 3840 x 2048 x 1 x 1 IQ4_NL
100 blk.7.ffn_down.weight Block 7 Feed-Forward Network "Down" (W) (~59M) 58982400 15360 x 3840 x 1 x 1 IQ4_NL
101 blk.7.ffn_gate.weight Block 7 Feed-Forward Network "Gate" (W) (~59M) 58982400 3840 x 15360 x 1 x 1 IQ3_S
102 blk.7.ffn_norm.weight Block 7 Feed-Forward Network Normalization (W) ( ~4K) 3840 3840 x 1 x 1 x 1 F32
103 blk.7.ffn_up.weight Block 7 Feed-Forward Network "Up" (W) (~59M) 58982400 3840 x 15360 x 1 x 1 IQ3_S
104 blk.7.post_attention_norm.weight Block 7 Post_Attention_Norm (W) ( ~4K) 3840 3840 x 1 x 1 x 1 F32
105 blk.7.post_ffw_norm.weight Block 7 Post_Ffw_Norm (W) ( ~4K) 3840 3840 x 1 x 1 x 1 F32
  • Total elements in blk.7: (~224M) 224148992
  • Percentage of total elements: 1.98%

Block 8 Tensor Group : ~224M Elements

T_ID Tensor Layer Name Human Friendly Tensor Layer Name Elements Shape Type
106 blk.8.attn_k.weight Block 8 Attention Key (W) ( ~8M) 7864320 3840 x 2048 x 1 x 1 IQ3_S
107 blk.8.attn_k_norm.weight Block 8 Attn_K_Norm (W) ( 256) 256 256 x 1 x 1 x 1 F32
108 blk.8.attn_norm.weight Block 8 Attention Normalization (W) ( ~4K) 3840 3840 x 1 x 1 x 1 F32
109 blk.8.attn_output.weight Block 8 Attention Output (W) (~16M) 15728640 4096 x 3840 x 1 x 1 Q4_K
110 blk.8.attn_q.weight Block 8 Attention Query (W) (~16M) 15728640 3840 x 4096 x 1 x 1 IQ3_S
111 blk.8.attn_q_norm.weight Block 8 Attn_Q_Norm (W) ( 256) 256 256 x 1 x 1 x 1 F32
112 blk.8.attn_v.weight Block 8 Attention Value (W) ( ~8M) 7864320 3840 x 2048 x 1 x 1 IQ4_NL
113 blk.8.ffn_down.weight Block 8 Feed-Forward Network "Down" (W) (~59M) 58982400 15360 x 3840 x 1 x 1 IQ4_NL
114 blk.8.ffn_gate.weight Block 8 Feed-Forward Network "Gate" (W) (~59M) 58982400 3840 x 15360 x 1 x 1 IQ3_S
115 blk.8.ffn_norm.weight Block 8 Feed-Forward Network Normalization (W) ( ~4K) 3840 3840 x 1 x 1 x 1 F32
116 blk.8.ffn_up.weight Block 8 Feed-Forward Network "Up" (W) (~59M) 58982400 3840 x 15360 x 1 x 1 IQ3_S
117 blk.8.post_attention_norm.weight Block 8 Post_Attention_Norm (W) ( ~4K) 3840 3840 x 1 x 1 x 1 F32
118 blk.8.post_ffw_norm.weight Block 8 Post_Ffw_Norm (W) ( ~4K) 3840 3840 x 1 x 1 x 1 F32
  • Total elements in blk.8: (~224M) 224148992
  • Percentage of total elements: 1.98%

Block 9 Tensor Group : ~224M Elements

T_ID Tensor Layer Name Human Friendly Tensor Layer Name Elements Shape Type
119 blk.9.attn_k.weight Block 9 Attention Key (W) ( ~8M) 7864320 3840 x 2048 x 1 x 1 IQ3_S
120 blk.9.attn_k_norm.weight Block 9 Attn_K_Norm (W) ( 256) 256 256 x 1 x 1 x 1 F32
121 blk.9.attn_norm.weight Block 9 Attention Normalization (W) ( ~4K) 3840 3840 x 1 x 1 x 1 F32
122 blk.9.attn_output.weight Block 9 Attention Output (W) (~16M) 15728640 4096 x 3840 x 1 x 1 Q4_K
123 blk.9.attn_q.weight Block 9 Attention Query (W) (~16M) 15728640 3840 x 4096 x 1 x 1 IQ3_S
124 blk.9.attn_q_norm.weight Block 9 Attn_Q_Norm (W) ( 256) 256 256 x 1 x 1 x 1 F32
125 blk.9.attn_v.weight Block 9 Attention Value (W) ( ~8M) 7864320 3840 x 2048 x 1 x 1 IQ4_NL
126 blk.9.ffn_down.weight Block 9 Feed-Forward Network "Down" (W) (~59M) 58982400 15360 x 3840 x 1 x 1 IQ4_NL
127 blk.9.ffn_gate.weight Block 9 Feed-Forward Network "Gate" (W) (~59M) 58982400 3840 x 15360 x 1 x 1 IQ3_S
128 blk.9.ffn_norm.weight Block 9 Feed-Forward Network Normalization (W) ( ~4K) 3840 3840 x 1 x 1 x 1 F32
129 blk.9.ffn_up.weight Block 9 Feed-Forward Network "Up" (W) (~59M) 58982400 3840 x 15360 x 1 x 1 IQ3_S
130 blk.9.post_attention_norm.weight Block 9 Post_Attention_Norm (W) ( ~4K) 3840 3840 x 1 x 1 x 1 F32
131 blk.9.post_ffw_norm.weight Block 9 Post_Ffw_Norm (W) ( ~4K) 3840 3840 x 1 x 1 x 1 F32
  • Total elements in blk.9: (~224M) 224148992
  • Percentage of total elements: 1.98%

Block 10 Tensor Group : ~224M Elements

T_ID Tensor Layer Name Human Friendly Tensor Layer Name Elements Shape Type
132 blk.10.attn_k.weight Block 10 Attention Key (W) ( ~8M) 7864320 3840 x 2048 x 1 x 1 IQ3_S
133 blk.10.attn_k_norm.weight Block 10 Attn_K_Norm (W) ( 256) 256 256 x 1 x 1 x 1 F32
134 blk.10.attn_norm.weight Block 10 Attention Normalization (W) ( ~4K) 3840 3840 x 1 x 1 x 1 F32
135 blk.10.attn_output.weight Block 10 Attention Output (W) (~16M) 15728640 4096 x 3840 x 1 x 1 Q4_K
136 blk.10.attn_q.weight Block 10 Attention Query (W) (~16M) 15728640 3840 x 4096 x 1 x 1 IQ3_S
137 blk.10.attn_q_norm.weight Block 10 Attn_Q_Norm (W) ( 256) 256 256 x 1 x 1 x 1 F32
138 blk.10.attn_v.weight Block 10 Attention Value (W) ( ~8M) 7864320 3840 x 2048 x 1 x 1 IQ4_NL
139 blk.10.ffn_down.weight Block 10 Feed-Forward Network "Down" (W) (~59M) 58982400 15360 x 3840 x 1 x 1 IQ4_NL
140 blk.10.ffn_gate.weight Block 10 Feed-Forward Network "Gate" (W) (~59M) 58982400 3840 x 15360 x 1 x 1 IQ3_S
141 blk.10.ffn_norm.weight Block 10 Feed-Forward Network Normalization (W) ( ~4K) 3840 3840 x 1 x 1 x 1 F32
142 blk.10.ffn_up.weight Block 10 Feed-Forward Network "Up" (W) (~59M) 58982400 3840 x 15360 x 1 x 1 IQ3_S
143 blk.10.post_attention_norm.weight Block 10 Post_Attention_Norm (W) ( ~4K) 3840 3840 x 1 x 1 x 1 F32
144 blk.10.post_ffw_norm.weight Block 10 Post_Ffw_Norm (W) ( ~4K) 3840 3840 x 1 x 1 x 1 F32
  • Total elements in blk.10: (~224M) 224148992
  • Percentage of total elements: 1.98%

Block 11 Tensor Group : ~224M Elements

T_ID Tensor Layer Name Human Friendly Tensor Layer Name Elements Shape Type
145 blk.11.attn_k.weight Block 11 Attention Key (W) ( ~8M) 7864320 3840 x 2048 x 1 x 1 IQ3_XXS
146 blk.11.attn_k_norm.weight Block 11 Attn_K_Norm (W) ( 256) 256 256 x 1 x 1 x 1 F32
147 blk.11.attn_norm.weight Block 11 Attention Normalization (W) ( ~4K) 3840 3840 x 1 x 1 x 1 F32
148 blk.11.attn_output.weight Block 11 Attention Output (W) (~16M) 15728640 4096 x 3840 x 1 x 1 Q4_K
149 blk.11.attn_q.weight Block 11 Attention Query (W) (~16M) 15728640 3840 x 4096 x 1 x 1 IQ3_XXS
150 blk.11.attn_q_norm.weight Block 11 Attn_Q_Norm (W) ( 256) 256 256 x 1 x 1 x 1 F32
151 blk.11.attn_v.weight Block 11 Attention Value (W) ( ~8M) 7864320 3840 x 2048 x 1 x 1 IQ3_S
152 blk.11.ffn_down.weight Block 11 Feed-Forward Network "Down" (W) (~59M) 58982400 15360 x 3840 x 1 x 1 IQ4_NL
153 blk.11.ffn_gate.weight Block 11 Feed-Forward Network "Gate" (W) (~59M) 58982400 3840 x 15360 x 1 x 1 IQ3_XXS
154 blk.11.ffn_norm.weight Block 11 Feed-Forward Network Normalization (W) ( ~4K) 3840 3840 x 1 x 1 x 1 F32
155 blk.11.ffn_up.weight Block 11 Feed-Forward Network "Up" (W) (~59M) 58982400 3840 x 15360 x 1 x 1 IQ3_XXS
156 blk.11.post_attention_norm.weight Block 11 Post_Attention_Norm (W) ( ~4K) 3840 3840 x 1 x 1 x 1 F32
157 blk.11.post_ffw_norm.weight Block 11 Post_Ffw_Norm (W) ( ~4K) 3840 3840 x 1 x 1 x 1 F32
  • Total elements in blk.11: (~224M) 224148992
  • Percentage of total elements: 1.98%

Block 12 Tensor Group : ~224M Elements

T_ID Tensor Layer Name Human Friendly Tensor Layer Name Elements Shape Type
158 blk.12.attn_k.weight Block 12 Attention Key (W) ( ~8M) 7864320 3840 x 2048 x 1 x 1 IQ3_XXS
159 blk.12.attn_k_norm.weight Block 12 Attn_K_Norm (W) ( 256) 256 256 x 1 x 1 x 1 F32
160 blk.12.attn_norm.weight Block 12 Attention Normalization (W) ( ~4K) 3840 3840 x 1 x 1 x 1 F32
161 blk.12.attn_output.weight Block 12 Attention Output (W) (~16M) 15728640 4096 x 3840 x 1 x 1 Q4_K
162 blk.12.attn_q.weight Block 12 Attention Query (W) (~16M) 15728640 3840 x 4096 x 1 x 1 IQ3_XXS
163 blk.12.attn_q_norm.weight Block 12 Attn_Q_Norm (W) ( 256) 256 256 x 1 x 1 x 1 F32
164 blk.12.attn_v.weight Block 12 Attention Value (W) ( ~8M) 7864320 3840 x 2048 x 1 x 1 IQ3_S
165 blk.12.ffn_down.weight Block 12 Feed-Forward Network "Down" (W) (~59M) 58982400 15360 x 3840 x 1 x 1 IQ4_NL
166 blk.12.ffn_gate.weight Block 12 Feed-Forward Network "Gate" (W) (~59M) 58982400 3840 x 15360 x 1 x 1 IQ3_XXS
167 blk.12.ffn_norm.weight Block 12 Feed-Forward Network Normalization (W) ( ~4K) 3840 3840 x 1 x 1 x 1 F32
168 blk.12.ffn_up.weight Block 12 Feed-Forward Network "Up" (W) (~59M) 58982400 3840 x 15360 x 1 x 1 IQ3_XXS
169 blk.12.post_attention_norm.weight Block 12 Post_Attention_Norm (W) ( ~4K) 3840 3840 x 1 x 1 x 1 F32
170 blk.12.post_ffw_norm.weight Block 12 Post_Ffw_Norm (W) ( ~4K) 3840 3840 x 1 x 1 x 1 F32
  • Total elements in blk.12: (~224M) 224148992
  • Percentage of total elements: 1.98%

Block 13 Tensor Group : ~224M Elements

T_ID Tensor Layer Name Human Friendly Tensor Layer Name Elements Shape Type
171 blk.13.attn_k.weight Block 13 Attention Key (W) ( ~8M) 7864320 3840 x 2048 x 1 x 1 IQ3_XXS
172 blk.13.attn_k_norm.weight Block 13 Attn_K_Norm (W) ( 256) 256 256 x 1 x 1 x 1 F32
173 blk.13.attn_norm.weight Block 13 Attention Normalization (W) ( ~4K) 3840 3840 x 1 x 1 x 1 F32
174 blk.13.attn_output.weight Block 13 Attention Output (W) (~16M) 15728640 4096 x 3840 x 1 x 1 Q4_K
175 blk.13.attn_q.weight Block 13 Attention Query (W) (~16M) 15728640 3840 x 4096 x 1 x 1 IQ3_XXS
176 blk.13.attn_q_norm.weight Block 13 Attn_Q_Norm (W) ( 256) 256 256 x 1 x 1 x 1 F32
177 blk.13.attn_v.weight Block 13 Attention Value (W) ( ~8M) 7864320 3840 x 2048 x 1 x 1 IQ3_S
178 blk.13.ffn_down.weight Block 13 Feed-Forward Network "Down" (W) (~59M) 58982400 15360 x 3840 x 1 x 1 IQ4_NL
179 blk.13.ffn_gate.weight Block 13 Feed-Forward Network "Gate" (W) (~59M) 58982400 3840 x 15360 x 1 x 1 IQ3_XXS
180 blk.13.ffn_norm.weight Block 13 Feed-Forward Network Normalization (W) ( ~4K) 3840 3840 x 1 x 1 x 1 F32
181 blk.13.ffn_up.weight Block 13 Feed-Forward Network "Up" (W) (~59M) 58982400 3840 x 15360 x 1 x 1 IQ3_XXS
182 blk.13.post_attention_norm.weight Block 13 Post_Attention_Norm (W) ( ~4K) 3840 3840 x 1 x 1 x 1 F32
183 blk.13.post_ffw_norm.weight Block 13 Post_Ffw_Norm (W) ( ~4K) 3840 3840 x 1 x 1 x 1 F32
  • Total elements in blk.13: (~224M) 224148992
  • Percentage of total elements: 1.98%

Block 14 Tensor Group : ~224M Elements

T_ID Tensor Layer Name Human Friendly Tensor Layer Name Elements Shape Type
184 blk.14.attn_k.weight Block 14 Attention Key (W) ( ~8M) 7864320 3840 x 2048 x 1 x 1 IQ3_XXS
185 blk.14.attn_k_norm.weight Block 14 Attn_K_Norm (W) ( 256) 256 256 x 1 x 1 x 1 F32
186 blk.14.attn_norm.weight Block 14 Attention Normalization (W) ( ~4K) 3840 3840 x 1 x 1 x 1 F32
187 blk.14.attn_output.weight Block 14 Attention Output (W) (~16M) 15728640 4096 x 3840 x 1 x 1 Q4_K
188 blk.14.attn_q.weight Block 14 Attention Query (W) (~16M) 15728640 3840 x 4096 x 1 x 1 IQ3_XXS
189 blk.14.attn_q_norm.weight Block 14 Attn_Q_Norm (W) ( 256) 256 256 x 1 x 1 x 1 F32
190 blk.14.attn_v.weight Block 14 Attention Value (W) ( ~8M) 7864320 3840 x 2048 x 1 x 1 IQ3_S
191 blk.14.ffn_down.weight Block 14 Feed-Forward Network "Down" (W) (~59M) 58982400 15360 x 3840 x 1 x 1 IQ4_NL
192 blk.14.ffn_gate.weight Block 14 Feed-Forward Network "Gate" (W) (~59M) 58982400 3840 x 15360 x 1 x 1 IQ3_XXS
193 blk.14.ffn_norm.weight Block 14 Feed-Forward Network Normalization (W) ( ~4K) 3840 3840 x 1 x 1 x 1 F32
194 blk.14.ffn_up.weight Block 14 Feed-Forward Network "Up" (W) (~59M) 58982400 3840 x 15360 x 1 x 1 IQ3_XXS
195 blk.14.post_attention_norm.weight Block 14 Post_Attention_Norm (W) ( ~4K) 3840 3840 x 1 x 1 x 1 F32
196 blk.14.post_ffw_norm.weight Block 14 Post_Ffw_Norm (W) ( ~4K) 3840 3840 x 1 x 1 x 1 F32
  • Total elements in blk.14: (~224M) 224148992
  • Percentage of total elements: 1.98%

Block 15 Tensor Group : ~224M Elements

T_ID Tensor Layer Name Human Friendly Tensor Layer Name Elements Shape Type
197 blk.15.attn_k.weight Block 15 Attention Key (W) ( ~8M) 7864320 3840 x 2048 x 1 x 1 IQ3_XXS
198 blk.15.attn_k_norm.weight Block 15 Attn_K_Norm (W) ( 256) 256 256 x 1 x 1 x 1 F32
199 blk.15.attn_norm.weight Block 15 Attention Normalization (W) ( ~4K) 3840 3840 x 1 x 1 x 1 F32
200 blk.15.attn_output.weight Block 15 Attention Output (W) (~16M) 15728640 4096 x 3840 x 1 x 1 Q4_K
201 blk.15.attn_q.weight Block 15 Attention Query (W) (~16M) 15728640 3840 x 4096 x 1 x 1 IQ3_XXS
202 blk.15.attn_q_norm.weight Block 15 Attn_Q_Norm (W) ( 256) 256 256 x 1 x 1 x 1 F32
203 blk.15.attn_v.weight Block 15 Attention Value (W) ( ~8M) 7864320 3840 x 2048 x 1 x 1 IQ3_S
204 blk.15.ffn_down.weight Block 15 Feed-Forward Network "Down" (W) (~59M) 58982400 15360 x 3840 x 1 x 1 IQ4_NL
205 blk.15.ffn_gate.weight Block 15 Feed-Forward Network "Gate" (W) (~59M) 58982400 3840 x 15360 x 1 x 1 IQ3_XXS
206 blk.15.ffn_norm.weight Block 15 Feed-Forward Network Normalization (W) ( ~4K) 3840 3840 x 1 x 1 x 1 F32
207 blk.15.ffn_up.weight Block 15 Feed-Forward Network "Up" (W) (~59M) 58982400 3840 x 15360 x 1 x 1 IQ3_XXS
208 blk.15.post_attention_norm.weight Block 15 Post_Attention_Norm (W) ( ~4K) 3840 3840 x 1 x 1 x 1 F32
209 blk.15.post_ffw_norm.weight Block 15 Post_Ffw_Norm (W) ( ~4K) 3840 3840 x 1 x 1 x 1 F32
  • Total elements in blk.15: (~224M) 224148992
  • Percentage of total elements: 1.98%

Block 16 Tensor Group : ~224M Elements

T_ID Tensor Layer Name Human Friendly Tensor Layer Name Elements Shape Type
210 blk.16.attn_k.weight Block 16 Attention Key (W) ( ~8M) 7864320 3840 x 2048 x 1 x 1 IQ3_XXS
211 blk.16.attn_k_norm.weight Block 16 Attn_K_Norm (W) ( 256) 256 256 x 1 x 1 x 1 F32
212 blk.16.attn_norm.weight Block 16 Attention Normalization (W) ( ~4K) 3840 3840 x 1 x 1 x 1 F32
213 blk.16.attn_output.weight Block 16 Attention Output (W) (~16M) 15728640 4096 x 3840 x 1 x 1 Q4_K
214 blk.16.attn_q.weight Block 16 Attention Query (W) (~16M) 15728640 3840 x 4096 x 1 x 1 IQ3_XXS
215 blk.16.attn_q_norm.weight Block 16 Attn_Q_Norm (W) ( 256) 256 256 x 1 x 1 x 1 F32
216 blk.16.attn_v.weight Block 16 Attention Value (W) ( ~8M) 7864320 3840 x 2048 x 1 x 1 IQ3_S
217 blk.16.ffn_down.weight Block 16 Feed-Forward Network "Down" (W) (~59M) 58982400 15360 x 3840 x 1 x 1 IQ4_NL
218 blk.16.ffn_gate.weight Block 16 Feed-Forward Network "Gate" (W) (~59M) 58982400 3840 x 15360 x 1 x 1 IQ3_XXS
219 blk.16.ffn_norm.weight Block 16 Feed-Forward Network Normalization (W) ( ~4K) 3840 3840 x 1 x 1 x 1 F32
220 blk.16.ffn_up.weight Block 16 Feed-Forward Network "Up" (W) (~59M) 58982400 3840 x 15360 x 1 x 1 IQ3_XXS
221 blk.16.post_attention_norm.weight Block 16 Post_Attention_Norm (W) ( ~4K) 3840 3840 x 1 x 1 x 1 F32
222 blk.16.post_ffw_norm.weight Block 16 Post_Ffw_Norm (W) ( ~4K) 3840 3840 x 1 x 1 x 1 F32
  • Total elements in blk.16: (~224M) 224148992
  • Percentage of total elements: 1.98%

Block 17 Tensor Group : ~224M Elements

T_ID Tensor Layer Name Human Friendly Tensor Layer Name Elements Shape Type
223 blk.17.attn_k.weight Block 17 Attention Key (W) ( ~8M) 7864320 3840 x 2048 x 1 x 1 IQ3_XXS
224 blk.17.attn_k_norm.weight Block 17 Attn_K_Norm (W) ( 256) 256 256 x 1 x 1 x 1 F32
225 blk.17.attn_norm.weight Block 17 Attention Normalization (W) ( ~4K) 3840 3840 x 1 x 1 x 1 F32
226 blk.17.attn_output.weight Block 17 Attention Output (W) (~16M) 15728640 4096 x 3840 x 1 x 1 Q4_K
227 blk.17.attn_q.weight Block 17 Attention Query (W) (~16M) 15728640 3840 x 4096 x 1 x 1 IQ3_XXS
228 blk.17.attn_q_norm.weight Block 17 Attn_Q_Norm (W) ( 256) 256 256 x 1 x 1 x 1 F32
229 blk.17.attn_v.weight Block 17 Attention Value (W) ( ~8M) 7864320 3840 x 2048 x 1 x 1 IQ3_S
230 blk.17.ffn_down.weight Block 17 Feed-Forward Network "Down" (W) (~59M) 58982400 15360 x 3840 x 1 x 1 IQ4_NL
231 blk.17.ffn_gate.weight Block 17 Feed-Forward Network "Gate" (W) (~59M) 58982400 3840 x 15360 x 1 x 1 IQ3_XXS
232 blk.17.ffn_norm.weight Block 17 Feed-Forward Network Normalization (W) ( ~4K) 3840 3840 x 1 x 1 x 1 F32
233 blk.17.ffn_up.weight Block 17 Feed-Forward Network "Up" (W) (~59M) 58982400 3840 x 15360 x 1 x 1 IQ3_XXS
234 blk.17.post_attention_norm.weight Block 17 Post_Attention_Norm (W) ( ~4K) 3840 3840 x 1 x 1 x 1 F32
235 blk.17.post_ffw_norm.weight Block 17 Post_Ffw_Norm (W) ( ~4K) 3840 3840 x 1 x 1 x 1 F32
  • Total elements in blk.17: (~224M) 224148992
  • Percentage of total elements: 1.98%

Block 18 Tensor Group : ~224M Elements

T_ID Tensor Layer Name Human Friendly Tensor Layer Name Elements Shape Type
236 blk.18.attn_k.weight Block 18 Attention Key (W) ( ~8M) 7864320 3840 x 2048 x 1 x 1 IQ3_XXS
237 blk.18.attn_k_norm.weight Block 18 Attn_K_Norm (W) ( 256) 256 256 x 1 x 1 x 1 F32
238 blk.18.attn_norm.weight Block 18 Attention Normalization (W) ( ~4K) 3840 3840 x 1 x 1 x 1 F32
239 blk.18.attn_output.weight Block 18 Attention Output (W) (~16M) 15728640 4096 x 3840 x 1 x 1 Q4_K
240 blk.18.attn_q.weight Block 18 Attention Query (W) (~16M) 15728640 3840 x 4096 x 1 x 1 IQ3_XXS
241 blk.18.attn_q_norm.weight Block 18 Attn_Q_Norm (W) ( 256) 256 256 x 1 x 1 x 1 F32
242 blk.18.attn_v.weight Block 18 Attention Value (W) ( ~8M) 7864320 3840 x 2048 x 1 x 1 IQ3_S
243 blk.18.ffn_down.weight Block 18 Feed-Forward Network "Down" (W) (~59M) 58982400 15360 x 3840 x 1 x 1 IQ4_NL
244 blk.18.ffn_gate.weight Block 18 Feed-Forward Network "Gate" (W) (~59M) 58982400 3840 x 15360 x 1 x 1 IQ3_XXS
245 blk.18.ffn_norm.weight Block 18 Feed-Forward Network Normalization (W) ( ~4K) 3840 3840 x 1 x 1 x 1 F32
246 blk.18.ffn_up.weight Block 18 Feed-Forward Network "Up" (W) (~59M) 58982400 3840 x 15360 x 1 x 1 IQ3_XXS
247 blk.18.post_attention_norm.weight Block 18 Post_Attention_Norm (W) ( ~4K) 3840 3840 x 1 x 1 x 1 F32
248 blk.18.post_ffw_norm.weight Block 18 Post_Ffw_Norm (W) ( ~4K) 3840 3840 x 1 x 1 x 1 F32
  • Total elements in blk.18: (~224M) 224148992
  • Percentage of total elements: 1.98%

Block 19 Tensor Group : ~224M Elements

T_ID Tensor Layer Name Human Friendly Tensor Layer Name Elements Shape Type
249 blk.19.attn_k.weight Block 19 Attention Key (W) ( ~8M) 7864320 3840 x 2048 x 1 x 1 IQ3_XXS
250 blk.19.attn_k_norm.weight Block 19 Attn_K_Norm (W) ( 256) 256 256 x 1 x 1 x 1 F32
251 blk.19.attn_norm.weight Block 19 Attention Normalization (W) ( ~4K) 3840 3840 x 1 x 1 x 1 F32
252 blk.19.attn_output.weight Block 19 Attention Output (W) (~16M) 15728640 4096 x 3840 x 1 x 1 Q4_K
253 blk.19.attn_q.weight Block 19 Attention Query (W) (~16M) 15728640 3840 x 4096 x 1 x 1 IQ3_XXS
254 blk.19.attn_q_norm.weight Block 19 Attn_Q_Norm (W) ( 256) 256 256 x 1 x 1 x 1 F32
255 blk.19.attn_v.weight Block 19 Attention Value (W) ( ~8M) 7864320 3840 x 2048 x 1 x 1 IQ3_S
256 blk.19.ffn_down.weight Block 19 Feed-Forward Network "Down" (W) (~59M) 58982400 15360 x 3840 x 1 x 1 IQ4_NL
257 blk.19.ffn_gate.weight Block 19 Feed-Forward Network "Gate" (W) (~59M) 58982400 3840 x 15360 x 1 x 1 IQ3_XXS
258 blk.19.ffn_norm.weight Block 19 Feed-Forward Network Normalization (W) ( ~4K) 3840 3840 x 1 x 1 x 1 F32
259 blk.19.ffn_up.weight Block 19 Feed-Forward Network "Up" (W) (~59M) 58982400 3840 x 15360 x 1 x 1 IQ3_XXS
260 blk.19.post_attention_norm.weight Block 19 Post_Attention_Norm (W) ( ~4K) 3840 3840 x 1 x 1 x 1 F32
261 blk.19.post_ffw_norm.weight Block 19 Post_Ffw_Norm (W) ( ~4K) 3840 3840 x 1 x 1 x 1 F32
  • Total elements in blk.19: (~224M) 224148992
  • Percentage of total elements: 1.98%

Block 20 Tensor Group : ~224M Elements

T_ID Tensor Layer Name Human Friendly Tensor Layer Name Elements Shape Type
262 blk.20.attn_k.weight Block 20 Attention Key (W) ( ~8M) 7864320 3840 x 2048 x 1 x 1 IQ3_XXS
263 blk.20.attn_k_norm.weight Block 20 Attn_K_Norm (W) ( 256) 256 256 x 1 x 1 x 1 F32
264 blk.20.attn_norm.weight Block 20 Attention Normalization (W) ( ~4K) 3840 3840 x 1 x 1 x 1 F32
265 blk.20.attn_output.weight Block 20 Attention Output (W) (~16M) 15728640 4096 x 3840 x 1 x 1 Q4_K
266 blk.20.attn_q.weight Block 20 Attention Query (W) (~16M) 15728640 3840 x 4096 x 1 x 1 IQ3_XXS
267 blk.20.attn_q_norm.weight Block 20 Attn_Q_Norm (W) ( 256) 256 256 x 1 x 1 x 1 F32
268 blk.20.attn_v.weight Block 20 Attention Value (W) ( ~8M) 7864320 3840 x 2048 x 1 x 1 IQ3_S
269 blk.20.ffn_down.weight Block 20 Feed-Forward Network "Down" (W) (~59M) 58982400 15360 x 3840 x 1 x 1 IQ4_NL
270 blk.20.ffn_gate.weight Block 20 Feed-Forward Network "Gate" (W) (~59M) 58982400 3840 x 15360 x 1 x 1 IQ3_XXS
271 blk.20.ffn_norm.weight Block 20 Feed-Forward Network Normalization (W) ( ~4K) 3840 3840 x 1 x 1 x 1 F32
272 blk.20.ffn_up.weight Block 20 Feed-Forward Network "Up" (W) (~59M) 58982400 3840 x 15360 x 1 x 1 IQ3_XXS
273 blk.20.post_attention_norm.weight Block 20 Post_Attention_Norm (W) ( ~4K) 3840 3840 x 1 x 1 x 1 F32
274 blk.20.post_ffw_norm.weight Block 20 Post_Ffw_Norm (W) ( ~4K) 3840 3840 x 1 x 1 x 1 F32
  • Total elements in blk.20: (~224M) 224148992
  • Percentage of total elements: 1.98%

Block 21 Tensor Group : ~224M Elements

T_ID Tensor Layer Name Human Friendly Tensor Layer Name Elements Shape Type
275 blk.21.attn_k.weight Block 21 Attention Key (W) ( ~8M) 7864320 3840 x 2048 x 1 x 1 IQ3_XXS
276 blk.21.attn_k_norm.weight Block 21 Attn_K_Norm (W) ( 256) 256 256 x 1 x 1 x 1 F32
277 blk.21.attn_norm.weight Block 21 Attention Normalization (W) ( ~4K) 3840 3840 x 1 x 1 x 1 F32
278 blk.21.attn_output.weight Block 21 Attention Output (W) (~16M) 15728640 4096 x 3840 x 1 x 1 Q4_K
279 blk.21.attn_q.weight Block 21 Attention Query (W) (~16M) 15728640 3840 x 4096 x 1 x 1 IQ3_XXS
280 blk.21.attn_q_norm.weight Block 21 Attn_Q_Norm (W) ( 256) 256 256 x 1 x 1 x 1 F32
281 blk.21.attn_v.weight Block 21 Attention Value (W) ( ~8M) 7864320 3840 x 2048 x 1 x 1 IQ3_S
282 blk.21.ffn_down.weight Block 21 Feed-Forward Network "Down" (W) (~59M) 58982400 15360 x 3840 x 1 x 1 IQ4_NL
283 blk.21.ffn_gate.weight Block 21 Feed-Forward Network "Gate" (W) (~59M) 58982400 3840 x 15360 x 1 x 1 IQ3_XXS
284 blk.21.ffn_norm.weight Block 21 Feed-Forward Network Normalization (W) ( ~4K) 3840 3840 x 1 x 1 x 1 F32
285 blk.21.ffn_up.weight Block 21 Feed-Forward Network "Up" (W) (~59M) 58982400 3840 x 15360 x 1 x 1 IQ3_XXS
286 blk.21.post_attention_norm.weight Block 21 Post_Attention_Norm (W) ( ~4K) 3840 3840 x 1 x 1 x 1 F32
287 blk.21.post_ffw_norm.weight Block 21 Post_Ffw_Norm (W) ( ~4K) 3840 3840 x 1 x 1 x 1 F32
  • Total elements in blk.21: (~224M) 224148992
  • Percentage of total elements: 1.98%

Block 22 Tensor Group : ~224M Elements

T_ID Tensor Layer Name Human Friendly Tensor Layer Name Elements Shape Type
288 blk.22.attn_k.weight Block 22 Attention Key (W) ( ~8M) 7864320 3840 x 2048 x 1 x 1 IQ3_XXS
289 blk.22.attn_k_norm.weight Block 22 Attn_K_Norm (W) ( 256) 256 256 x 1 x 1 x 1 F32
290 blk.22.attn_norm.weight Block 22 Attention Normalization (W) ( ~4K) 3840 3840 x 1 x 1 x 1 F32
291 blk.22.attn_output.weight Block 22 Attention Output (W) (~16M) 15728640 4096 x 3840 x 1 x 1 Q4_K
292 blk.22.attn_q.weight Block 22 Attention Query (W) (~16M) 15728640 3840 x 4096 x 1 x 1 IQ3_XXS
293 blk.22.attn_q_norm.weight Block 22 Attn_Q_Norm (W) ( 256) 256 256 x 1 x 1 x 1 F32
294 blk.22.attn_v.weight Block 22 Attention Value (W) ( ~8M) 7864320 3840 x 2048 x 1 x 1 IQ3_S
295 blk.22.ffn_down.weight Block 22 Feed-Forward Network "Down" (W) (~59M) 58982400 15360 x 3840 x 1 x 1 IQ4_NL
296 blk.22.ffn_gate.weight Block 22 Feed-Forward Network "Gate" (W) (~59M) 58982400 3840 x 15360 x 1 x 1 IQ3_XXS
297 blk.22.ffn_norm.weight Block 22 Feed-Forward Network Normalization (W) ( ~4K) 3840 3840 x 1 x 1 x 1 F32
298 blk.22.ffn_up.weight Block 22 Feed-Forward Network "Up" (W) (~59M) 58982400 3840 x 15360 x 1 x 1 IQ3_XXS
299 blk.22.post_attention_norm.weight Block 22 Post_Attention_Norm (W) ( ~4K) 3840 3840 x 1 x 1 x 1 F32
300 blk.22.post_ffw_norm.weight Block 22 Post_Ffw_Norm (W) ( ~4K) 3840 3840 x 1 x 1 x 1 F32
  • Total elements in blk.22: (~224M) 224148992
  • Percentage of total elements: 1.98%

Block 23 Tensor Group : ~224M Elements

T_ID Tensor Layer Name Human Friendly Tensor Layer Name Elements Shape Type
301 blk.23.attn_k.weight Block 23 Attention Key (W) ( ~8M) 7864320 3840 x 2048 x 1 x 1 IQ3_XXS
302 blk.23.attn_k_norm.weight Block 23 Attn_K_Norm (W) ( 256) 256 256 x 1 x 1 x 1 F32
303 blk.23.attn_norm.weight Block 23 Attention Normalization (W) ( ~4K) 3840 3840 x 1 x 1 x 1 F32
304 blk.23.attn_output.weight Block 23 Attention Output (W) (~16M) 15728640 4096 x 3840 x 1 x 1 Q4_K
305 blk.23.attn_q.weight Block 23 Attention Query (W) (~16M) 15728640 3840 x 4096 x 1 x 1 IQ3_XXS
306 blk.23.attn_q_norm.weight Block 23 Attn_Q_Norm (W) ( 256) 256 256 x 1 x 1 x 1 F32
307 blk.23.attn_v.weight Block 23 Attention Value (W) ( ~8M) 7864320 3840 x 2048 x 1 x 1 IQ3_S
308 blk.23.ffn_down.weight Block 23 Feed-Forward Network "Down" (W) (~59M) 58982400 15360 x 3840 x 1 x 1 IQ4_NL
309 blk.23.ffn_gate.weight Block 23 Feed-Forward Network "Gate" (W) (~59M) 58982400 3840 x 15360 x 1 x 1 IQ3_XXS
310 blk.23.ffn_norm.weight Block 23 Feed-Forward Network Normalization (W) ( ~4K) 3840 3840 x 1 x 1 x 1 F32
311 blk.23.ffn_up.weight Block 23 Feed-Forward Network "Up" (W) (~59M) 58982400 3840 x 15360 x 1 x 1 IQ3_XXS
312 blk.23.post_attention_norm.weight Block 23 Post_Attention_Norm (W) ( ~4K) 3840 3840 x 1 x 1 x 1 F32
313 blk.23.post_ffw_norm.weight Block 23 Post_Ffw_Norm (W) ( ~4K) 3840 3840 x 1 x 1 x 1 F32
  • Total elements in blk.23: (~224M) 224148992
  • Percentage of total elements: 1.98%

Block 24 Tensor Group : ~224M Elements

T_ID Tensor Layer Name Human Friendly Tensor Layer Name Elements Shape Type
314 blk.24.attn_k.weight Block 24 Attention Key (W) ( ~8M) 7864320 3840 x 2048 x 1 x 1 IQ3_S
315 blk.24.attn_k_norm.weight Block 24 Attn_K_Norm (W) ( 256) 256 256 x 1 x 1 x 1 F32
316 blk.24.attn_norm.weight Block 24 Attention Normalization (W) ( ~4K) 3840 3840 x 1 x 1 x 1 F32
317 blk.24.attn_output.weight Block 24 Attention Output (W) (~16M) 15728640 4096 x 3840 x 1 x 1 Q4_K
318 blk.24.attn_q.weight Block 24 Attention Query (W) (~16M) 15728640 3840 x 4096 x 1 x 1 IQ3_S
319 blk.24.attn_q_norm.weight Block 24 Attn_Q_Norm (W) ( 256) 256 256 x 1 x 1 x 1 F32
320 blk.24.attn_v.weight Block 24 Attention Value (W) ( ~8M) 7864320 3840 x 2048 x 1 x 1 IQ4_NL
321 blk.24.ffn_down.weight Block 24 Feed-Forward Network "Down" (W) (~59M) 58982400 15360 x 3840 x 1 x 1 IQ4_NL
322 blk.24.ffn_gate.weight Block 24 Feed-Forward Network "Gate" (W) (~59M) 58982400 3840 x 15360 x 1 x 1 IQ3_S
323 blk.24.ffn_norm.weight Block 24 Feed-Forward Network Normalization (W) ( ~4K) 3840 3840 x 1 x 1 x 1 F32
324 blk.24.ffn_up.weight Block 24 Feed-Forward Network "Up" (W) (~59M) 58982400 3840 x 15360 x 1 x 1 IQ3_S
325 blk.24.post_attention_norm.weight Block 24 Post_Attention_Norm (W) ( ~4K) 3840 3840 x 1 x 1 x 1 F32
326 blk.24.post_ffw_norm.weight Block 24 Post_Ffw_Norm (W) ( ~4K) 3840 3840 x 1 x 1 x 1 F32
  • Total elements in blk.24: (~224M) 224148992
  • Percentage of total elements: 1.98%

Block 25 Tensor Group : ~224M Elements

T_ID Tensor Layer Name Human Friendly Tensor Layer Name Elements Shape Type
327 blk.25.attn_k.weight Block 25 Attention Key (W) ( ~8M) 7864320 3840 x 2048 x 1 x 1 IQ3_XXS
328 blk.25.attn_k_norm.weight Block 25 Attn_K_Norm (W) ( 256) 256 256 x 1 x 1 x 1 F32
329 blk.25.attn_norm.weight Block 25 Attention Normalization (W) ( ~4K) 3840 3840 x 1 x 1 x 1 F32
330 blk.25.attn_output.weight Block 25 Attention Output (W) (~16M) 15728640 4096 x 3840 x 1 x 1 Q4_K
331 blk.25.attn_q.weight Block 25 Attention Query (W) (~16M) 15728640 3840 x 4096 x 1 x 1 IQ3_XXS
332 blk.25.attn_q_norm.weight Block 25 Attn_Q_Norm (W) ( 256) 256 256 x 1 x 1 x 1 F32
333 blk.25.attn_v.weight Block 25 Attention Value (W) ( ~8M) 7864320 3840 x 2048 x 1 x 1 IQ3_S
334 blk.25.ffn_down.weight Block 25 Feed-Forward Network "Down" (W) (~59M) 58982400 15360 x 3840 x 1 x 1 IQ4_NL
335 blk.25.ffn_gate.weight Block 25 Feed-Forward Network "Gate" (W) (~59M) 58982400 3840 x 15360 x 1 x 1 IQ3_XXS
336 blk.25.ffn_norm.weight Block 25 Feed-Forward Network Normalization (W) ( ~4K) 3840 3840 x 1 x 1 x 1 F32
337 blk.25.ffn_up.weight Block 25 Feed-Forward Network "Up" (W) (~59M) 58982400 3840 x 15360 x 1 x 1 IQ3_XXS
338 blk.25.post_attention_norm.weight Block 25 Post_Attention_Norm (W) ( ~4K) 3840 3840 x 1 x 1 x 1 F32
339 blk.25.post_ffw_norm.weight Block 25 Post_Ffw_Norm (W) ( ~4K) 3840 3840 x 1 x 1 x 1 F32
  • Total elements in blk.25: (~224M) 224148992
  • Percentage of total elements: 1.98%

Block 26 Tensor Group : ~224M Elements

T_ID Tensor Layer Name Human Friendly Tensor Layer Name Elements Shape Type
340 blk.26.attn_k.weight Block 26 Attention Key (W) ( ~8M) 7864320 3840 x 2048 x 1 x 1 IQ3_XXS
341 blk.26.attn_k_norm.weight Block 26 Attn_K_Norm (W) ( 256) 256 256 x 1 x 1 x 1 F32
342 blk.26.attn_norm.weight Block 26 Attention Normalization (W) ( ~4K) 3840 3840 x 1 x 1 x 1 F32
343 blk.26.attn_output.weight Block 26 Attention Output (W) (~16M) 15728640 4096 x 3840 x 1 x 1 Q4_K
344 blk.26.attn_q.weight Block 26 Attention Query (W) (~16M) 15728640 3840 x 4096 x 1 x 1 IQ3_XXS
345 blk.26.attn_q_norm.weight Block 26 Attn_Q_Norm (W) ( 256) 256 256 x 1 x 1 x 1 F32
346 blk.26.attn_v.weight Block 26 Attention Value (W) ( ~8M) 7864320 3840 x 2048 x 1 x 1 IQ3_S
347 blk.26.ffn_down.weight Block 26 Feed-Forward Network "Down" (W) (~59M) 58982400 15360 x 3840 x 1 x 1 IQ4_NL
348 blk.26.ffn_gate.weight Block 26 Feed-Forward Network "Gate" (W) (~59M) 58982400 3840 x 15360 x 1 x 1 IQ3_XXS
349 blk.26.ffn_norm.weight Block 26 Feed-Forward Network Normalization (W) ( ~4K) 3840 3840 x 1 x 1 x 1 F32
350 blk.26.ffn_up.weight Block 26 Feed-Forward Network "Up" (W) (~59M) 58982400 3840 x 15360 x 1 x 1 IQ3_XXS
351 blk.26.post_attention_norm.weight Block 26 Post_Attention_Norm (W) ( ~4K) 3840 3840 x 1 x 1 x 1 F32
352 blk.26.post_ffw_norm.weight Block 26 Post_Ffw_Norm (W) ( ~4K) 3840 3840 x 1 x 1 x 1 F32
  • Total elements in blk.26: (~224M) 224148992
  • Percentage of total elements: 1.98%

Block 27 Tensor Group : ~224M Elements

T_ID Tensor Layer Name Human Friendly Tensor Layer Name Elements Shape Type
353 blk.27.attn_k.weight Block 27 Attention Key (W) ( ~8M) 7864320 3840 x 2048 x 1 x 1 IQ3_XXS
354 blk.27.attn_k_norm.weight Block 27 Attn_K_Norm (W) ( 256) 256 256 x 1 x 1 x 1 F32
355 blk.27.attn_norm.weight Block 27 Attention Normalization (W) ( ~4K) 3840 3840 x 1 x 1 x 1 F32
356 blk.27.attn_output.weight Block 27 Attention Output (W) (~16M) 15728640 4096 x 3840 x 1 x 1 Q4_K
357 blk.27.attn_q.weight Block 27 Attention Query (W) (~16M) 15728640 3840 x 4096 x 1 x 1 IQ3_XXS
358 blk.27.attn_q_norm.weight Block 27 Attn_Q_Norm (W) ( 256) 256 256 x 1 x 1 x 1 F32
359 blk.27.attn_v.weight Block 27 Attention Value (W) ( ~8M) 7864320 3840 x 2048 x 1 x 1 IQ3_S
360 blk.27.ffn_down.weight Block 27 Feed-Forward Network "Down" (W) (~59M) 58982400 15360 x 3840 x 1 x 1 IQ4_NL
361 blk.27.ffn_gate.weight Block 27 Feed-Forward Network "Gate" (W) (~59M) 58982400 3840 x 15360 x 1 x 1 IQ3_XXS
362 blk.27.ffn_norm.weight Block 27 Feed-Forward Network Normalization (W) ( ~4K) 3840 3840 x 1 x 1 x 1 F32
363 blk.27.ffn_up.weight Block 27 Feed-Forward Network "Up" (W) (~59M) 58982400 3840 x 15360 x 1 x 1 IQ3_XXS
364 blk.27.post_attention_norm.weight Block 27 Post_Attention_Norm (W) ( ~4K) 3840 3840 x 1 x 1 x 1 F32
365 blk.27.post_ffw_norm.weight Block 27 Post_Ffw_Norm (W) ( ~4K) 3840 3840 x 1 x 1 x 1 F32
  • Total elements in blk.27: (~224M) 224148992
  • Percentage of total elements: 1.98%

Block 28 Tensor Group : ~224M Elements

T_ID Tensor Layer Name Human Friendly Tensor Layer Name Elements Shape Type
366 blk.28.attn_k.weight Block 28 Attention Key (W) ( ~8M) 7864320 3840 x 2048 x 1 x 1 IQ3_S
367 blk.28.attn_k_norm.weight Block 28 Attn_K_Norm (W) ( 256) 256 256 x 1 x 1 x 1 F32
368 blk.28.attn_norm.weight Block 28 Attention Normalization (W) ( ~4K) 3840 3840 x 1 x 1 x 1 F32
369 blk.28.attn_output.weight Block 28 Attention Output (W) (~16M) 15728640 4096 x 3840 x 1 x 1 Q4_K
370 blk.28.attn_q.weight Block 28 Attention Query (W) (~16M) 15728640 3840 x 4096 x 1 x 1 IQ3_S
371 blk.28.attn_q_norm.weight Block 28 Attn_Q_Norm (W) ( 256) 256 256 x 1 x 1 x 1 F32
372 blk.28.attn_v.weight Block 28 Attention Value (W) ( ~8M) 7864320 3840 x 2048 x 1 x 1 IQ4_NL
373 blk.28.ffn_down.weight Block 28 Feed-Forward Network "Down" (W) (~59M) 58982400 15360 x 3840 x 1 x 1 IQ4_NL
374 blk.28.ffn_gate.weight Block 28 Feed-Forward Network "Gate" (W) (~59M) 58982400 3840 x 15360 x 1 x 1 IQ3_S
375 blk.28.ffn_norm.weight Block 28 Feed-Forward Network Normalization (W) ( ~4K) 3840 3840 x 1 x 1 x 1 F32
376 blk.28.ffn_up.weight Block 28 Feed-Forward Network "Up" (W) (~59M) 58982400 3840 x 15360 x 1 x 1 IQ3_S
377 blk.28.post_attention_norm.weight Block 28 Post_Attention_Norm (W) ( ~4K) 3840 3840 x 1 x 1 x 1 F32
378 blk.28.post_ffw_norm.weight Block 28 Post_Ffw_Norm (W) ( ~4K) 3840 3840 x 1 x 1 x 1 F32
  • Total elements in blk.28: (~224M) 224148992
  • Percentage of total elements: 1.98%

Block 29 Tensor Group : ~224M Elements

T_ID Tensor Layer Name Human Friendly Tensor Layer Name Elements Shape Type
379 blk.29.attn_k.weight Block 29 Attention Key (W) ( ~8M) 7864320 3840 x 2048 x 1 x 1 IQ3_XXS
380 blk.29.attn_k_norm.weight Block 29 Attn_K_Norm (W) ( 256) 256 256 x 1 x 1 x 1 F32
381 blk.29.attn_norm.weight Block 29 Attention Normalization (W) ( ~4K) 3840 3840 x 1 x 1 x 1 F32
382 blk.29.attn_output.weight Block 29 Attention Output (W) (~16M) 15728640 4096 x 3840 x 1 x 1 Q4_K
383 blk.29.attn_q.weight Block 29 Attention Query (W) (~16M) 15728640 3840 x 4096 x 1 x 1 IQ3_XXS
384 blk.29.attn_q_norm.weight Block 29 Attn_Q_Norm (W) ( 256) 256 256 x 1 x 1 x 1 F32
385 blk.29.attn_v.weight Block 29 Attention Value (W) ( ~8M) 7864320 3840 x 2048 x 1 x 1 IQ3_S
386 blk.29.ffn_down.weight Block 29 Feed-Forward Network "Down" (W) (~59M) 58982400 15360 x 3840 x 1 x 1 IQ4_NL
387 blk.29.ffn_gate.weight Block 29 Feed-Forward Network "Gate" (W) (~59M) 58982400 3840 x 15360 x 1 x 1 IQ3_XXS
388 blk.29.ffn_norm.weight Block 29 Feed-Forward Network Normalization (W) ( ~4K) 3840 3840 x 1 x 1 x 1 F32
389 blk.29.ffn_up.weight Block 29 Feed-Forward Network "Up" (W) (~59M) 58982400 3840 x 15360 x 1 x 1 IQ3_XXS
390 blk.29.post_attention_norm.weight Block 29 Post_Attention_Norm (W) ( ~4K) 3840 3840 x 1 x 1 x 1 F32
391 blk.29.post_ffw_norm.weight Block 29 Post_Ffw_Norm (W) ( ~4K) 3840 3840 x 1 x 1 x 1 F32
  • Total elements in blk.29: (~224M) 224148992
  • Percentage of total elements: 1.98%

Block 30 Tensor Group : ~224M Elements

T_ID Tensor Layer Name Human Friendly Tensor Layer Name Elements Shape Type
392 blk.30.attn_k.weight Block 30 Attention Key (W) ( ~8M) 7864320 3840 x 2048 x 1 x 1 IQ3_XXS
393 blk.30.attn_k_norm.weight Block 30 Attn_K_Norm (W) ( 256) 256 256 x 1 x 1 x 1 F32
394 blk.30.attn_norm.weight Block 30 Attention Normalization (W) ( ~4K) 3840 3840 x 1 x 1 x 1 F32
395 blk.30.attn_output.weight Block 30 Attention Output (W) (~16M) 15728640 4096 x 3840 x 1 x 1 Q4_K
396 blk.30.attn_q.weight Block 30 Attention Query (W) (~16M) 15728640 3840 x 4096 x 1 x 1 IQ3_XXS
397 blk.30.attn_q_norm.weight Block 30 Attn_Q_Norm (W) ( 256) 256 256 x 1 x 1 x 1 F32
398 blk.30.attn_v.weight Block 30 Attention Value (W) ( ~8M) 7864320 3840 x 2048 x 1 x 1 IQ3_S
399 blk.30.ffn_down.weight Block 30 Feed-Forward Network "Down" (W) (~59M) 58982400 15360 x 3840 x 1 x 1 IQ4_NL
400 blk.30.ffn_gate.weight Block 30 Feed-Forward Network "Gate" (W) (~59M) 58982400 3840 x 15360 x 1 x 1 IQ3_XXS
401 blk.30.ffn_norm.weight Block 30 Feed-Forward Network Normalization (W) ( ~4K) 3840 3840 x 1 x 1 x 1 F32
402 blk.30.ffn_up.weight Block 30 Feed-Forward Network "Up" (W) (~59M) 58982400 3840 x 15360 x 1 x 1 IQ3_XXS
403 blk.30.post_attention_norm.weight Block 30 Post_Attention_Norm (W) ( ~4K) 3840 3840 x 1 x 1 x 1 F32
404 blk.30.post_ffw_norm.weight Block 30 Post_Ffw_Norm (W) ( ~4K) 3840 3840 x 1 x 1 x 1 F32
  • Total elements in blk.30: (~224M) 224148992
  • Percentage of total elements: 1.98%

Block 31 Tensor Group : ~224M Elements

T_ID Tensor Layer Name Human Friendly Tensor Layer Name Elements Shape Type
405 blk.31.attn_k.weight Block 31 Attention Key (W) ( ~8M) 7864320 3840 x 2048 x 1 x 1 IQ3_S
406 blk.31.attn_k_norm.weight Block 31 Attn_K_Norm (W) ( 256) 256 256 x 1 x 1 x 1 F32
407 blk.31.attn_norm.weight Block 31 Attention Normalization (W) ( ~4K) 3840 3840 x 1 x 1 x 1 F32
408 blk.31.attn_output.weight Block 31 Attention Output (W) (~16M) 15728640 4096 x 3840 x 1 x 1 Q4_K
409 blk.31.attn_q.weight Block 31 Attention Query (W) (~16M) 15728640 3840 x 4096 x 1 x 1 IQ3_S
410 blk.31.attn_q_norm.weight Block 31 Attn_Q_Norm (W) ( 256) 256 256 x 1 x 1 x 1 F32
411 blk.31.attn_v.weight Block 31 Attention Value (W) ( ~8M) 7864320 3840 x 2048 x 1 x 1 IQ4_NL
412 blk.31.ffn_down.weight Block 31 Feed-Forward Network "Down" (W) (~59M) 58982400 15360 x 3840 x 1 x 1 IQ4_NL
413 blk.31.ffn_gate.weight Block 31 Feed-Forward Network "Gate" (W) (~59M) 58982400 3840 x 15360 x 1 x 1 IQ3_S
414 blk.31.ffn_norm.weight Block 31 Feed-Forward Network Normalization (W) ( ~4K) 3840 3840 x 1 x 1 x 1 F32
415 blk.31.ffn_up.weight Block 31 Feed-Forward Network "Up" (W) (~59M) 58982400 3840 x 15360 x 1 x 1 IQ3_S
416 blk.31.post_attention_norm.weight Block 31 Post_Attention_Norm (W) ( ~4K) 3840 3840 x 1 x 1 x 1 F32
417 blk.31.post_ffw_norm.weight Block 31 Post_Ffw_Norm (W) ( ~4K) 3840 3840 x 1 x 1 x 1 F32
  • Total elements in blk.31: (~224M) 224148992
  • Percentage of total elements: 1.98%

Block 32 Tensor Group : ~224M Elements

T_ID Tensor Layer Name Human Friendly Tensor Layer Name Elements Shape Type
418 blk.32.attn_k.weight Block 32 Attention Key (W) ( ~8M) 7864320 3840 x 2048 x 1 x 1 IQ3_S
419 blk.32.attn_k_norm.weight Block 32 Attn_K_Norm (W) ( 256) 256 256 x 1 x 1 x 1 F32
420 blk.32.attn_norm.weight Block 32 Attention Normalization (W) ( ~4K) 3840 3840 x 1 x 1 x 1 F32
421 blk.32.attn_output.weight Block 32 Attention Output (W) (~16M) 15728640 4096 x 3840 x 1 x 1 Q4_K
422 blk.32.attn_q.weight Block 32 Attention Query (W) (~16M) 15728640 3840 x 4096 x 1 x 1 IQ3_S
423 blk.32.attn_q_norm.weight Block 32 Attn_Q_Norm (W) ( 256) 256 256 x 1 x 1 x 1 F32
424 blk.32.attn_v.weight Block 32 Attention Value (W) ( ~8M) 7864320 3840 x 2048 x 1 x 1 IQ4_NL
425 blk.32.ffn_down.weight Block 32 Feed-Forward Network "Down" (W) (~59M) 58982400 15360 x 3840 x 1 x 1 IQ4_NL
426 blk.32.ffn_gate.weight Block 32 Feed-Forward Network "Gate" (W) (~59M) 58982400 3840 x 15360 x 1 x 1 IQ3_S
427 blk.32.ffn_norm.weight Block 32 Feed-Forward Network Normalization (W) ( ~4K) 3840 3840 x 1 x 1 x 1 F32
428 blk.32.ffn_up.weight Block 32 Feed-Forward Network "Up" (W) (~59M) 58982400 3840 x 15360 x 1 x 1 IQ3_S
429 blk.32.post_attention_norm.weight Block 32 Post_Attention_Norm (W) ( ~4K) 3840 3840 x 1 x 1 x 1 F32
430 blk.32.post_ffw_norm.weight Block 32 Post_Ffw_Norm (W) ( ~4K) 3840 3840 x 1 x 1 x 1 F32
  • Total elements in blk.32: (~224M) 224148992
  • Percentage of total elements: 1.98%

Block 33 Tensor Group : ~224M Elements

T_ID Tensor Layer Name Human Friendly Tensor Layer Name Elements Shape Type
431 blk.33.attn_k.weight Block 33 Attention Key (W) ( ~8M) 7864320 3840 x 2048 x 1 x 1 IQ3_S
432 blk.33.attn_k_norm.weight Block 33 Attn_K_Norm (W) ( 256) 256 256 x 1 x 1 x 1 F32
433 blk.33.attn_norm.weight Block 33 Attention Normalization (W) ( ~4K) 3840 3840 x 1 x 1 x 1 F32
434 blk.33.attn_output.weight Block 33 Attention Output (W) (~16M) 15728640 4096 x 3840 x 1 x 1 Q4_K
435 blk.33.attn_q.weight Block 33 Attention Query (W) (~16M) 15728640 3840 x 4096 x 1 x 1 IQ3_S
436 blk.33.attn_q_norm.weight Block 33 Attn_Q_Norm (W) ( 256) 256 256 x 1 x 1 x 1 F32
437 blk.33.attn_v.weight Block 33 Attention Value (W) ( ~8M) 7864320 3840 x 2048 x 1 x 1 IQ4_NL
438 blk.33.ffn_down.weight Block 33 Feed-Forward Network "Down" (W) (~59M) 58982400 15360 x 3840 x 1 x 1 IQ4_NL
439 blk.33.ffn_gate.weight Block 33 Feed-Forward Network "Gate" (W) (~59M) 58982400 3840 x 15360 x 1 x 1 IQ3_S
440 blk.33.ffn_norm.weight Block 33 Feed-Forward Network Normalization (W) ( ~4K) 3840 3840 x 1 x 1 x 1 F32
441 blk.33.ffn_up.weight Block 33 Feed-Forward Network "Up" (W) (~59M) 58982400 3840 x 15360 x 1 x 1 IQ3_S
442 blk.33.post_attention_norm.weight Block 33 Post_Attention_Norm (W) ( ~4K) 3840 3840 x 1 x 1 x 1 F32
443 blk.33.post_ffw_norm.weight Block 33 Post_Ffw_Norm (W) ( ~4K) 3840 3840 x 1 x 1 x 1 F32
  • Total elements in blk.33: (~224M) 224148992
  • Percentage of total elements: 1.98%

Block 34 Tensor Group : ~224M Elements

T_ID Tensor Layer Name Human Friendly Tensor Layer Name Elements Shape Type
444 blk.34.attn_k.weight Block 34 Attention Key (W) ( ~8M) 7864320 3840 x 2048 x 1 x 1 IQ3_S
445 blk.34.attn_k_norm.weight Block 34 Attn_K_Norm (W) ( 256) 256 256 x 1 x 1 x 1 F32
446 blk.34.attn_norm.weight Block 34 Attention Normalization (W) ( ~4K) 3840 3840 x 1 x 1 x 1 F32
447 blk.34.attn_output.weight Block 34 Attention Output (W) (~16M) 15728640 4096 x 3840 x 1 x 1 Q4_K
448 blk.34.attn_q.weight Block 34 Attention Query (W) (~16M) 15728640 3840 x 4096 x 1 x 1 IQ3_S
449 blk.34.attn_q_norm.weight Block 34 Attn_Q_Norm (W) ( 256) 256 256 x 1 x 1 x 1 F32
450 blk.34.attn_v.weight Block 34 Attention Value (W) ( ~8M) 7864320 3840 x 2048 x 1 x 1 IQ4_NL
451 blk.34.ffn_down.weight Block 34 Feed-Forward Network "Down" (W) (~59M) 58982400 15360 x 3840 x 1 x 1 IQ4_NL
452 blk.34.ffn_gate.weight Block 34 Feed-Forward Network "Gate" (W) (~59M) 58982400 3840 x 15360 x 1 x 1 IQ3_S
453 blk.34.ffn_norm.weight Block 34 Feed-Forward Network Normalization (W) ( ~4K) 3840 3840 x 1 x 1 x 1 F32
454 blk.34.ffn_up.weight Block 34 Feed-Forward Network "Up" (W) (~59M) 58982400 3840 x 15360 x 1 x 1 IQ3_S
455 blk.34.post_attention_norm.weight Block 34 Post_Attention_Norm (W) ( ~4K) 3840 3840 x 1 x 1 x 1 F32
456 blk.34.post_ffw_norm.weight Block 34 Post_Ffw_Norm (W) ( ~4K) 3840 3840 x 1 x 1 x 1 F32
  • Total elements in blk.34: (~224M) 224148992
  • Percentage of total elements: 1.98%

Block 35 Tensor Group : ~224M Elements

T_ID Tensor Layer Name Human Friendly Tensor Layer Name Elements Shape Type
457 blk.35.attn_k.weight Block 35 Attention Key (W) ( ~8M) 7864320 3840 x 2048 x 1 x 1 IQ3_XXS
458 blk.35.attn_k_norm.weight Block 35 Attn_K_Norm (W) ( 256) 256 256 x 1 x 1 x 1 F32
459 blk.35.attn_norm.weight Block 35 Attention Normalization (W) ( ~4K) 3840 3840 x 1 x 1 x 1 F32
460 blk.35.attn_output.weight Block 35 Attention Output (W) (~16M) 15728640 4096 x 3840 x 1 x 1 Q4_K
461 blk.35.attn_q.weight Block 35 Attention Query (W) (~16M) 15728640 3840 x 4096 x 1 x 1 IQ3_XXS
462 blk.35.attn_q_norm.weight Block 35 Attn_Q_Norm (W) ( 256) 256 256 x 1 x 1 x 1 F32
463 blk.35.attn_v.weight Block 35 Attention Value (W) ( ~8M) 7864320 3840 x 2048 x 1 x 1 IQ3_S
464 blk.35.ffn_down.weight Block 35 Feed-Forward Network "Down" (W) (~59M) 58982400 15360 x 3840 x 1 x 1 IQ4_NL
465 blk.35.ffn_gate.weight Block 35 Feed-Forward Network "Gate" (W) (~59M) 58982400 3840 x 15360 x 1 x 1 IQ3_XXS
466 blk.35.ffn_norm.weight Block 35 Feed-Forward Network Normalization (W) ( ~4K) 3840 3840 x 1 x 1 x 1 F32
467 blk.35.ffn_up.weight Block 35 Feed-Forward Network "Up" (W) (~59M) 58982400 3840 x 15360 x 1 x 1 IQ3_XXS
468 blk.35.post_attention_norm.weight Block 35 Post_Attention_Norm (W) ( ~4K) 3840 3840 x 1 x 1 x 1 F32
469 blk.35.post_ffw_norm.weight Block 35 Post_Ffw_Norm (W) ( ~4K) 3840 3840 x 1 x 1 x 1 F32
  • Total elements in blk.35: (~224M) 224148992
  • Percentage of total elements: 1.98%

Block 36 Tensor Group : ~224M Elements

T_ID Tensor Layer Name Human Friendly Tensor Layer Name Elements Shape Type
470 blk.36.attn_k.weight Block 36 Attention Key (W) ( ~8M) 7864320 3840 x 2048 x 1 x 1 IQ3_S
471 blk.36.attn_k_norm.weight Block 36 Attn_K_Norm (W) ( 256) 256 256 x 1 x 1 x 1 F32
472 blk.36.attn_norm.weight Block 36 Attention Normalization (W) ( ~4K) 3840 3840 x 1 x 1 x 1 F32
473 blk.36.attn_output.weight Block 36 Attention Output (W) (~16M) 15728640 4096 x 3840 x 1 x 1 Q4_K
474 blk.36.attn_q.weight Block 36 Attention Query (W) (~16M) 15728640 3840 x 4096 x 1 x 1 IQ3_S
475 blk.36.attn_q_norm.weight Block 36 Attn_Q_Norm (W) ( 256) 256 256 x 1 x 1 x 1 F32
476 blk.36.attn_v.weight Block 36 Attention Value (W) ( ~8M) 7864320 3840 x 2048 x 1 x 1 IQ4_NL
477 blk.36.ffn_down.weight Block 36 Feed-Forward Network "Down" (W) (~59M) 58982400 15360 x 3840 x 1 x 1 IQ4_NL
478 blk.36.ffn_gate.weight Block 36 Feed-Forward Network "Gate" (W) (~59M) 58982400 3840 x 15360 x 1 x 1 IQ3_S
479 blk.36.ffn_norm.weight Block 36 Feed-Forward Network Normalization (W) ( ~4K) 3840 3840 x 1 x 1 x 1 F32
480 blk.36.ffn_up.weight Block 36 Feed-Forward Network "Up" (W) (~59M) 58982400 3840 x 15360 x 1 x 1 IQ3_S
481 blk.36.post_attention_norm.weight Block 36 Post_Attention_Norm (W) ( ~4K) 3840 3840 x 1 x 1 x 1 F32
482 blk.36.post_ffw_norm.weight Block 36 Post_Ffw_Norm (W) ( ~4K) 3840 3840 x 1 x 1 x 1 F32
  • Total elements in blk.36: (~224M) 224148992
  • Percentage of total elements: 1.98%

Block 37 Tensor Group : ~224M Elements

T_ID Tensor Layer Name Human Friendly Tensor Layer Name Elements Shape Type
483 blk.37.attn_k.weight Block 37 Attention Key (W) ( ~8M) 7864320 3840 x 2048 x 1 x 1 IQ3_S
484 blk.37.attn_k_norm.weight Block 37 Attn_K_Norm (W) ( 256) 256 256 x 1 x 1 x 1 F32
485 blk.37.attn_norm.weight Block 37 Attention Normalization (W) ( ~4K) 3840 3840 x 1 x 1 x 1 F32
486 blk.37.attn_output.weight Block 37 Attention Output (W) (~16M) 15728640 4096 x 3840 x 1 x 1 Q4_K
487 blk.37.attn_q.weight Block 37 Attention Query (W) (~16M) 15728640 3840 x 4096 x 1 x 1 IQ3_S
488 blk.37.attn_q_norm.weight Block 37 Attn_Q_Norm (W) ( 256) 256 256 x 1 x 1 x 1 F32
489 blk.37.attn_v.weight Block 37 Attention Value (W) ( ~8M) 7864320 3840 x 2048 x 1 x 1 IQ4_NL
490 blk.37.ffn_down.weight Block 37 Feed-Forward Network "Down" (W) (~59M) 58982400 15360 x 3840 x 1 x 1 IQ4_NL
491 blk.37.ffn_gate.weight Block 37 Feed-Forward Network "Gate" (W) (~59M) 58982400 3840 x 15360 x 1 x 1 IQ3_S
492 blk.37.ffn_norm.weight Block 37 Feed-Forward Network Normalization (W) ( ~4K) 3840 3840 x 1 x 1 x 1 F32
493 blk.37.ffn_up.weight Block 37 Feed-Forward Network "Up" (W) (~59M) 58982400 3840 x 15360 x 1 x 1 IQ3_S
494 blk.37.post_attention_norm.weight Block 37 Post_Attention_Norm (W) ( ~4K) 3840 3840 x 1 x 1 x 1 F32
495 blk.37.post_ffw_norm.weight Block 37 Post_Ffw_Norm (W) ( ~4K) 3840 3840 x 1 x 1 x 1 F32
  • Total elements in blk.37: (~224M) 224148992
  • Percentage of total elements: 1.98%

Block 38 Tensor Group : ~224M Elements

T_ID Tensor Layer Name Human Friendly Tensor Layer Name Elements Shape Type
496 blk.38.attn_k.weight Block 38 Attention Key (W) ( ~8M) 7864320 3840 x 2048 x 1 x 1 IQ3_S
497 blk.38.attn_k_norm.weight Block 38 Attn_K_Norm (W) ( 256) 256 256 x 1 x 1 x 1 F32
498 blk.38.attn_norm.weight Block 38 Attention Normalization (W) ( ~4K) 3840 3840 x 1 x 1 x 1 F32
499 blk.38.attn_output.weight Block 38 Attention Output (W) (~16M) 15728640 4096 x 3840 x 1 x 1 Q4_K
500 blk.38.attn_q.weight Block 38 Attention Query (W) (~16M) 15728640 3840 x 4096 x 1 x 1 IQ3_S
501 blk.38.attn_q_norm.weight Block 38 Attn_Q_Norm (W) ( 256) 256 256 x 1 x 1 x 1 F32
502 blk.38.attn_v.weight Block 38 Attention Value (W) ( ~8M) 7864320 3840 x 2048 x 1 x 1 IQ4_NL
503 blk.38.ffn_down.weight Block 38 Feed-Forward Network "Down" (W) (~59M) 58982400 15360 x 3840 x 1 x 1 IQ4_NL
504 blk.38.ffn_gate.weight Block 38 Feed-Forward Network "Gate" (W) (~59M) 58982400 3840 x 15360 x 1 x 1 IQ3_S
505 blk.38.ffn_norm.weight Block 38 Feed-Forward Network Normalization (W) ( ~4K) 3840 3840 x 1 x 1 x 1 F32
506 blk.38.ffn_up.weight Block 38 Feed-Forward Network "Up" (W) (~59M) 58982400 3840 x 15360 x 1 x 1 IQ3_S
507 blk.38.post_attention_norm.weight Block 38 Post_Attention_Norm (W) ( ~4K) 3840 3840 x 1 x 1 x 1 F32
508 blk.38.post_ffw_norm.weight Block 38 Post_Ffw_Norm (W) ( ~4K) 3840 3840 x 1 x 1 x 1 F32
  • Total elements in blk.38: (~224M) 224148992
  • Percentage of total elements: 1.98%

Block 39 Tensor Group : ~224M Elements

T_ID Tensor Layer Name Human Friendly Tensor Layer Name Elements Shape Type
509 blk.39.attn_k.weight Block 39 Attention Key (W) ( ~8M) 7864320 3840 x 2048 x 1 x 1 IQ3_S
510 blk.39.attn_k_norm.weight Block 39 Attn_K_Norm (W) ( 256) 256 256 x 1 x 1 x 1 F32
511 blk.39.attn_norm.weight Block 39 Attention Normalization (W) ( ~4K) 3840 3840 x 1 x 1 x 1 F32
512 blk.39.attn_output.weight Block 39 Attention Output (W) (~16M) 15728640 4096 x 3840 x 1 x 1 Q4_K
513 blk.39.attn_q.weight Block 39 Attention Query (W) (~16M) 15728640 3840 x 4096 x 1 x 1 IQ3_S
514 blk.39.attn_q_norm.weight Block 39 Attn_Q_Norm (W) ( 256) 256 256 x 1 x 1 x 1 F32
515 blk.39.attn_v.weight Block 39 Attention Value (W) ( ~8M) 7864320 3840 x 2048 x 1 x 1 IQ4_NL
516 blk.39.ffn_down.weight Block 39 Feed-Forward Network "Down" (W) (~59M) 58982400 15360 x 3840 x 1 x 1 IQ4_NL
517 blk.39.ffn_gate.weight Block 39 Feed-Forward Network "Gate" (W) (~59M) 58982400 3840 x 15360 x 1 x 1 IQ3_S
518 blk.39.ffn_norm.weight Block 39 Feed-Forward Network Normalization (W) ( ~4K) 3840 3840 x 1 x 1 x 1 F32
519 blk.39.ffn_up.weight Block 39 Feed-Forward Network "Up" (W) (~59M) 58982400 3840 x 15360 x 1 x 1 IQ3_S
520 blk.39.post_attention_norm.weight Block 39 Post_Attention_Norm (W) ( ~4K) 3840 3840 x 1 x 1 x 1 F32
521 blk.39.post_ffw_norm.weight Block 39 Post_Ffw_Norm (W) ( ~4K) 3840 3840 x 1 x 1 x 1 F32
  • Total elements in blk.39: (~224M) 224148992
  • Percentage of total elements: 1.98%

Block 40 Tensor Group : ~224M Elements

T_ID Tensor Layer Name Human Friendly Tensor Layer Name Elements Shape Type
522 blk.40.attn_k.weight Block 40 Attention Key (W) ( ~8M) 7864320 3840 x 2048 x 1 x 1 IQ3_S
523 blk.40.attn_k_norm.weight Block 40 Attn_K_Norm (W) ( 256) 256 256 x 1 x 1 x 1 F32
524 blk.40.attn_norm.weight Block 40 Attention Normalization (W) ( ~4K) 3840 3840 x 1 x 1 x 1 F32
525 blk.40.attn_output.weight Block 40 Attention Output (W) (~16M) 15728640 4096 x 3840 x 1 x 1 Q4_K
526 blk.40.attn_q.weight Block 40 Attention Query (W) (~16M) 15728640 3840 x 4096 x 1 x 1 IQ3_S
527 blk.40.attn_q_norm.weight Block 40 Attn_Q_Norm (W) ( 256) 256 256 x 1 x 1 x 1 F32
528 blk.40.attn_v.weight Block 40 Attention Value (W) ( ~8M) 7864320 3840 x 2048 x 1 x 1 IQ4_NL
529 blk.40.ffn_down.weight Block 40 Feed-Forward Network "Down" (W) (~59M) 58982400 15360 x 3840 x 1 x 1 IQ4_NL
530 blk.40.ffn_gate.weight Block 40 Feed-Forward Network "Gate" (W) (~59M) 58982400 3840 x 15360 x 1 x 1 IQ3_S
531 blk.40.ffn_norm.weight Block 40 Feed-Forward Network Normalization (W) ( ~4K) 3840 3840 x 1 x 1 x 1 F32
532 blk.40.ffn_up.weight Block 40 Feed-Forward Network "Up" (W) (~59M) 58982400 3840 x 15360 x 1 x 1 IQ3_S
533 blk.40.post_attention_norm.weight Block 40 Post_Attention_Norm (W) ( ~4K) 3840 3840 x 1 x 1 x 1 F32
534 blk.40.post_ffw_norm.weight Block 40 Post_Ffw_Norm (W) ( ~4K) 3840 3840 x 1 x 1 x 1 F32
  • Total elements in blk.40: (~224M) 224148992
  • Percentage of total elements: 1.98%

Block 41 Tensor Group : ~224M Elements

T_ID Tensor Layer Name Human Friendly Tensor Layer Name Elements Shape Type
535 blk.41.attn_k.weight Block 41 Attention Key (W) ( ~8M) 7864320 3840 x 2048 x 1 x 1 IQ3_XXS
536 blk.41.attn_k_norm.weight Block 41 Attn_K_Norm (W) ( 256) 256 256 x 1 x 1 x 1 F32
537 blk.41.attn_norm.weight Block 41 Attention Normalization (W) ( ~4K) 3840 3840 x 1 x 1 x 1 F32
538 blk.41.attn_output.weight Block 41 Attention Output (W) (~16M) 15728640 4096 x 3840 x 1 x 1 Q4_K
539 blk.41.attn_q.weight Block 41 Attention Query (W) (~16M) 15728640 3840 x 4096 x 1 x 1 IQ3_XXS
540 blk.41.attn_q_norm.weight Block 41 Attn_Q_Norm (W) ( 256) 256 256 x 1 x 1 x 1 F32
541 blk.41.attn_v.weight Block 41 Attention Value (W) ( ~8M) 7864320 3840 x 2048 x 1 x 1 IQ3_S
542 blk.41.ffn_down.weight Block 41 Feed-Forward Network "Down" (W) (~59M) 58982400 15360 x 3840 x 1 x 1 IQ4_NL
543 blk.41.ffn_gate.weight Block 41 Feed-Forward Network "Gate" (W) (~59M) 58982400 3840 x 15360 x 1 x 1 IQ3_XXS
544 blk.41.ffn_norm.weight Block 41 Feed-Forward Network Normalization (W) ( ~4K) 3840 3840 x 1 x 1 x 1 F32
545 blk.41.ffn_up.weight Block 41 Feed-Forward Network "Up" (W) (~59M) 58982400 3840 x 15360 x 1 x 1 IQ3_XXS
546 blk.41.post_attention_norm.weight Block 41 Post_Attention_Norm (W) ( ~4K) 3840 3840 x 1 x 1 x 1 F32
547 blk.41.post_ffw_norm.weight Block 41 Post_Ffw_Norm (W) ( ~4K) 3840 3840 x 1 x 1 x 1 F32
  • Total elements in blk.41: (~224M) 224148992
  • Percentage of total elements: 1.98%

Block 42 Tensor Group : ~224M Elements

T_ID Tensor Layer Name Human Friendly Tensor Layer Name Elements Shape Type
548 blk.42.attn_k.weight Block 42 Attention Key (W) ( ~8M) 7864320 3840 x 2048 x 1 x 1 IQ3_XXS
549 blk.42.attn_k_norm.weight Block 42 Attn_K_Norm (W) ( 256) 256 256 x 1 x 1 x 1 F32
550 blk.42.attn_norm.weight Block 42 Attention Normalization (W) ( ~4K) 3840 3840 x 1 x 1 x 1 F32
551 blk.42.attn_output.weight Block 42 Attention Output (W) (~16M) 15728640 4096 x 3840 x 1 x 1 Q4_K
552 blk.42.attn_q.weight Block 42 Attention Query (W) (~16M) 15728640 3840 x 4096 x 1 x 1 IQ3_XXS
553 blk.42.attn_q_norm.weight Block 42 Attn_Q_Norm (W) ( 256) 256 256 x 1 x 1 x 1 F32
554 blk.42.attn_v.weight Block 42 Attention Value (W) ( ~8M) 7864320 3840 x 2048 x 1 x 1 IQ3_S
555 blk.42.ffn_down.weight Block 42 Feed-Forward Network "Down" (W) (~59M) 58982400 15360 x 3840 x 1 x 1 IQ4_NL
556 blk.42.ffn_gate.weight Block 42 Feed-Forward Network "Gate" (W) (~59M) 58982400 3840 x 15360 x 1 x 1 IQ3_XXS
557 blk.42.ffn_norm.weight Block 42 Feed-Forward Network Normalization (W) ( ~4K) 3840 3840 x 1 x 1 x 1 F32
558 blk.42.ffn_up.weight Block 42 Feed-Forward Network "Up" (W) (~59M) 58982400 3840 x 15360 x 1 x 1 IQ3_XXS
559 blk.42.post_attention_norm.weight Block 42 Post_Attention_Norm (W) ( ~4K) 3840 3840 x 1 x 1 x 1 F32
560 blk.42.post_ffw_norm.weight Block 42 Post_Ffw_Norm (W) ( ~4K) 3840 3840 x 1 x 1 x 1 F32
  • Total elements in blk.42: (~224M) 224148992
  • Percentage of total elements: 1.98%

Block 43 Tensor Group : ~224M Elements

T_ID Tensor Layer Name Human Friendly Tensor Layer Name Elements Shape Type
561 blk.43.attn_k.weight Block 43 Attention Key (W) ( ~8M) 7864320 3840 x 2048 x 1 x 1 IQ3_XXS
562 blk.43.attn_k_norm.weight Block 43 Attn_K_Norm (W) ( 256) 256 256 x 1 x 1 x 1 F32
563 blk.43.attn_norm.weight Block 43 Attention Normalization (W) ( ~4K) 3840 3840 x 1 x 1 x 1 F32
564 blk.43.attn_output.weight Block 43 Attention Output (W) (~16M) 15728640 4096 x 3840 x 1 x 1 Q4_K
565 blk.43.attn_q.weight Block 43 Attention Query (W) (~16M) 15728640 3840 x 4096 x 1 x 1 IQ3_XXS
566 blk.43.attn_q_norm.weight Block 43 Attn_Q_Norm (W) ( 256) 256 256 x 1 x 1 x 1 F32
567 blk.43.attn_v.weight Block 43 Attention Value (W) ( ~8M) 7864320 3840 x 2048 x 1 x 1 IQ3_S
568 blk.43.ffn_down.weight Block 43 Feed-Forward Network "Down" (W) (~59M) 58982400 15360 x 3840 x 1 x 1 IQ4_NL
569 blk.43.ffn_gate.weight Block 43 Feed-Forward Network "Gate" (W) (~59M) 58982400 3840 x 15360 x 1 x 1 IQ3_XXS
570 blk.43.ffn_norm.weight Block 43 Feed-Forward Network Normalization (W) ( ~4K) 3840 3840 x 1 x 1 x 1 F32
571 blk.43.ffn_up.weight Block 43 Feed-Forward Network "Up" (W) (~59M) 58982400 3840 x 15360 x 1 x 1 IQ3_XXS
572 blk.43.post_attention_norm.weight Block 43 Post_Attention_Norm (W) ( ~4K) 3840 3840 x 1 x 1 x 1 F32
573 blk.43.post_ffw_norm.weight Block 43 Post_Ffw_Norm (W) ( ~4K) 3840 3840 x 1 x 1 x 1 F32
  • Total elements in blk.43: (~224M) 224148992
  • Percentage of total elements: 1.98%

Block 44 Tensor Group : ~224M Elements

T_ID Tensor Layer Name Human Friendly Tensor Layer Name Elements Shape Type
574 blk.44.attn_k.weight Block 44 Attention Key (W) ( ~8M) 7864320 3840 x 2048 x 1 x 1 IQ3_S
575 blk.44.attn_k_norm.weight Block 44 Attn_K_Norm (W) ( 256) 256 256 x 1 x 1 x 1 F32
576 blk.44.attn_norm.weight Block 44 Attention Normalization (W) ( ~4K) 3840 3840 x 1 x 1 x 1 F32
577 blk.44.attn_output.weight Block 44 Attention Output (W) (~16M) 15728640 4096 x 3840 x 1 x 1 Q4_K
578 blk.44.attn_q.weight Block 44 Attention Query (W) (~16M) 15728640 3840 x 4096 x 1 x 1 IQ3_S
579 blk.44.attn_q_norm.weight Block 44 Attn_Q_Norm (W) ( 256) 256 256 x 1 x 1 x 1 F32
580 blk.44.attn_v.weight Block 44 Attention Value (W) ( ~8M) 7864320 3840 x 2048 x 1 x 1 IQ4_NL
581 blk.44.ffn_down.weight Block 44 Feed-Forward Network "Down" (W) (~59M) 58982400 15360 x 3840 x 1 x 1 IQ4_NL
582 blk.44.ffn_gate.weight Block 44 Feed-Forward Network "Gate" (W) (~59M) 58982400 3840 x 15360 x 1 x 1 IQ3_S
583 blk.44.ffn_norm.weight Block 44 Feed-Forward Network Normalization (W) ( ~4K) 3840 3840 x 1 x 1 x 1 F32
584 blk.44.ffn_up.weight Block 44 Feed-Forward Network "Up" (W) (~59M) 58982400 3840 x 15360 x 1 x 1 IQ3_S
585 blk.44.post_attention_norm.weight Block 44 Post_Attention_Norm (W) ( ~4K) 3840 3840 x 1 x 1 x 1 F32
586 blk.44.post_ffw_norm.weight Block 44 Post_Ffw_Norm (W) ( ~4K) 3840 3840 x 1 x 1 x 1 F32
  • Total elements in blk.44: (~224M) 224148992
  • Percentage of total elements: 1.98%

Block 45 Tensor Group : ~224M Elements

T_ID Tensor Layer Name Human Friendly Tensor Layer Name Elements Shape Type
587 blk.45.attn_k.weight Block 45 Attention Key (W) ( ~8M) 7864320 3840 x 2048 x 1 x 1 IQ3_S
588 blk.45.attn_k_norm.weight Block 45 Attn_K_Norm (W) ( 256) 256 256 x 1 x 1 x 1 F32
589 blk.45.attn_norm.weight Block 45 Attention Normalization (W) ( ~4K) 3840 3840 x 1 x 1 x 1 F32
590 blk.45.attn_output.weight Block 45 Attention Output (W) (~16M) 15728640 4096 x 3840 x 1 x 1 Q4_K
591 blk.45.attn_q.weight Block 45 Attention Query (W) (~16M) 15728640 3840 x 4096 x 1 x 1 IQ3_S
592 blk.45.attn_q_norm.weight Block 45 Attn_Q_Norm (W) ( 256) 256 256 x 1 x 1 x 1 F32
593 blk.45.attn_v.weight Block 45 Attention Value (W) ( ~8M) 7864320 3840 x 2048 x 1 x 1 IQ4_NL
594 blk.45.ffn_down.weight Block 45 Feed-Forward Network "Down" (W) (~59M) 58982400 15360 x 3840 x 1 x 1 IQ4_NL
595 blk.45.ffn_gate.weight Block 45 Feed-Forward Network "Gate" (W) (~59M) 58982400 3840 x 15360 x 1 x 1 IQ3_S
596 blk.45.ffn_norm.weight Block 45 Feed-Forward Network Normalization (W) ( ~4K) 3840 3840 x 1 x 1 x 1 F32
597 blk.45.ffn_up.weight Block 45 Feed-Forward Network "Up" (W) (~59M) 58982400 3840 x 15360 x 1 x 1 IQ3_S
598 blk.45.post_attention_norm.weight Block 45 Post_Attention_Norm (W) ( ~4K) 3840 3840 x 1 x 1 x 1 F32
599 blk.45.post_ffw_norm.weight Block 45 Post_Ffw_Norm (W) ( ~4K) 3840 3840 x 1 x 1 x 1 F32
  • Total elements in blk.45: (~224M) 224148992
  • Percentage of total elements: 1.98%