Files
Dolphin-Mistral-24B-Venice-…/scores/Dolphin-Mistral-24B-Venice-Edition-IQ3_S.md
2025-07-01 08:19:46 +01:00

99 KiB

Dolphin-Mistral-24B-Venice-Edition-pruned-IQ3_S.gguf - GGUF Internal File Dump

  • Endian: LITTLE endian

Key Value Metadata Store

There are 46 key-value pairs in this file

POS TYPE Count Key Value
1 UINT32 1 GGUF.version 3
2 UINT64 1 GGUF.tensor_count 345
3 UINT64 1 GGUF.kv_count 43
4 STRING 1 general.architecture llama
5 STRING 1 general.type model
6 STRING 1 general.name Dolphin Mistral 24B Venice Edition
7 STRING 1 general.finetune Venice-Edition
8 STRING 1 general.basename Dolphin-Mistral
9 STRING 1 general.size_label 24B
10 STRING 1 general.license apache-2.0
11 UINT32 1 general.base_model.count 1
12 STRING 1 general.base_model.0.name Mistral Small 24B Instruct 2501
13 STRING 1 general.base_model.0.version 2501
14 STRING 1 general.base_model.0.organization Mistralai
15 STRING 1 general.base_model.0.repo_url https://huggingface.co/mistral...istral-Small-24B-Instruct-2501
16 UINT32 1 llama.context_length 32768
17 UINT32 1 llama.embedding_length 5120
18 UINT32 1 llama.feed_forward_length 32768
19 UINT32 1 llama.attention.head_count 32
20 UINT32 1 llama.attention.head_count_kv 8
21 FLOAT32 1 llama.rope.freq_base 100000000.0
22 FLOAT32 1 llama.attention.layer_norm_rms_epsilon 1e-05
23 UINT32 1 llama.attention.key_length 128
24 UINT32 1 llama.attention.value_length 128
25 UINT32 1 llama.vocab_size 131072
26 UINT32 1 llama.rope.dimension_count 128
27 STRING 1 tokenizer.ggml.model gpt2
28 STRING 1 tokenizer.ggml.pre tekken
29 [STRING] 131072 tokenizer.ggml.tokens [ <unk>, <s>, </s>, [INST], [/INST], ... ]
30 [INT32] 131072 tokenizer.ggml.token_type [ 3, 3, 3, 3, 3, 3, 3, ... ]
31 [STRING] 269443 tokenizer.ggml.merges [ Ġ Ġ, Ġ t, e r, i n, Ġ ĠĠĠ, ... ]
32 UINT32 1 tokenizer.ggml.bos_token_id 1
33 UINT32 1 tokenizer.ggml.eos_token_id 2
34 UINT32 1 tokenizer.ggml.unknown_token_id 0
35 UINT32 1 tokenizer.ggml.padding_token_id 11
36 BOOL 1 tokenizer.ggml.add_bos_token True
37 BOOL 1 tokenizer.ggml.add_eos_token False
38 STRING 1 tokenizer.chat_template {%- set today = strftime_now("... {%- endif %}{%- endfor %}
39 BOOL 1 tokenizer.ggml.add_space_prefix False
40 UINT32 1 general.quantization_version 2
41 UINT32 1 general.file_type 26
42 STRING 1 quantize.imatrix.file ./imatrix/imatrix-Dolphin-Mist...l-24B-Venice-Edition-small.dat
43 STRING 1 quantize.imatrix.dataset ../../datasets/imatrix/combined_eur_small.txt
44 UINT32 1 quantize.imatrix.entries_count 281
45 UINT32 1 quantize.imatrix.chunks_count 3192
46 UINT32 1 llama.block_count 38

Tensors Overview ~22B Elements

Total number of elements in all tensors: 22460892160 Elements

Tensor Data Offset

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

T_ID Tensor Layer Name Data Offset (B) Data Size (B)
0 output.weight 0x784500 0xf500000
1 output_norm.weight 0xfc84500 0x5000
2 token_embd.weight 0xfc89500 0xf500000
3 blk.0.attn_k.weight 0x1f189500 0x1ea000
4 blk.0.attn_norm.weight 0x1f373500 0x5000
5 blk.0.attn_output.weight 0x1f378500 0x898000
6 blk.0.attn_q.weight 0x1fc10500 0x7a8000
7 blk.0.attn_v.weight 0x203b8500 0x226000
8 blk.0.ffn_down.weight 0x205de500 0x44c0000
9 blk.0.ffn_gate.weight 0x24a9e500 0x3d40000
10 blk.0.ffn_norm.weight 0x287de500 0x5000
11 blk.0.ffn_up.weight 0x287e3500 0x3d40000
12 blk.1.attn_k.weight 0x2c523500 0x1ea000
13 blk.1.attn_norm.weight 0x2c70d500 0x5000
14 blk.1.attn_output.weight 0x2c712500 0x898000
15 blk.1.attn_q.weight 0x2cfaa500 0x7a8000
16 blk.1.attn_v.weight 0x2d752500 0x226000
17 blk.1.ffn_down.weight 0x2d978500 0x44c0000
18 blk.1.ffn_gate.weight 0x31e38500 0x3d40000
19 blk.1.ffn_norm.weight 0x35b78500 0x5000
20 blk.1.ffn_up.weight 0x35b7d500 0x3d40000
21 blk.2.attn_k.weight 0x398bd500 0x1ea000
22 blk.2.attn_norm.weight 0x39aa7500 0x5000
23 blk.2.attn_output.weight 0x39aac500 0x898000
24 blk.2.attn_q.weight 0x3a344500 0x7a8000
25 blk.2.attn_v.weight 0x3aaec500 0x226000
26 blk.2.ffn_down.weight 0x3ad12500 0x44c0000
27 blk.2.ffn_gate.weight 0x3f1d2500 0x3d40000
28 blk.2.ffn_norm.weight 0x42f12500 0x5000
29 blk.2.ffn_up.weight 0x42f17500 0x3d40000
30 blk.3.attn_k.weight 0x46c57500 0x1ea000
31 blk.3.attn_norm.weight 0x46e41500 0x5000
32 blk.3.attn_output.weight 0x46e46500 0x898000
33 blk.3.attn_q.weight 0x476de500 0x7a8000
34 blk.3.attn_v.weight 0x47e86500 0x226000
35 blk.3.ffn_down.weight 0x480ac500 0x44c0000
36 blk.3.ffn_gate.weight 0x4c56c500 0x3d40000
37 blk.3.ffn_norm.weight 0x502ac500 0x5000
38 blk.3.ffn_up.weight 0x502b1500 0x3d40000
39 blk.4.attn_k.weight 0x53ff1500 0x1ea000
40 blk.4.attn_norm.weight 0x541db500 0x5000
41 blk.4.attn_output.weight 0x541e0500 0x898000
42 blk.4.attn_q.weight 0x54a78500 0x7a8000
43 blk.4.attn_v.weight 0x55220500 0x226000
44 blk.4.ffn_down.weight 0x55446500 0x44c0000
45 blk.4.ffn_gate.weight 0x59906500 0x3d40000
46 blk.4.ffn_norm.weight 0x5d646500 0x5000
47 blk.4.ffn_up.weight 0x5d64b500 0x3d40000
48 blk.5.attn_k.weight 0x6138b500 0x1ea000
49 blk.5.attn_norm.weight 0x61575500 0x5000
50 blk.5.attn_output.weight 0x6157a500 0x898000
51 blk.5.attn_q.weight 0x61e12500 0x7a8000
52 blk.5.attn_v.weight 0x625ba500 0x226000
53 blk.5.ffn_down.weight 0x627e0500 0x44c0000
54 blk.5.ffn_gate.weight 0x66ca0500 0x3d40000
55 blk.5.ffn_norm.weight 0x6a9e0500 0x5000
56 blk.5.ffn_up.weight 0x6a9e5500 0x3d40000
57 blk.6.attn_k.weight 0x6e725500 0x1ea000
58 blk.6.attn_norm.weight 0x6e90f500 0x5000
59 blk.6.attn_output.weight 0x6e914500 0x898000
60 blk.6.attn_q.weight 0x6f1ac500 0x7a8000
61 blk.6.attn_v.weight 0x6f954500 0x226000
62 blk.6.ffn_down.weight 0x6fb7a500 0x44c0000
63 blk.6.ffn_gate.weight 0x7403a500 0x3d40000
64 blk.6.ffn_norm.weight 0x77d7a500 0x5000
65 blk.6.ffn_up.weight 0x77d7f500 0x3d40000
66 blk.7.attn_k.weight 0x7babf500 0x1ea000
67 blk.7.attn_norm.weight 0x7bca9500 0x5000
68 blk.7.attn_output.weight 0x7bcae500 0x898000
69 blk.7.attn_q.weight 0x7c546500 0x7a8000
70 blk.7.attn_v.weight 0x7ccee500 0x226000
71 blk.7.ffn_down.weight 0x7cf14500 0x44c0000
72 blk.7.ffn_gate.weight 0x813d4500 0x3d40000
73 blk.7.ffn_norm.weight 0x85114500 0x5000
74 blk.7.ffn_up.weight 0x85119500 0x3d40000
75 blk.8.attn_k.weight 0x88e59500 0x1ea000
76 blk.8.attn_norm.weight 0x89043500 0x5000
77 blk.8.attn_output.weight 0x89048500 0x898000
78 blk.8.attn_q.weight 0x898e0500 0x7a8000
79 blk.8.attn_v.weight 0x8a088500 0x226000
80 blk.8.ffn_down.weight 0x8a2ae500 0x44c0000
81 blk.8.ffn_gate.weight 0x8e76e500 0x3d40000
82 blk.8.ffn_norm.weight 0x924ae500 0x5000
83 blk.8.ffn_up.weight 0x924b3500 0x3d40000
84 blk.9.attn_k.weight 0x961f3500 0x1ea000
85 blk.9.attn_norm.weight 0x963dd500 0x5000
86 blk.9.attn_output.weight 0x963e2500 0x898000
87 blk.9.attn_q.weight 0x96c7a500 0x7a8000
88 blk.9.attn_v.weight 0x97422500 0x226000
89 blk.9.ffn_down.weight 0x97648500 0x44c0000
90 blk.9.ffn_gate.weight 0x9bb08500 0x3d40000
91 blk.9.ffn_norm.weight 0x9f848500 0x5000
92 blk.9.ffn_up.weight 0x9f84d500 0x3d40000
93 blk.10.attn_k.weight 0xa358d500 0x1ea000
94 blk.10.attn_norm.weight 0xa3777500 0x5000
95 blk.10.attn_output.weight 0xa377c500 0x898000
96 blk.10.attn_q.weight 0xa4014500 0x7a8000
97 blk.10.attn_v.weight 0xa47bc500 0x226000
98 blk.10.ffn_down.weight 0xa49e2500 0x44c0000
99 blk.10.ffn_gate.weight 0xa8ea2500 0x3d40000
100 blk.10.ffn_norm.weight 0xacbe2500 0x5000
101 blk.10.ffn_up.weight 0xacbe7500 0x3d40000
102 blk.11.attn_k.weight 0xb0927500 0x1ea000
103 blk.11.attn_norm.weight 0xb0b11500 0x5000
104 blk.11.attn_output.weight 0xb0b16500 0x898000
105 blk.11.attn_q.weight 0xb13ae500 0x7a8000
106 blk.11.attn_v.weight 0xb1b56500 0x226000
107 blk.11.ffn_down.weight 0xb1d7c500 0x44c0000
108 blk.11.ffn_gate.weight 0xb623c500 0x3d40000
109 blk.11.ffn_norm.weight 0xb9f7c500 0x5000
110 blk.11.ffn_up.weight 0xb9f81500 0x3d40000
111 blk.12.attn_k.weight 0xbdcc1500 0x1ea000
112 blk.12.attn_norm.weight 0xbdeab500 0x5000
113 blk.12.attn_output.weight 0xbdeb0500 0x898000
114 blk.12.attn_q.weight 0xbe748500 0x7a8000
115 blk.12.attn_v.weight 0xbeef0500 0x226000
116 blk.12.ffn_down.weight 0xbf116500 0x44c0000
117 blk.12.ffn_gate.weight 0xc35d6500 0x3d40000
118 blk.12.ffn_norm.weight 0xc7316500 0x5000
119 blk.12.ffn_up.weight 0xc731b500 0x3d40000
120 blk.13.attn_k.weight 0xcb05b500 0x1ea000
121 blk.13.attn_norm.weight 0xcb245500 0x5000
122 blk.13.attn_output.weight 0xcb24a500 0x898000
123 blk.13.attn_q.weight 0xcbae2500 0x7a8000
124 blk.13.attn_v.weight 0xcc28a500 0x226000
125 blk.13.ffn_down.weight 0xcc4b0500 0x44c0000
126 blk.13.ffn_gate.weight 0xd0970500 0x3d40000
127 blk.13.ffn_norm.weight 0xd46b0500 0x5000
128 blk.13.ffn_up.weight 0xd46b5500 0x3d40000
129 blk.14.attn_k.weight 0xd83f5500 0x1ea000
130 blk.14.attn_norm.weight 0xd85df500 0x5000
131 blk.14.attn_output.weight 0xd85e4500 0x898000
132 blk.14.attn_q.weight 0xd8e7c500 0x7a8000
133 blk.14.attn_v.weight 0xd9624500 0x226000
134 blk.14.ffn_down.weight 0xd984a500 0x44c0000
135 blk.14.ffn_gate.weight 0xddd0a500 0x3d40000
136 blk.14.ffn_norm.weight 0xe1a4a500 0x5000
137 blk.14.ffn_up.weight 0xe1a4f500 0x3d40000
138 blk.15.attn_k.weight 0xe578f500 0x1ea000
139 blk.15.attn_norm.weight 0xe5979500 0x5000
140 blk.15.attn_output.weight 0xe597e500 0x898000
141 blk.15.attn_q.weight 0xe6216500 0x7a8000
142 blk.15.attn_v.weight 0xe69be500 0x226000
143 blk.15.ffn_down.weight 0xe6be4500 0x44c0000
144 blk.15.ffn_gate.weight 0xeb0a4500 0x3d40000
145 blk.15.ffn_norm.weight 0xeede4500 0x5000
146 blk.15.ffn_up.weight 0xeede9500 0x3d40000
147 blk.16.attn_k.weight 0xf2b29500 0x1ea000
148 blk.16.attn_norm.weight 0xf2d13500 0x5000
149 blk.16.attn_output.weight 0xf2d18500 0x898000
150 blk.16.attn_q.weight 0xf35b0500 0x7a8000
151 blk.16.attn_v.weight 0xf3d58500 0x226000
152 blk.16.ffn_down.weight 0xf3f7e500 0x44c0000
153 blk.16.ffn_gate.weight 0xf843e500 0x3d40000
154 blk.16.ffn_norm.weight 0xfc17e500 0x5000
155 blk.16.ffn_up.weight 0xfc183500 0x3d40000
156 blk.17.attn_k.weight 0xffec3500 0x226000
157 blk.17.attn_norm.weight 0x1000e9500 0x5000
158 blk.17.attn_output.weight 0x1000ee500 0x898000
159 blk.17.attn_q.weight 0x100986500 0x898000
160 blk.17.attn_v.weight 0x10121e500 0x226000
161 blk.17.ffn_down.weight 0x101444500 0x44c0000
162 blk.17.ffn_gate.weight 0x105904500 0x3d40000
163 blk.17.ffn_norm.weight 0x109644500 0x5000
164 blk.17.ffn_up.weight 0x109649500 0x3d40000
165 blk.18.attn_k.weight 0x10d389500 0x226000
166 blk.18.attn_norm.weight 0x10d5af500 0x5000
167 blk.18.attn_output.weight 0x10d5b4500 0x898000
168 blk.18.attn_q.weight 0x10de4c500 0x898000
169 blk.18.attn_v.weight 0x10e6e4500 0x226000
170 blk.18.ffn_down.weight 0x10e90a500 0x44c0000
171 blk.18.ffn_gate.weight 0x112dca500 0x3d40000
172 blk.18.ffn_norm.weight 0x116b0a500 0x5000
173 blk.18.ffn_up.weight 0x116b0f500 0x3d40000
174 blk.19.attn_k.weight 0x11a84f500 0x1ea000
175 blk.19.attn_norm.weight 0x11aa39500 0x5000
176 blk.19.attn_output.weight 0x11aa3e500 0x898000
177 blk.19.attn_q.weight 0x11b2d6500 0x7a8000
178 blk.19.attn_v.weight 0x11ba7e500 0x226000
179 blk.19.ffn_down.weight 0x11bca4500 0x44c0000
180 blk.19.ffn_gate.weight 0x120164500 0x3d40000
181 blk.19.ffn_norm.weight 0x123ea4500 0x5000
182 blk.19.ffn_up.weight 0x123ea9500 0x3d40000
183 blk.20.attn_k.weight 0x127be9500 0x226000
184 blk.20.attn_norm.weight 0x127e0f500 0x5000
185 blk.20.attn_output.weight 0x127e14500 0x898000
186 blk.20.attn_q.weight 0x1286ac500 0x898000
187 blk.20.attn_v.weight 0x128f44500 0x226000
188 blk.20.ffn_down.weight 0x12916a500 0x44c0000
189 blk.20.ffn_gate.weight 0x12d62a500 0x44c0000
190 blk.20.ffn_norm.weight 0x131aea500 0x5000
191 blk.20.ffn_up.weight 0x131aef500 0x44c0000
192 blk.21.attn_k.weight 0x135faf500 0x1ea000
193 blk.21.attn_norm.weight 0x136199500 0x5000
194 blk.21.attn_output.weight 0x13619e500 0x898000
195 blk.21.attn_q.weight 0x136a36500 0x7a8000
196 blk.21.attn_v.weight 0x1371de500 0x226000
197 blk.21.ffn_down.weight 0x137404500 0x44c0000
198 blk.21.ffn_gate.weight 0x13b8c4500 0x44c0000
199 blk.21.ffn_norm.weight 0x13fd84500 0x5000
200 blk.21.ffn_up.weight 0x13fd89500 0x44c0000
201 blk.22.attn_k.weight 0x144249500 0x226000
202 blk.22.attn_norm.weight 0x14446f500 0x5000
203 blk.22.attn_output.weight 0x144474500 0x898000
204 blk.22.attn_q.weight 0x144d0c500 0x898000
205 blk.22.attn_v.weight 0x1455a4500 0x226000
206 blk.22.ffn_down.weight 0x1457ca500 0x44c0000
207 blk.22.ffn_gate.weight 0x149c8a500 0x44c0000
208 blk.22.ffn_norm.weight 0x14e14a500 0x5000
209 blk.22.ffn_up.weight 0x14e14f500 0x44c0000
210 blk.23.attn_k.weight 0x15260f500 0x226000
211 blk.23.attn_norm.weight 0x152835500 0x5000
212 blk.23.attn_output.weight 0x15283a500 0x898000
213 blk.23.attn_q.weight 0x1530d2500 0x898000
214 blk.23.attn_v.weight 0x15396a500 0x226000
215 blk.23.ffn_down.weight 0x153b90500 0x44c0000
216 blk.23.ffn_gate.weight 0x158050500 0x44c0000
217 blk.23.ffn_norm.weight 0x15c510500 0x5000
218 blk.23.ffn_up.weight 0x15c515500 0x44c0000
219 blk.24.attn_k.weight 0x1609d5500 0x226000
220 blk.24.attn_norm.weight 0x160bfb500 0x5000
221 blk.24.attn_output.weight 0x160c00500 0x898000
222 blk.24.attn_q.weight 0x161498500 0x898000
223 blk.24.attn_v.weight 0x161d30500 0x226000
224 blk.24.ffn_down.weight 0x161f56500 0x44c0000
225 blk.24.ffn_gate.weight 0x166416500 0x44c0000
226 blk.24.ffn_norm.weight 0x16a8d6500 0x5000
227 blk.24.ffn_up.weight 0x16a8db500 0x44c0000
228 blk.25.attn_k.weight 0x16ed9b500 0x226000
229 blk.25.attn_norm.weight 0x16efc1500 0x5000
230 blk.25.attn_output.weight 0x16efc6500 0x898000
231 blk.25.attn_q.weight 0x16f85e500 0x898000
232 blk.25.attn_v.weight 0x1700f6500 0x226000
233 blk.25.ffn_down.weight 0x17031c500 0x44c0000
234 blk.25.ffn_gate.weight 0x1747dc500 0x44c0000
235 blk.25.ffn_norm.weight 0x178c9c500 0x5000
236 blk.25.ffn_up.weight 0x178ca1500 0x44c0000
237 blk.26.attn_k.weight 0x17d161500 0x226000
238 blk.26.attn_norm.weight 0x17d387500 0x5000
239 blk.26.attn_output.weight 0x17d38c500 0x898000
240 blk.26.attn_q.weight 0x17dc24500 0x898000
241 blk.26.attn_v.weight 0x17e4bc500 0x226000
242 blk.26.ffn_down.weight 0x17e6e2500 0x44c0000
243 blk.26.ffn_gate.weight 0x182ba2500 0x44c0000
244 blk.26.ffn_norm.weight 0x187062500 0x5000
245 blk.26.ffn_up.weight 0x187067500 0x44c0000
246 blk.27.attn_k.weight 0x18b527500 0x1ea000
247 blk.27.attn_norm.weight 0x18b711500 0x5000
248 blk.27.attn_output.weight 0x18b716500 0x898000
249 blk.27.attn_q.weight 0x18bfae500 0x7a8000
250 blk.27.attn_v.weight 0x18c756500 0x226000
251 blk.27.ffn_down.weight 0x18c97c500 0x44c0000
252 blk.27.ffn_gate.weight 0x190e3c500 0x44c0000
253 blk.27.ffn_norm.weight 0x1952fc500 0x5000
254 blk.27.ffn_up.weight 0x195301500 0x44c0000
255 blk.28.attn_k.weight 0x1997c1500 0x226000
256 blk.28.attn_norm.weight 0x1999e7500 0x5000
257 blk.28.attn_output.weight 0x1999ec500 0x898000
258 blk.28.attn_q.weight 0x19a284500 0x898000
259 blk.28.attn_v.weight 0x19ab1c500 0x226000
260 blk.28.ffn_down.weight 0x19ad42500 0x44c0000
261 blk.28.ffn_gate.weight 0x19f202500 0x44c0000
262 blk.28.ffn_norm.weight 0x1a36c2500 0x5000
263 blk.28.ffn_up.weight 0x1a36c7500 0x44c0000
264 blk.29.attn_k.weight 0x1a7b87500 0x226000
265 blk.29.attn_norm.weight 0x1a7dad500 0x5000
266 blk.29.attn_output.weight 0x1a7db2500 0x898000
267 blk.29.attn_q.weight 0x1a864a500 0x898000
268 blk.29.attn_v.weight 0x1a8ee2500 0x226000
269 blk.29.ffn_down.weight 0x1a9108500 0x44c0000
270 blk.29.ffn_gate.weight 0x1ad5c8500 0x44c0000
271 blk.29.ffn_norm.weight 0x1b1a88500 0x5000
272 blk.29.ffn_up.weight 0x1b1a8d500 0x44c0000
273 blk.30.attn_k.weight 0x1b5f4d500 0x226000
274 blk.30.attn_norm.weight 0x1b6173500 0x5000
275 blk.30.attn_output.weight 0x1b6178500 0x898000
276 blk.30.attn_q.weight 0x1b6a10500 0x898000
277 blk.30.attn_v.weight 0x1b72a8500 0x226000
278 blk.30.ffn_down.weight 0x1b74ce500 0x44c0000
279 blk.30.ffn_gate.weight 0x1bb98e500 0x44c0000
280 blk.30.ffn_norm.weight 0x1bfe4e500 0x5000
281 blk.30.ffn_up.weight 0x1bfe53500 0x44c0000
282 blk.31.attn_k.weight 0x1c4313500 0x226000
283 blk.31.attn_norm.weight 0x1c4539500 0x5000
284 blk.31.attn_output.weight 0x1c453e500 0x898000
285 blk.31.attn_q.weight 0x1c4dd6500 0x898000
286 blk.31.attn_v.weight 0x1c566e500 0x226000
287 blk.31.ffn_down.weight 0x1c5894500 0x44c0000
288 blk.31.ffn_gate.weight 0x1c9d54500 0x44c0000
289 blk.31.ffn_norm.weight 0x1ce214500 0x5000
290 blk.31.ffn_up.weight 0x1ce219500 0x44c0000
291 blk.32.attn_k.weight 0x1d26d9500 0x226000
292 blk.32.attn_norm.weight 0x1d28ff500 0x5000
293 blk.32.attn_output.weight 0x1d2904500 0x898000
294 blk.32.attn_q.weight 0x1d319c500 0x898000
295 blk.32.attn_v.weight 0x1d3a34500 0x226000
296 blk.32.ffn_down.weight 0x1d3c5a500 0x44c0000
297 blk.32.ffn_gate.weight 0x1d811a500 0x44c0000
298 blk.32.ffn_norm.weight 0x1dc5da500 0x5000
299 blk.32.ffn_up.weight 0x1dc5df500 0x44c0000
300 blk.33.attn_k.weight 0x1e0a9f500 0x226000
301 blk.33.attn_norm.weight 0x1e0cc5500 0x5000
302 blk.33.attn_output.weight 0x1e0cca500 0x898000
303 blk.33.attn_q.weight 0x1e1562500 0x898000
304 blk.33.attn_v.weight 0x1e1dfa500 0x226000
305 blk.33.ffn_down.weight 0x1e2020500 0x44c0000
306 blk.33.ffn_gate.weight 0x1e64e0500 0x44c0000
307 blk.33.ffn_norm.weight 0x1ea9a0500 0x5000
308 blk.33.ffn_up.weight 0x1ea9a5500 0x44c0000
309 blk.34.attn_k.weight 0x1eee65500 0x226000
310 blk.34.attn_norm.weight 0x1ef08b500 0x5000
311 blk.34.attn_output.weight 0x1ef090500 0x898000
312 blk.34.attn_q.weight 0x1ef928500 0x898000
313 blk.34.attn_v.weight 0x1f01c0500 0x226000
314 blk.34.ffn_down.weight 0x1f03e6500 0x44c0000
315 blk.34.ffn_gate.weight 0x1f48a6500 0x44c0000
316 blk.34.ffn_norm.weight 0x1f8d66500 0x5000
317 blk.34.ffn_up.weight 0x1f8d6b500 0x44c0000
318 blk.35.attn_k.weight 0x1fd22b500 0x226000
319 blk.35.attn_norm.weight 0x1fd451500 0x5000
320 blk.35.attn_output.weight 0x1fd456500 0x898000
321 blk.35.attn_q.weight 0x1fdcee500 0x898000
322 blk.35.attn_v.weight 0x1fe586500 0x226000
323 blk.35.ffn_down.weight 0x1fe7ac500 0x44c0000
324 blk.35.ffn_gate.weight 0x202c6c500 0x44c0000
325 blk.35.ffn_norm.weight 0x20712c500 0x5000
326 blk.35.ffn_up.weight 0x207131500 0x44c0000
327 blk.36.attn_k.weight 0x20b5f1500 0x226000
328 blk.36.attn_norm.weight 0x20b817500 0x5000
329 blk.36.attn_output.weight 0x20b81c500 0x898000
330 blk.36.attn_q.weight 0x20c0b4500 0x898000
331 blk.36.attn_v.weight 0x20c94c500 0x226000
332 blk.36.ffn_down.weight 0x20cb72500 0x44c0000
333 blk.36.ffn_gate.weight 0x211032500 0x44c0000
334 blk.36.ffn_norm.weight 0x2154f2500 0x5000
335 blk.36.ffn_up.weight 0x2154f7500 0x44c0000
336 blk.37.attn_k.weight 0x2199b7500 0x226000
337 blk.37.attn_norm.weight 0x219bdd500 0x5000
338 blk.37.attn_output.weight 0x219be2500 0x898000
339 blk.37.attn_q.weight 0x21a47a500 0x898000
340 blk.37.attn_v.weight 0x21ad12500 0x226000
341 blk.37.ffn_down.weight 0x21af38500 0x44c0000
342 blk.37.ffn_gate.weight 0x21f3f8500 0x44c0000
343 blk.37.ffn_norm.weight 0x2238b8500 0x5000
344 blk.37.ffn_up.weight 0x2238bd500 0x44c0000

Base Tensor Group : ~1B Elements

T_ID Tensor Layer Name Human Friendly Tensor Layer Name Elements Shape Type
0 output.weight Output (W) (~671M) 671088640 5120 x 131072 x 1 x 1 IQ3_XXS
1 output_norm.weight Output Normalization (W) ( ~5K) 5120 5120 x 1 x 1 x 1 F32
2 token_embd.weight Token Embedding (W) (~671M) 671088640 5120 x 131072 x 1 x 1 IQ3_XXS
  • Total elements in base: ( ~1B) 1342182400
  • Percentage of total elements: 5.98%

Block 0 Tensor Group : ~556M Elements

T_ID Tensor Layer Name Human Friendly Tensor Layer Name Elements Shape Type
3 blk.0.attn_k.weight Block 0 Attention Key (W) ( ~5M) 5242880 5120 x 1024 x 1 x 1 IQ3_XXS
4 blk.0.attn_norm.weight Block 0 Attention Normalization (W) ( ~5K) 5120 5120 x 1 x 1 x 1 F32
5 blk.0.attn_output.weight Block 0 Attention Output (W) ( ~21M) 20971520 4096 x 5120 x 1 x 1 IQ3_S
6 blk.0.attn_q.weight Block 0 Attention Query (W) ( ~21M) 20971520 5120 x 4096 x 1 x 1 IQ3_XXS
7 blk.0.attn_v.weight Block 0 Attention Value (W) ( ~5M) 5242880 5120 x 1024 x 1 x 1 IQ3_S
8 blk.0.ffn_down.weight Block 0 Feed-Forward Network "Down" (W) (~168M) 167772160 32768 x 5120 x 1 x 1 IQ3_S
9 blk.0.ffn_gate.weight Block 0 Feed-Forward Network "Gate" (W) (~168M) 167772160 5120 x 32768 x 1 x 1 IQ3_XXS
10 blk.0.ffn_norm.weight Block 0 Feed-Forward Network Normalization (W) ( ~5K) 5120 5120 x 1 x 1 x 1 F32
11 blk.0.ffn_up.weight Block 0 Feed-Forward Network "Up" (W) (~168M) 167772160 5120 x 32768 x 1 x 1 IQ3_XXS
  • Total elements in blk.0: (~556M) 555755520
  • Percentage of total elements: 2.47%

Block 1 Tensor Group : ~556M Elements

T_ID Tensor Layer Name Human Friendly Tensor Layer Name Elements Shape Type
12 blk.1.attn_k.weight Block 1 Attention Key (W) ( ~5M) 5242880 5120 x 1024 x 1 x 1 IQ3_XXS
13 blk.1.attn_norm.weight Block 1 Attention Normalization (W) ( ~5K) 5120 5120 x 1 x 1 x 1 F32
14 blk.1.attn_output.weight Block 1 Attention Output (W) ( ~21M) 20971520 4096 x 5120 x 1 x 1 IQ3_S
15 blk.1.attn_q.weight Block 1 Attention Query (W) ( ~21M) 20971520 5120 x 4096 x 1 x 1 IQ3_XXS
16 blk.1.attn_v.weight Block 1 Attention Value (W) ( ~5M) 5242880 5120 x 1024 x 1 x 1 IQ3_S
17 blk.1.ffn_down.weight Block 1 Feed-Forward Network "Down" (W) (~168M) 167772160 32768 x 5120 x 1 x 1 IQ3_S
18 blk.1.ffn_gate.weight Block 1 Feed-Forward Network "Gate" (W) (~168M) 167772160 5120 x 32768 x 1 x 1 IQ3_XXS
19 blk.1.ffn_norm.weight Block 1 Feed-Forward Network Normalization (W) ( ~5K) 5120 5120 x 1 x 1 x 1 F32
20 blk.1.ffn_up.weight Block 1 Feed-Forward Network "Up" (W) (~168M) 167772160 5120 x 32768 x 1 x 1 IQ3_XXS
  • Total elements in blk.1: (~556M) 555755520
  • Percentage of total elements: 2.47%

Block 2 Tensor Group : ~556M Elements

T_ID Tensor Layer Name Human Friendly Tensor Layer Name Elements Shape Type
21 blk.2.attn_k.weight Block 2 Attention Key (W) ( ~5M) 5242880 5120 x 1024 x 1 x 1 IQ3_XXS
22 blk.2.attn_norm.weight Block 2 Attention Normalization (W) ( ~5K) 5120 5120 x 1 x 1 x 1 F32
23 blk.2.attn_output.weight Block 2 Attention Output (W) ( ~21M) 20971520 4096 x 5120 x 1 x 1 IQ3_S
24 blk.2.attn_q.weight Block 2 Attention Query (W) ( ~21M) 20971520 5120 x 4096 x 1 x 1 IQ3_XXS
25 blk.2.attn_v.weight Block 2 Attention Value (W) ( ~5M) 5242880 5120 x 1024 x 1 x 1 IQ3_S
26 blk.2.ffn_down.weight Block 2 Feed-Forward Network "Down" (W) (~168M) 167772160 32768 x 5120 x 1 x 1 IQ3_S
27 blk.2.ffn_gate.weight Block 2 Feed-Forward Network "Gate" (W) (~168M) 167772160 5120 x 32768 x 1 x 1 IQ3_XXS
28 blk.2.ffn_norm.weight Block 2 Feed-Forward Network Normalization (W) ( ~5K) 5120 5120 x 1 x 1 x 1 F32
29 blk.2.ffn_up.weight Block 2 Feed-Forward Network "Up" (W) (~168M) 167772160 5120 x 32768 x 1 x 1 IQ3_XXS
  • Total elements in blk.2: (~556M) 555755520
  • Percentage of total elements: 2.47%

Block 3 Tensor Group : ~556M Elements

T_ID Tensor Layer Name Human Friendly Tensor Layer Name Elements Shape Type
30 blk.3.attn_k.weight Block 3 Attention Key (W) ( ~5M) 5242880 5120 x 1024 x 1 x 1 IQ3_XXS
31 blk.3.attn_norm.weight Block 3 Attention Normalization (W) ( ~5K) 5120 5120 x 1 x 1 x 1 F32
32 blk.3.attn_output.weight Block 3 Attention Output (W) ( ~21M) 20971520 4096 x 5120 x 1 x 1 IQ3_S
33 blk.3.attn_q.weight Block 3 Attention Query (W) ( ~21M) 20971520 5120 x 4096 x 1 x 1 IQ3_XXS
34 blk.3.attn_v.weight Block 3 Attention Value (W) ( ~5M) 5242880 5120 x 1024 x 1 x 1 IQ3_S
35 blk.3.ffn_down.weight Block 3 Feed-Forward Network "Down" (W) (~168M) 167772160 32768 x 5120 x 1 x 1 IQ3_S
36 blk.3.ffn_gate.weight Block 3 Feed-Forward Network "Gate" (W) (~168M) 167772160 5120 x 32768 x 1 x 1 IQ3_XXS
37 blk.3.ffn_norm.weight Block 3 Feed-Forward Network Normalization (W) ( ~5K) 5120 5120 x 1 x 1 x 1 F32
38 blk.3.ffn_up.weight Block 3 Feed-Forward Network "Up" (W) (~168M) 167772160 5120 x 32768 x 1 x 1 IQ3_XXS
  • Total elements in blk.3: (~556M) 555755520
  • Percentage of total elements: 2.47%

Block 4 Tensor Group : ~556M Elements

T_ID Tensor Layer Name Human Friendly Tensor Layer Name Elements Shape Type
39 blk.4.attn_k.weight Block 4 Attention Key (W) ( ~5M) 5242880 5120 x 1024 x 1 x 1 IQ3_XXS
40 blk.4.attn_norm.weight Block 4 Attention Normalization (W) ( ~5K) 5120 5120 x 1 x 1 x 1 F32
41 blk.4.attn_output.weight Block 4 Attention Output (W) ( ~21M) 20971520 4096 x 5120 x 1 x 1 IQ3_S
42 blk.4.attn_q.weight Block 4 Attention Query (W) ( ~21M) 20971520 5120 x 4096 x 1 x 1 IQ3_XXS
43 blk.4.attn_v.weight Block 4 Attention Value (W) ( ~5M) 5242880 5120 x 1024 x 1 x 1 IQ3_S
44 blk.4.ffn_down.weight Block 4 Feed-Forward Network "Down" (W) (~168M) 167772160 32768 x 5120 x 1 x 1 IQ3_S
45 blk.4.ffn_gate.weight Block 4 Feed-Forward Network "Gate" (W) (~168M) 167772160 5120 x 32768 x 1 x 1 IQ3_XXS
46 blk.4.ffn_norm.weight Block 4 Feed-Forward Network Normalization (W) ( ~5K) 5120 5120 x 1 x 1 x 1 F32
47 blk.4.ffn_up.weight Block 4 Feed-Forward Network "Up" (W) (~168M) 167772160 5120 x 32768 x 1 x 1 IQ3_XXS
  • Total elements in blk.4: (~556M) 555755520
  • Percentage of total elements: 2.47%

Block 5 Tensor Group : ~556M Elements

T_ID Tensor Layer Name Human Friendly Tensor Layer Name Elements Shape Type
48 blk.5.attn_k.weight Block 5 Attention Key (W) ( ~5M) 5242880 5120 x 1024 x 1 x 1 IQ3_XXS
49 blk.5.attn_norm.weight Block 5 Attention Normalization (W) ( ~5K) 5120 5120 x 1 x 1 x 1 F32
50 blk.5.attn_output.weight Block 5 Attention Output (W) ( ~21M) 20971520 4096 x 5120 x 1 x 1 IQ3_S
51 blk.5.attn_q.weight Block 5 Attention Query (W) ( ~21M) 20971520 5120 x 4096 x 1 x 1 IQ3_XXS
52 blk.5.attn_v.weight Block 5 Attention Value (W) ( ~5M) 5242880 5120 x 1024 x 1 x 1 IQ3_S
53 blk.5.ffn_down.weight Block 5 Feed-Forward Network "Down" (W) (~168M) 167772160 32768 x 5120 x 1 x 1 IQ3_S
54 blk.5.ffn_gate.weight Block 5 Feed-Forward Network "Gate" (W) (~168M) 167772160 5120 x 32768 x 1 x 1 IQ3_XXS
55 blk.5.ffn_norm.weight Block 5 Feed-Forward Network Normalization (W) ( ~5K) 5120 5120 x 1 x 1 x 1 F32
56 blk.5.ffn_up.weight Block 5 Feed-Forward Network "Up" (W) (~168M) 167772160 5120 x 32768 x 1 x 1 IQ3_XXS
  • Total elements in blk.5: (~556M) 555755520
  • Percentage of total elements: 2.47%

Block 6 Tensor Group : ~556M Elements

T_ID Tensor Layer Name Human Friendly Tensor Layer Name Elements Shape Type
57 blk.6.attn_k.weight Block 6 Attention Key (W) ( ~5M) 5242880 5120 x 1024 x 1 x 1 IQ3_XXS
58 blk.6.attn_norm.weight Block 6 Attention Normalization (W) ( ~5K) 5120 5120 x 1 x 1 x 1 F32
59 blk.6.attn_output.weight Block 6 Attention Output (W) ( ~21M) 20971520 4096 x 5120 x 1 x 1 IQ3_S
60 blk.6.attn_q.weight Block 6 Attention Query (W) ( ~21M) 20971520 5120 x 4096 x 1 x 1 IQ3_XXS
61 blk.6.attn_v.weight Block 6 Attention Value (W) ( ~5M) 5242880 5120 x 1024 x 1 x 1 IQ3_S
62 blk.6.ffn_down.weight Block 6 Feed-Forward Network "Down" (W) (~168M) 167772160 32768 x 5120 x 1 x 1 IQ3_S
63 blk.6.ffn_gate.weight Block 6 Feed-Forward Network "Gate" (W) (~168M) 167772160 5120 x 32768 x 1 x 1 IQ3_XXS
64 blk.6.ffn_norm.weight Block 6 Feed-Forward Network Normalization (W) ( ~5K) 5120 5120 x 1 x 1 x 1 F32
65 blk.6.ffn_up.weight Block 6 Feed-Forward Network "Up" (W) (~168M) 167772160 5120 x 32768 x 1 x 1 IQ3_XXS
  • Total elements in blk.6: (~556M) 555755520
  • Percentage of total elements: 2.47%

Block 7 Tensor Group : ~556M Elements

T_ID Tensor Layer Name Human Friendly Tensor Layer Name Elements Shape Type
66 blk.7.attn_k.weight Block 7 Attention Key (W) ( ~5M) 5242880 5120 x 1024 x 1 x 1 IQ3_XXS
67 blk.7.attn_norm.weight Block 7 Attention Normalization (W) ( ~5K) 5120 5120 x 1 x 1 x 1 F32
68 blk.7.attn_output.weight Block 7 Attention Output (W) ( ~21M) 20971520 4096 x 5120 x 1 x 1 IQ3_S
69 blk.7.attn_q.weight Block 7 Attention Query (W) ( ~21M) 20971520 5120 x 4096 x 1 x 1 IQ3_XXS
70 blk.7.attn_v.weight Block 7 Attention Value (W) ( ~5M) 5242880 5120 x 1024 x 1 x 1 IQ3_S
71 blk.7.ffn_down.weight Block 7 Feed-Forward Network "Down" (W) (~168M) 167772160 32768 x 5120 x 1 x 1 IQ3_S
72 blk.7.ffn_gate.weight Block 7 Feed-Forward Network "Gate" (W) (~168M) 167772160 5120 x 32768 x 1 x 1 IQ3_XXS
73 blk.7.ffn_norm.weight Block 7 Feed-Forward Network Normalization (W) ( ~5K) 5120 5120 x 1 x 1 x 1 F32
74 blk.7.ffn_up.weight Block 7 Feed-Forward Network "Up" (W) (~168M) 167772160 5120 x 32768 x 1 x 1 IQ3_XXS
  • Total elements in blk.7: (~556M) 555755520
  • Percentage of total elements: 2.47%

Block 8 Tensor Group : ~556M Elements

T_ID Tensor Layer Name Human Friendly Tensor Layer Name Elements Shape Type
75 blk.8.attn_k.weight Block 8 Attention Key (W) ( ~5M) 5242880 5120 x 1024 x 1 x 1 IQ3_XXS
76 blk.8.attn_norm.weight Block 8 Attention Normalization (W) ( ~5K) 5120 5120 x 1 x 1 x 1 F32
77 blk.8.attn_output.weight Block 8 Attention Output (W) ( ~21M) 20971520 4096 x 5120 x 1 x 1 IQ3_S
78 blk.8.attn_q.weight Block 8 Attention Query (W) ( ~21M) 20971520 5120 x 4096 x 1 x 1 IQ3_XXS
79 blk.8.attn_v.weight Block 8 Attention Value (W) ( ~5M) 5242880 5120 x 1024 x 1 x 1 IQ3_S
80 blk.8.ffn_down.weight Block 8 Feed-Forward Network "Down" (W) (~168M) 167772160 32768 x 5120 x 1 x 1 IQ3_S
81 blk.8.ffn_gate.weight Block 8 Feed-Forward Network "Gate" (W) (~168M) 167772160 5120 x 32768 x 1 x 1 IQ3_XXS
82 blk.8.ffn_norm.weight Block 8 Feed-Forward Network Normalization (W) ( ~5K) 5120 5120 x 1 x 1 x 1 F32
83 blk.8.ffn_up.weight Block 8 Feed-Forward Network "Up" (W) (~168M) 167772160 5120 x 32768 x 1 x 1 IQ3_XXS
  • Total elements in blk.8: (~556M) 555755520
  • Percentage of total elements: 2.47%

Block 9 Tensor Group : ~556M Elements

T_ID Tensor Layer Name Human Friendly Tensor Layer Name Elements Shape Type
84 blk.9.attn_k.weight Block 9 Attention Key (W) ( ~5M) 5242880 5120 x 1024 x 1 x 1 IQ3_XXS
85 blk.9.attn_norm.weight Block 9 Attention Normalization (W) ( ~5K) 5120 5120 x 1 x 1 x 1 F32
86 blk.9.attn_output.weight Block 9 Attention Output (W) ( ~21M) 20971520 4096 x 5120 x 1 x 1 IQ3_S
87 blk.9.attn_q.weight Block 9 Attention Query (W) ( ~21M) 20971520 5120 x 4096 x 1 x 1 IQ3_XXS
88 blk.9.attn_v.weight Block 9 Attention Value (W) ( ~5M) 5242880 5120 x 1024 x 1 x 1 IQ3_S
89 blk.9.ffn_down.weight Block 9 Feed-Forward Network "Down" (W) (~168M) 167772160 32768 x 5120 x 1 x 1 IQ3_S
90 blk.9.ffn_gate.weight Block 9 Feed-Forward Network "Gate" (W) (~168M) 167772160 5120 x 32768 x 1 x 1 IQ3_XXS
91 blk.9.ffn_norm.weight Block 9 Feed-Forward Network Normalization (W) ( ~5K) 5120 5120 x 1 x 1 x 1 F32
92 blk.9.ffn_up.weight Block 9 Feed-Forward Network "Up" (W) (~168M) 167772160 5120 x 32768 x 1 x 1 IQ3_XXS
  • Total elements in blk.9: (~556M) 555755520
  • Percentage of total elements: 2.47%

Block 10 Tensor Group : ~556M Elements

T_ID Tensor Layer Name Human Friendly Tensor Layer Name Elements Shape Type
93 blk.10.attn_k.weight Block 10 Attention Key (W) ( ~5M) 5242880 5120 x 1024 x 1 x 1 IQ3_XXS
94 blk.10.attn_norm.weight Block 10 Attention Normalization (W) ( ~5K) 5120 5120 x 1 x 1 x 1 F32
95 blk.10.attn_output.weight Block 10 Attention Output (W) ( ~21M) 20971520 4096 x 5120 x 1 x 1 IQ3_S
96 blk.10.attn_q.weight Block 10 Attention Query (W) ( ~21M) 20971520 5120 x 4096 x 1 x 1 IQ3_XXS
97 blk.10.attn_v.weight Block 10 Attention Value (W) ( ~5M) 5242880 5120 x 1024 x 1 x 1 IQ3_S
98 blk.10.ffn_down.weight Block 10 Feed-Forward Network "Down" (W) (~168M) 167772160 32768 x 5120 x 1 x 1 IQ3_S
99 blk.10.ffn_gate.weight Block 10 Feed-Forward Network "Gate" (W) (~168M) 167772160 5120 x 32768 x 1 x 1 IQ3_XXS
100 blk.10.ffn_norm.weight Block 10 Feed-Forward Network Normalization (W) ( ~5K) 5120 5120 x 1 x 1 x 1 F32
101 blk.10.ffn_up.weight Block 10 Feed-Forward Network "Up" (W) (~168M) 167772160 5120 x 32768 x 1 x 1 IQ3_XXS
  • Total elements in blk.10: (~556M) 555755520
  • Percentage of total elements: 2.47%

Block 11 Tensor Group : ~556M Elements

T_ID Tensor Layer Name Human Friendly Tensor Layer Name Elements Shape Type
102 blk.11.attn_k.weight Block 11 Attention Key (W) ( ~5M) 5242880 5120 x 1024 x 1 x 1 IQ3_XXS
103 blk.11.attn_norm.weight Block 11 Attention Normalization (W) ( ~5K) 5120 5120 x 1 x 1 x 1 F32
104 blk.11.attn_output.weight Block 11 Attention Output (W) ( ~21M) 20971520 4096 x 5120 x 1 x 1 IQ3_S
105 blk.11.attn_q.weight Block 11 Attention Query (W) ( ~21M) 20971520 5120 x 4096 x 1 x 1 IQ3_XXS
106 blk.11.attn_v.weight Block 11 Attention Value (W) ( ~5M) 5242880 5120 x 1024 x 1 x 1 IQ3_S
107 blk.11.ffn_down.weight Block 11 Feed-Forward Network "Down" (W) (~168M) 167772160 32768 x 5120 x 1 x 1 IQ3_S
108 blk.11.ffn_gate.weight Block 11 Feed-Forward Network "Gate" (W) (~168M) 167772160 5120 x 32768 x 1 x 1 IQ3_XXS
109 blk.11.ffn_norm.weight Block 11 Feed-Forward Network Normalization (W) ( ~5K) 5120 5120 x 1 x 1 x 1 F32
110 blk.11.ffn_up.weight Block 11 Feed-Forward Network "Up" (W) (~168M) 167772160 5120 x 32768 x 1 x 1 IQ3_XXS
  • Total elements in blk.11: (~556M) 555755520
  • Percentage of total elements: 2.47%

Block 12 Tensor Group : ~556M Elements

T_ID Tensor Layer Name Human Friendly Tensor Layer Name Elements Shape Type
111 blk.12.attn_k.weight Block 12 Attention Key (W) ( ~5M) 5242880 5120 x 1024 x 1 x 1 IQ3_XXS
112 blk.12.attn_norm.weight Block 12 Attention Normalization (W) ( ~5K) 5120 5120 x 1 x 1 x 1 F32
113 blk.12.attn_output.weight Block 12 Attention Output (W) ( ~21M) 20971520 4096 x 5120 x 1 x 1 IQ3_S
114 blk.12.attn_q.weight Block 12 Attention Query (W) ( ~21M) 20971520 5120 x 4096 x 1 x 1 IQ3_XXS
115 blk.12.attn_v.weight Block 12 Attention Value (W) ( ~5M) 5242880 5120 x 1024 x 1 x 1 IQ3_S
116 blk.12.ffn_down.weight Block 12 Feed-Forward Network "Down" (W) (~168M) 167772160 32768 x 5120 x 1 x 1 IQ3_S
117 blk.12.ffn_gate.weight Block 12 Feed-Forward Network "Gate" (W) (~168M) 167772160 5120 x 32768 x 1 x 1 IQ3_XXS
118 blk.12.ffn_norm.weight Block 12 Feed-Forward Network Normalization (W) ( ~5K) 5120 5120 x 1 x 1 x 1 F32
119 blk.12.ffn_up.weight Block 12 Feed-Forward Network "Up" (W) (~168M) 167772160 5120 x 32768 x 1 x 1 IQ3_XXS
  • Total elements in blk.12: (~556M) 555755520
  • Percentage of total elements: 2.47%

Block 13 Tensor Group : ~556M Elements

T_ID Tensor Layer Name Human Friendly Tensor Layer Name Elements Shape Type
120 blk.13.attn_k.weight Block 13 Attention Key (W) ( ~5M) 5242880 5120 x 1024 x 1 x 1 IQ3_XXS
121 blk.13.attn_norm.weight Block 13 Attention Normalization (W) ( ~5K) 5120 5120 x 1 x 1 x 1 F32
122 blk.13.attn_output.weight Block 13 Attention Output (W) ( ~21M) 20971520 4096 x 5120 x 1 x 1 IQ3_S
123 blk.13.attn_q.weight Block 13 Attention Query (W) ( ~21M) 20971520 5120 x 4096 x 1 x 1 IQ3_XXS
124 blk.13.attn_v.weight Block 13 Attention Value (W) ( ~5M) 5242880 5120 x 1024 x 1 x 1 IQ3_S
125 blk.13.ffn_down.weight Block 13 Feed-Forward Network "Down" (W) (~168M) 167772160 32768 x 5120 x 1 x 1 IQ3_S
126 blk.13.ffn_gate.weight Block 13 Feed-Forward Network "Gate" (W) (~168M) 167772160 5120 x 32768 x 1 x 1 IQ3_XXS
127 blk.13.ffn_norm.weight Block 13 Feed-Forward Network Normalization (W) ( ~5K) 5120 5120 x 1 x 1 x 1 F32
128 blk.13.ffn_up.weight Block 13 Feed-Forward Network "Up" (W) (~168M) 167772160 5120 x 32768 x 1 x 1 IQ3_XXS
  • Total elements in blk.13: (~556M) 555755520
  • Percentage of total elements: 2.47%

Block 14 Tensor Group : ~556M Elements

T_ID Tensor Layer Name Human Friendly Tensor Layer Name Elements Shape Type
129 blk.14.attn_k.weight Block 14 Attention Key (W) ( ~5M) 5242880 5120 x 1024 x 1 x 1 IQ3_XXS
130 blk.14.attn_norm.weight Block 14 Attention Normalization (W) ( ~5K) 5120 5120 x 1 x 1 x 1 F32
131 blk.14.attn_output.weight Block 14 Attention Output (W) ( ~21M) 20971520 4096 x 5120 x 1 x 1 IQ3_S
132 blk.14.attn_q.weight Block 14 Attention Query (W) ( ~21M) 20971520 5120 x 4096 x 1 x 1 IQ3_XXS
133 blk.14.attn_v.weight Block 14 Attention Value (W) ( ~5M) 5242880 5120 x 1024 x 1 x 1 IQ3_S
134 blk.14.ffn_down.weight Block 14 Feed-Forward Network "Down" (W) (~168M) 167772160 32768 x 5120 x 1 x 1 IQ3_S
135 blk.14.ffn_gate.weight Block 14 Feed-Forward Network "Gate" (W) (~168M) 167772160 5120 x 32768 x 1 x 1 IQ3_XXS
136 blk.14.ffn_norm.weight Block 14 Feed-Forward Network Normalization (W) ( ~5K) 5120 5120 x 1 x 1 x 1 F32
137 blk.14.ffn_up.weight Block 14 Feed-Forward Network "Up" (W) (~168M) 167772160 5120 x 32768 x 1 x 1 IQ3_XXS
  • Total elements in blk.14: (~556M) 555755520
  • Percentage of total elements: 2.47%

Block 15 Tensor Group : ~556M Elements

T_ID Tensor Layer Name Human Friendly Tensor Layer Name Elements Shape Type
138 blk.15.attn_k.weight Block 15 Attention Key (W) ( ~5M) 5242880 5120 x 1024 x 1 x 1 IQ3_XXS
139 blk.15.attn_norm.weight Block 15 Attention Normalization (W) ( ~5K) 5120 5120 x 1 x 1 x 1 F32
140 blk.15.attn_output.weight Block 15 Attention Output (W) ( ~21M) 20971520 4096 x 5120 x 1 x 1 IQ3_S
141 blk.15.attn_q.weight Block 15 Attention Query (W) ( ~21M) 20971520 5120 x 4096 x 1 x 1 IQ3_XXS
142 blk.15.attn_v.weight Block 15 Attention Value (W) ( ~5M) 5242880 5120 x 1024 x 1 x 1 IQ3_S
143 blk.15.ffn_down.weight Block 15 Feed-Forward Network "Down" (W) (~168M) 167772160 32768 x 5120 x 1 x 1 IQ3_S
144 blk.15.ffn_gate.weight Block 15 Feed-Forward Network "Gate" (W) (~168M) 167772160 5120 x 32768 x 1 x 1 IQ3_XXS
145 blk.15.ffn_norm.weight Block 15 Feed-Forward Network Normalization (W) ( ~5K) 5120 5120 x 1 x 1 x 1 F32
146 blk.15.ffn_up.weight Block 15 Feed-Forward Network "Up" (W) (~168M) 167772160 5120 x 32768 x 1 x 1 IQ3_XXS
  • Total elements in blk.15: (~556M) 555755520
  • Percentage of total elements: 2.47%

Block 16 Tensor Group : ~556M Elements

T_ID Tensor Layer Name Human Friendly Tensor Layer Name Elements Shape Type
147 blk.16.attn_k.weight Block 16 Attention Key (W) ( ~5M) 5242880 5120 x 1024 x 1 x 1 IQ3_XXS
148 blk.16.attn_norm.weight Block 16 Attention Normalization (W) ( ~5K) 5120 5120 x 1 x 1 x 1 F32
149 blk.16.attn_output.weight Block 16 Attention Output (W) ( ~21M) 20971520 4096 x 5120 x 1 x 1 IQ3_S
150 blk.16.attn_q.weight Block 16 Attention Query (W) ( ~21M) 20971520 5120 x 4096 x 1 x 1 IQ3_XXS
151 blk.16.attn_v.weight Block 16 Attention Value (W) ( ~5M) 5242880 5120 x 1024 x 1 x 1 IQ3_S
152 blk.16.ffn_down.weight Block 16 Feed-Forward Network "Down" (W) (~168M) 167772160 32768 x 5120 x 1 x 1 IQ3_S
153 blk.16.ffn_gate.weight Block 16 Feed-Forward Network "Gate" (W) (~168M) 167772160 5120 x 32768 x 1 x 1 IQ3_XXS
154 blk.16.ffn_norm.weight Block 16 Feed-Forward Network Normalization (W) ( ~5K) 5120 5120 x 1 x 1 x 1 F32
155 blk.16.ffn_up.weight Block 16 Feed-Forward Network "Up" (W) (~168M) 167772160 5120 x 32768 x 1 x 1 IQ3_XXS
  • Total elements in blk.16: (~556M) 555755520
  • Percentage of total elements: 2.47%

Block 17 Tensor Group : ~556M Elements

T_ID Tensor Layer Name Human Friendly Tensor Layer Name Elements Shape Type
156 blk.17.attn_k.weight Block 17 Attention Key (W) ( ~5M) 5242880 5120 x 1024 x 1 x 1 IQ3_S
157 blk.17.attn_norm.weight Block 17 Attention Normalization (W) ( ~5K) 5120 5120 x 1 x 1 x 1 F32
158 blk.17.attn_output.weight Block 17 Attention Output (W) ( ~21M) 20971520 4096 x 5120 x 1 x 1 IQ3_S
159 blk.17.attn_q.weight Block 17 Attention Query (W) ( ~21M) 20971520 5120 x 4096 x 1 x 1 IQ3_S
160 blk.17.attn_v.weight Block 17 Attention Value (W) ( ~5M) 5242880 5120 x 1024 x 1 x 1 IQ3_S
161 blk.17.ffn_down.weight Block 17 Feed-Forward Network "Down" (W) (~168M) 167772160 32768 x 5120 x 1 x 1 IQ3_S
162 blk.17.ffn_gate.weight Block 17 Feed-Forward Network "Gate" (W) (~168M) 167772160 5120 x 32768 x 1 x 1 IQ3_XXS
163 blk.17.ffn_norm.weight Block 17 Feed-Forward Network Normalization (W) ( ~5K) 5120 5120 x 1 x 1 x 1 F32
164 blk.17.ffn_up.weight Block 17 Feed-Forward Network "Up" (W) (~168M) 167772160 5120 x 32768 x 1 x 1 IQ3_XXS
  • Total elements in blk.17: (~556M) 555755520
  • Percentage of total elements: 2.47%

Block 18 Tensor Group : ~556M Elements

T_ID Tensor Layer Name Human Friendly Tensor Layer Name Elements Shape Type
165 blk.18.attn_k.weight Block 18 Attention Key (W) ( ~5M) 5242880 5120 x 1024 x 1 x 1 IQ3_S
166 blk.18.attn_norm.weight Block 18 Attention Normalization (W) ( ~5K) 5120 5120 x 1 x 1 x 1 F32
167 blk.18.attn_output.weight Block 18 Attention Output (W) ( ~21M) 20971520 4096 x 5120 x 1 x 1 IQ3_S
168 blk.18.attn_q.weight Block 18 Attention Query (W) ( ~21M) 20971520 5120 x 4096 x 1 x 1 IQ3_S
169 blk.18.attn_v.weight Block 18 Attention Value (W) ( ~5M) 5242880 5120 x 1024 x 1 x 1 IQ3_S
170 blk.18.ffn_down.weight Block 18 Feed-Forward Network "Down" (W) (~168M) 167772160 32768 x 5120 x 1 x 1 IQ3_S
171 blk.18.ffn_gate.weight Block 18 Feed-Forward Network "Gate" (W) (~168M) 167772160 5120 x 32768 x 1 x 1 IQ3_XXS
172 blk.18.ffn_norm.weight Block 18 Feed-Forward Network Normalization (W) ( ~5K) 5120 5120 x 1 x 1 x 1 F32
173 blk.18.ffn_up.weight Block 18 Feed-Forward Network "Up" (W) (~168M) 167772160 5120 x 32768 x 1 x 1 IQ3_XXS
  • Total elements in blk.18: (~556M) 555755520
  • Percentage of total elements: 2.47%

Block 19 Tensor Group : ~556M Elements

T_ID Tensor Layer Name Human Friendly Tensor Layer Name Elements Shape Type
174 blk.19.attn_k.weight Block 19 Attention Key (W) ( ~5M) 5242880 5120 x 1024 x 1 x 1 IQ3_XXS
175 blk.19.attn_norm.weight Block 19 Attention Normalization (W) ( ~5K) 5120 5120 x 1 x 1 x 1 F32
176 blk.19.attn_output.weight Block 19 Attention Output (W) ( ~21M) 20971520 4096 x 5120 x 1 x 1 IQ3_S
177 blk.19.attn_q.weight Block 19 Attention Query (W) ( ~21M) 20971520 5120 x 4096 x 1 x 1 IQ3_XXS
178 blk.19.attn_v.weight Block 19 Attention Value (W) ( ~5M) 5242880 5120 x 1024 x 1 x 1 IQ3_S
179 blk.19.ffn_down.weight Block 19 Feed-Forward Network "Down" (W) (~168M) 167772160 32768 x 5120 x 1 x 1 IQ3_S
180 blk.19.ffn_gate.weight Block 19 Feed-Forward Network "Gate" (W) (~168M) 167772160 5120 x 32768 x 1 x 1 IQ3_XXS
181 blk.19.ffn_norm.weight Block 19 Feed-Forward Network Normalization (W) ( ~5K) 5120 5120 x 1 x 1 x 1 F32
182 blk.19.ffn_up.weight Block 19 Feed-Forward Network "Up" (W) (~168M) 167772160 5120 x 32768 x 1 x 1 IQ3_XXS
  • Total elements in blk.19: (~556M) 555755520
  • Percentage of total elements: 2.47%

Block 20 Tensor Group : ~556M Elements

T_ID Tensor Layer Name Human Friendly Tensor Layer Name Elements Shape Type
183 blk.20.attn_k.weight Block 20 Attention Key (W) ( ~5M) 5242880 5120 x 1024 x 1 x 1 IQ3_S
184 blk.20.attn_norm.weight Block 20 Attention Normalization (W) ( ~5K) 5120 5120 x 1 x 1 x 1 F32
185 blk.20.attn_output.weight Block 20 Attention Output (W) ( ~21M) 20971520 4096 x 5120 x 1 x 1 IQ3_S
186 blk.20.attn_q.weight Block 20 Attention Query (W) ( ~21M) 20971520 5120 x 4096 x 1 x 1 IQ3_S
187 blk.20.attn_v.weight Block 20 Attention Value (W) ( ~5M) 5242880 5120 x 1024 x 1 x 1 IQ3_S
188 blk.20.ffn_down.weight Block 20 Feed-Forward Network "Down" (W) (~168M) 167772160 32768 x 5120 x 1 x 1 IQ3_S
189 blk.20.ffn_gate.weight Block 20 Feed-Forward Network "Gate" (W) (~168M) 167772160 5120 x 32768 x 1 x 1 IQ3_S
190 blk.20.ffn_norm.weight Block 20 Feed-Forward Network Normalization (W) ( ~5K) 5120 5120 x 1 x 1 x 1 F32
191 blk.20.ffn_up.weight Block 20 Feed-Forward Network "Up" (W) (~168M) 167772160 5120 x 32768 x 1 x 1 IQ3_S
  • Total elements in blk.20: (~556M) 555755520
  • Percentage of total elements: 2.47%

Block 21 Tensor Group : ~556M Elements

T_ID Tensor Layer Name Human Friendly Tensor Layer Name Elements Shape Type
192 blk.21.attn_k.weight Block 21 Attention Key (W) ( ~5M) 5242880 5120 x 1024 x 1 x 1 IQ3_XXS
193 blk.21.attn_norm.weight Block 21 Attention Normalization (W) ( ~5K) 5120 5120 x 1 x 1 x 1 F32
194 blk.21.attn_output.weight Block 21 Attention Output (W) ( ~21M) 20971520 4096 x 5120 x 1 x 1 IQ3_S
195 blk.21.attn_q.weight Block 21 Attention Query (W) ( ~21M) 20971520 5120 x 4096 x 1 x 1 IQ3_XXS
196 blk.21.attn_v.weight Block 21 Attention Value (W) ( ~5M) 5242880 5120 x 1024 x 1 x 1 IQ3_S
197 blk.21.ffn_down.weight Block 21 Feed-Forward Network "Down" (W) (~168M) 167772160 32768 x 5120 x 1 x 1 IQ3_S
198 blk.21.ffn_gate.weight Block 21 Feed-Forward Network "Gate" (W) (~168M) 167772160 5120 x 32768 x 1 x 1 IQ3_S
199 blk.21.ffn_norm.weight Block 21 Feed-Forward Network Normalization (W) ( ~5K) 5120 5120 x 1 x 1 x 1 F32
200 blk.21.ffn_up.weight Block 21 Feed-Forward Network "Up" (W) (~168M) 167772160 5120 x 32768 x 1 x 1 IQ3_S
  • Total elements in blk.21: (~556M) 555755520
  • Percentage of total elements: 2.47%

Block 22 Tensor Group : ~556M Elements

T_ID Tensor Layer Name Human Friendly Tensor Layer Name Elements Shape Type
201 blk.22.attn_k.weight Block 22 Attention Key (W) ( ~5M) 5242880 5120 x 1024 x 1 x 1 IQ3_S
202 blk.22.attn_norm.weight Block 22 Attention Normalization (W) ( ~5K) 5120 5120 x 1 x 1 x 1 F32
203 blk.22.attn_output.weight Block 22 Attention Output (W) ( ~21M) 20971520 4096 x 5120 x 1 x 1 IQ3_S
204 blk.22.attn_q.weight Block 22 Attention Query (W) ( ~21M) 20971520 5120 x 4096 x 1 x 1 IQ3_S
205 blk.22.attn_v.weight Block 22 Attention Value (W) ( ~5M) 5242880 5120 x 1024 x 1 x 1 IQ3_S
206 blk.22.ffn_down.weight Block 22 Feed-Forward Network "Down" (W) (~168M) 167772160 32768 x 5120 x 1 x 1 IQ3_S
207 blk.22.ffn_gate.weight Block 22 Feed-Forward Network "Gate" (W) (~168M) 167772160 5120 x 32768 x 1 x 1 IQ3_S
208 blk.22.ffn_norm.weight Block 22 Feed-Forward Network Normalization (W) ( ~5K) 5120 5120 x 1 x 1 x 1 F32
209 blk.22.ffn_up.weight Block 22 Feed-Forward Network "Up" (W) (~168M) 167772160 5120 x 32768 x 1 x 1 IQ3_S
  • Total elements in blk.22: (~556M) 555755520
  • Percentage of total elements: 2.47%

Block 23 Tensor Group : ~556M Elements

T_ID Tensor Layer Name Human Friendly Tensor Layer Name Elements Shape Type
210 blk.23.attn_k.weight Block 23 Attention Key (W) ( ~5M) 5242880 5120 x 1024 x 1 x 1 IQ3_S
211 blk.23.attn_norm.weight Block 23 Attention Normalization (W) ( ~5K) 5120 5120 x 1 x 1 x 1 F32
212 blk.23.attn_output.weight Block 23 Attention Output (W) ( ~21M) 20971520 4096 x 5120 x 1 x 1 IQ3_S
213 blk.23.attn_q.weight Block 23 Attention Query (W) ( ~21M) 20971520 5120 x 4096 x 1 x 1 IQ3_S
214 blk.23.attn_v.weight Block 23 Attention Value (W) ( ~5M) 5242880 5120 x 1024 x 1 x 1 IQ3_S
215 blk.23.ffn_down.weight Block 23 Feed-Forward Network "Down" (W) (~168M) 167772160 32768 x 5120 x 1 x 1 IQ3_S
216 blk.23.ffn_gate.weight Block 23 Feed-Forward Network "Gate" (W) (~168M) 167772160 5120 x 32768 x 1 x 1 IQ3_S
217 blk.23.ffn_norm.weight Block 23 Feed-Forward Network Normalization (W) ( ~5K) 5120 5120 x 1 x 1 x 1 F32
218 blk.23.ffn_up.weight Block 23 Feed-Forward Network "Up" (W) (~168M) 167772160 5120 x 32768 x 1 x 1 IQ3_S
  • Total elements in blk.23: (~556M) 555755520
  • Percentage of total elements: 2.47%

Block 24 Tensor Group : ~556M Elements

T_ID Tensor Layer Name Human Friendly Tensor Layer Name Elements Shape Type
219 blk.24.attn_k.weight Block 24 Attention Key (W) ( ~5M) 5242880 5120 x 1024 x 1 x 1 IQ3_S
220 blk.24.attn_norm.weight Block 24 Attention Normalization (W) ( ~5K) 5120 5120 x 1 x 1 x 1 F32
221 blk.24.attn_output.weight Block 24 Attention Output (W) ( ~21M) 20971520 4096 x 5120 x 1 x 1 IQ3_S
222 blk.24.attn_q.weight Block 24 Attention Query (W) ( ~21M) 20971520 5120 x 4096 x 1 x 1 IQ3_S
223 blk.24.attn_v.weight Block 24 Attention Value (W) ( ~5M) 5242880 5120 x 1024 x 1 x 1 IQ3_S
224 blk.24.ffn_down.weight Block 24 Feed-Forward Network "Down" (W) (~168M) 167772160 32768 x 5120 x 1 x 1 IQ3_S
225 blk.24.ffn_gate.weight Block 24 Feed-Forward Network "Gate" (W) (~168M) 167772160 5120 x 32768 x 1 x 1 IQ3_S
226 blk.24.ffn_norm.weight Block 24 Feed-Forward Network Normalization (W) ( ~5K) 5120 5120 x 1 x 1 x 1 F32
227 blk.24.ffn_up.weight Block 24 Feed-Forward Network "Up" (W) (~168M) 167772160 5120 x 32768 x 1 x 1 IQ3_S
  • Total elements in blk.24: (~556M) 555755520
  • Percentage of total elements: 2.47%

Block 25 Tensor Group : ~556M Elements

T_ID Tensor Layer Name Human Friendly Tensor Layer Name Elements Shape Type
228 blk.25.attn_k.weight Block 25 Attention Key (W) ( ~5M) 5242880 5120 x 1024 x 1 x 1 IQ3_S
229 blk.25.attn_norm.weight Block 25 Attention Normalization (W) ( ~5K) 5120 5120 x 1 x 1 x 1 F32
230 blk.25.attn_output.weight Block 25 Attention Output (W) ( ~21M) 20971520 4096 x 5120 x 1 x 1 IQ3_S
231 blk.25.attn_q.weight Block 25 Attention Query (W) ( ~21M) 20971520 5120 x 4096 x 1 x 1 IQ3_S
232 blk.25.attn_v.weight Block 25 Attention Value (W) ( ~5M) 5242880 5120 x 1024 x 1 x 1 IQ3_S
233 blk.25.ffn_down.weight Block 25 Feed-Forward Network "Down" (W) (~168M) 167772160 32768 x 5120 x 1 x 1 IQ3_S
234 blk.25.ffn_gate.weight Block 25 Feed-Forward Network "Gate" (W) (~168M) 167772160 5120 x 32768 x 1 x 1 IQ3_S
235 blk.25.ffn_norm.weight Block 25 Feed-Forward Network Normalization (W) ( ~5K) 5120 5120 x 1 x 1 x 1 F32
236 blk.25.ffn_up.weight Block 25 Feed-Forward Network "Up" (W) (~168M) 167772160 5120 x 32768 x 1 x 1 IQ3_S
  • Total elements in blk.25: (~556M) 555755520
  • Percentage of total elements: 2.47%

Block 26 Tensor Group : ~556M Elements

T_ID Tensor Layer Name Human Friendly Tensor Layer Name Elements Shape Type
237 blk.26.attn_k.weight Block 26 Attention Key (W) ( ~5M) 5242880 5120 x 1024 x 1 x 1 IQ3_S
238 blk.26.attn_norm.weight Block 26 Attention Normalization (W) ( ~5K) 5120 5120 x 1 x 1 x 1 F32
239 blk.26.attn_output.weight Block 26 Attention Output (W) ( ~21M) 20971520 4096 x 5120 x 1 x 1 IQ3_S
240 blk.26.attn_q.weight Block 26 Attention Query (W) ( ~21M) 20971520 5120 x 4096 x 1 x 1 IQ3_S
241 blk.26.attn_v.weight Block 26 Attention Value (W) ( ~5M) 5242880 5120 x 1024 x 1 x 1 IQ3_S
242 blk.26.ffn_down.weight Block 26 Feed-Forward Network "Down" (W) (~168M) 167772160 32768 x 5120 x 1 x 1 IQ3_S
243 blk.26.ffn_gate.weight Block 26 Feed-Forward Network "Gate" (W) (~168M) 167772160 5120 x 32768 x 1 x 1 IQ3_S
244 blk.26.ffn_norm.weight Block 26 Feed-Forward Network Normalization (W) ( ~5K) 5120 5120 x 1 x 1 x 1 F32
245 blk.26.ffn_up.weight Block 26 Feed-Forward Network "Up" (W) (~168M) 167772160 5120 x 32768 x 1 x 1 IQ3_S
  • Total elements in blk.26: (~556M) 555755520
  • Percentage of total elements: 2.47%

Block 27 Tensor Group : ~556M Elements

T_ID Tensor Layer Name Human Friendly Tensor Layer Name Elements Shape Type
246 blk.27.attn_k.weight Block 27 Attention Key (W) ( ~5M) 5242880 5120 x 1024 x 1 x 1 IQ3_XXS
247 blk.27.attn_norm.weight Block 27 Attention Normalization (W) ( ~5K) 5120 5120 x 1 x 1 x 1 F32
248 blk.27.attn_output.weight Block 27 Attention Output (W) ( ~21M) 20971520 4096 x 5120 x 1 x 1 IQ3_S
249 blk.27.attn_q.weight Block 27 Attention Query (W) ( ~21M) 20971520 5120 x 4096 x 1 x 1 IQ3_XXS
250 blk.27.attn_v.weight Block 27 Attention Value (W) ( ~5M) 5242880 5120 x 1024 x 1 x 1 IQ3_S
251 blk.27.ffn_down.weight Block 27 Feed-Forward Network "Down" (W) (~168M) 167772160 32768 x 5120 x 1 x 1 IQ3_S
252 blk.27.ffn_gate.weight Block 27 Feed-Forward Network "Gate" (W) (~168M) 167772160 5120 x 32768 x 1 x 1 IQ3_S
253 blk.27.ffn_norm.weight Block 27 Feed-Forward Network Normalization (W) ( ~5K) 5120 5120 x 1 x 1 x 1 F32
254 blk.27.ffn_up.weight Block 27 Feed-Forward Network "Up" (W) (~168M) 167772160 5120 x 32768 x 1 x 1 IQ3_S
  • Total elements in blk.27: (~556M) 555755520
  • Percentage of total elements: 2.47%

Block 28 Tensor Group : ~556M Elements

T_ID Tensor Layer Name Human Friendly Tensor Layer Name Elements Shape Type
255 blk.28.attn_k.weight Block 28 Attention Key (W) ( ~5M) 5242880 5120 x 1024 x 1 x 1 IQ3_S
256 blk.28.attn_norm.weight Block 28 Attention Normalization (W) ( ~5K) 5120 5120 x 1 x 1 x 1 F32
257 blk.28.attn_output.weight Block 28 Attention Output (W) ( ~21M) 20971520 4096 x 5120 x 1 x 1 IQ3_S
258 blk.28.attn_q.weight Block 28 Attention Query (W) ( ~21M) 20971520 5120 x 4096 x 1 x 1 IQ3_S
259 blk.28.attn_v.weight Block 28 Attention Value (W) ( ~5M) 5242880 5120 x 1024 x 1 x 1 IQ3_S
260 blk.28.ffn_down.weight Block 28 Feed-Forward Network "Down" (W) (~168M) 167772160 32768 x 5120 x 1 x 1 IQ3_S
261 blk.28.ffn_gate.weight Block 28 Feed-Forward Network "Gate" (W) (~168M) 167772160 5120 x 32768 x 1 x 1 IQ3_S
262 blk.28.ffn_norm.weight Block 28 Feed-Forward Network Normalization (W) ( ~5K) 5120 5120 x 1 x 1 x 1 F32
263 blk.28.ffn_up.weight Block 28 Feed-Forward Network "Up" (W) (~168M) 167772160 5120 x 32768 x 1 x 1 IQ3_S
  • Total elements in blk.28: (~556M) 555755520
  • Percentage of total elements: 2.47%

Block 29 Tensor Group : ~556M Elements

T_ID Tensor Layer Name Human Friendly Tensor Layer Name Elements Shape Type
264 blk.29.attn_k.weight Block 29 Attention Key (W) ( ~5M) 5242880 5120 x 1024 x 1 x 1 IQ3_S
265 blk.29.attn_norm.weight Block 29 Attention Normalization (W) ( ~5K) 5120 5120 x 1 x 1 x 1 F32
266 blk.29.attn_output.weight Block 29 Attention Output (W) ( ~21M) 20971520 4096 x 5120 x 1 x 1 IQ3_S
267 blk.29.attn_q.weight Block 29 Attention Query (W) ( ~21M) 20971520 5120 x 4096 x 1 x 1 IQ3_S
268 blk.29.attn_v.weight Block 29 Attention Value (W) ( ~5M) 5242880 5120 x 1024 x 1 x 1 IQ3_S
269 blk.29.ffn_down.weight Block 29 Feed-Forward Network "Down" (W) (~168M) 167772160 32768 x 5120 x 1 x 1 IQ3_S
270 blk.29.ffn_gate.weight Block 29 Feed-Forward Network "Gate" (W) (~168M) 167772160 5120 x 32768 x 1 x 1 IQ3_S
271 blk.29.ffn_norm.weight Block 29 Feed-Forward Network Normalization (W) ( ~5K) 5120 5120 x 1 x 1 x 1 F32
272 blk.29.ffn_up.weight Block 29 Feed-Forward Network "Up" (W) (~168M) 167772160 5120 x 32768 x 1 x 1 IQ3_S
  • Total elements in blk.29: (~556M) 555755520
  • Percentage of total elements: 2.47%

Block 30 Tensor Group : ~556M Elements

T_ID Tensor Layer Name Human Friendly Tensor Layer Name Elements Shape Type
273 blk.30.attn_k.weight Block 30 Attention Key (W) ( ~5M) 5242880 5120 x 1024 x 1 x 1 IQ3_S
274 blk.30.attn_norm.weight Block 30 Attention Normalization (W) ( ~5K) 5120 5120 x 1 x 1 x 1 F32
275 blk.30.attn_output.weight Block 30 Attention Output (W) ( ~21M) 20971520 4096 x 5120 x 1 x 1 IQ3_S
276 blk.30.attn_q.weight Block 30 Attention Query (W) ( ~21M) 20971520 5120 x 4096 x 1 x 1 IQ3_S
277 blk.30.attn_v.weight Block 30 Attention Value (W) ( ~5M) 5242880 5120 x 1024 x 1 x 1 IQ3_S
278 blk.30.ffn_down.weight Block 30 Feed-Forward Network "Down" (W) (~168M) 167772160 32768 x 5120 x 1 x 1 IQ3_S
279 blk.30.ffn_gate.weight Block 30 Feed-Forward Network "Gate" (W) (~168M) 167772160 5120 x 32768 x 1 x 1 IQ3_S
280 blk.30.ffn_norm.weight Block 30 Feed-Forward Network Normalization (W) ( ~5K) 5120 5120 x 1 x 1 x 1 F32
281 blk.30.ffn_up.weight Block 30 Feed-Forward Network "Up" (W) (~168M) 167772160 5120 x 32768 x 1 x 1 IQ3_S
  • Total elements in blk.30: (~556M) 555755520
  • Percentage of total elements: 2.47%

Block 31 Tensor Group : ~556M Elements

T_ID Tensor Layer Name Human Friendly Tensor Layer Name Elements Shape Type
282 blk.31.attn_k.weight Block 31 Attention Key (W) ( ~5M) 5242880 5120 x 1024 x 1 x 1 IQ3_S
283 blk.31.attn_norm.weight Block 31 Attention Normalization (W) ( ~5K) 5120 5120 x 1 x 1 x 1 F32
284 blk.31.attn_output.weight Block 31 Attention Output (W) ( ~21M) 20971520 4096 x 5120 x 1 x 1 IQ3_S
285 blk.31.attn_q.weight Block 31 Attention Query (W) ( ~21M) 20971520 5120 x 4096 x 1 x 1 IQ3_S
286 blk.31.attn_v.weight Block 31 Attention Value (W) ( ~5M) 5242880 5120 x 1024 x 1 x 1 IQ3_S
287 blk.31.ffn_down.weight Block 31 Feed-Forward Network "Down" (W) (~168M) 167772160 32768 x 5120 x 1 x 1 IQ3_S
288 blk.31.ffn_gate.weight Block 31 Feed-Forward Network "Gate" (W) (~168M) 167772160 5120 x 32768 x 1 x 1 IQ3_S
289 blk.31.ffn_norm.weight Block 31 Feed-Forward Network Normalization (W) ( ~5K) 5120 5120 x 1 x 1 x 1 F32
290 blk.31.ffn_up.weight Block 31 Feed-Forward Network "Up" (W) (~168M) 167772160 5120 x 32768 x 1 x 1 IQ3_S
  • Total elements in blk.31: (~556M) 555755520
  • Percentage of total elements: 2.47%

Block 32 Tensor Group : ~556M Elements

T_ID Tensor Layer Name Human Friendly Tensor Layer Name Elements Shape Type
291 blk.32.attn_k.weight Block 32 Attention Key (W) ( ~5M) 5242880 5120 x 1024 x 1 x 1 IQ3_S
292 blk.32.attn_norm.weight Block 32 Attention Normalization (W) ( ~5K) 5120 5120 x 1 x 1 x 1 F32
293 blk.32.attn_output.weight Block 32 Attention Output (W) ( ~21M) 20971520 4096 x 5120 x 1 x 1 IQ3_S
294 blk.32.attn_q.weight Block 32 Attention Query (W) ( ~21M) 20971520 5120 x 4096 x 1 x 1 IQ3_S
295 blk.32.attn_v.weight Block 32 Attention Value (W) ( ~5M) 5242880 5120 x 1024 x 1 x 1 IQ3_S
296 blk.32.ffn_down.weight Block 32 Feed-Forward Network "Down" (W) (~168M) 167772160 32768 x 5120 x 1 x 1 IQ3_S
297 blk.32.ffn_gate.weight Block 32 Feed-Forward Network "Gate" (W) (~168M) 167772160 5120 x 32768 x 1 x 1 IQ3_S
298 blk.32.ffn_norm.weight Block 32 Feed-Forward Network Normalization (W) ( ~5K) 5120 5120 x 1 x 1 x 1 F32
299 blk.32.ffn_up.weight Block 32 Feed-Forward Network "Up" (W) (~168M) 167772160 5120 x 32768 x 1 x 1 IQ3_S
  • Total elements in blk.32: (~556M) 555755520
  • Percentage of total elements: 2.47%

Block 33 Tensor Group : ~556M Elements

T_ID Tensor Layer Name Human Friendly Tensor Layer Name Elements Shape Type
300 blk.33.attn_k.weight Block 33 Attention Key (W) ( ~5M) 5242880 5120 x 1024 x 1 x 1 IQ3_S
301 blk.33.attn_norm.weight Block 33 Attention Normalization (W) ( ~5K) 5120 5120 x 1 x 1 x 1 F32
302 blk.33.attn_output.weight Block 33 Attention Output (W) ( ~21M) 20971520 4096 x 5120 x 1 x 1 IQ3_S
303 blk.33.attn_q.weight Block 33 Attention Query (W) ( ~21M) 20971520 5120 x 4096 x 1 x 1 IQ3_S
304 blk.33.attn_v.weight Block 33 Attention Value (W) ( ~5M) 5242880 5120 x 1024 x 1 x 1 IQ3_S
305 blk.33.ffn_down.weight Block 33 Feed-Forward Network "Down" (W) (~168M) 167772160 32768 x 5120 x 1 x 1 IQ3_S
306 blk.33.ffn_gate.weight Block 33 Feed-Forward Network "Gate" (W) (~168M) 167772160 5120 x 32768 x 1 x 1 IQ3_S
307 blk.33.ffn_norm.weight Block 33 Feed-Forward Network Normalization (W) ( ~5K) 5120 5120 x 1 x 1 x 1 F32
308 blk.33.ffn_up.weight Block 33 Feed-Forward Network "Up" (W) (~168M) 167772160 5120 x 32768 x 1 x 1 IQ3_S
  • Total elements in blk.33: (~556M) 555755520
  • Percentage of total elements: 2.47%

Block 34 Tensor Group : ~556M Elements

T_ID Tensor Layer Name Human Friendly Tensor Layer Name Elements Shape Type
309 blk.34.attn_k.weight Block 34 Attention Key (W) ( ~5M) 5242880 5120 x 1024 x 1 x 1 IQ3_S
310 blk.34.attn_norm.weight Block 34 Attention Normalization (W) ( ~5K) 5120 5120 x 1 x 1 x 1 F32
311 blk.34.attn_output.weight Block 34 Attention Output (W) ( ~21M) 20971520 4096 x 5120 x 1 x 1 IQ3_S
312 blk.34.attn_q.weight Block 34 Attention Query (W) ( ~21M) 20971520 5120 x 4096 x 1 x 1 IQ3_S
313 blk.34.attn_v.weight Block 34 Attention Value (W) ( ~5M) 5242880 5120 x 1024 x 1 x 1 IQ3_S
314 blk.34.ffn_down.weight Block 34 Feed-Forward Network "Down" (W) (~168M) 167772160 32768 x 5120 x 1 x 1 IQ3_S
315 blk.34.ffn_gate.weight Block 34 Feed-Forward Network "Gate" (W) (~168M) 167772160 5120 x 32768 x 1 x 1 IQ3_S
316 blk.34.ffn_norm.weight Block 34 Feed-Forward Network Normalization (W) ( ~5K) 5120 5120 x 1 x 1 x 1 F32
317 blk.34.ffn_up.weight Block 34 Feed-Forward Network "Up" (W) (~168M) 167772160 5120 x 32768 x 1 x 1 IQ3_S
  • Total elements in blk.34: (~556M) 555755520
  • Percentage of total elements: 2.47%

Block 35 Tensor Group : ~556M Elements

T_ID Tensor Layer Name Human Friendly Tensor Layer Name Elements Shape Type
318 blk.35.attn_k.weight Block 35 Attention Key (W) ( ~5M) 5242880 5120 x 1024 x 1 x 1 IQ3_S
319 blk.35.attn_norm.weight Block 35 Attention Normalization (W) ( ~5K) 5120 5120 x 1 x 1 x 1 F32
320 blk.35.attn_output.weight Block 35 Attention Output (W) ( ~21M) 20971520 4096 x 5120 x 1 x 1 IQ3_S
321 blk.35.attn_q.weight Block 35 Attention Query (W) ( ~21M) 20971520 5120 x 4096 x 1 x 1 IQ3_S
322 blk.35.attn_v.weight Block 35 Attention Value (W) ( ~5M) 5242880 5120 x 1024 x 1 x 1 IQ3_S
323 blk.35.ffn_down.weight Block 35 Feed-Forward Network "Down" (W) (~168M) 167772160 32768 x 5120 x 1 x 1 IQ3_S
324 blk.35.ffn_gate.weight Block 35 Feed-Forward Network "Gate" (W) (~168M) 167772160 5120 x 32768 x 1 x 1 IQ3_S
325 blk.35.ffn_norm.weight Block 35 Feed-Forward Network Normalization (W) ( ~5K) 5120 5120 x 1 x 1 x 1 F32
326 blk.35.ffn_up.weight Block 35 Feed-Forward Network "Up" (W) (~168M) 167772160 5120 x 32768 x 1 x 1 IQ3_S
  • Total elements in blk.35: (~556M) 555755520
  • Percentage of total elements: 2.47%

Block 36 Tensor Group : ~556M Elements

T_ID Tensor Layer Name Human Friendly Tensor Layer Name Elements Shape Type
327 blk.36.attn_k.weight Block 36 Attention Key (W) ( ~5M) 5242880 5120 x 1024 x 1 x 1 IQ3_S
328 blk.36.attn_norm.weight Block 36 Attention Normalization (W) ( ~5K) 5120 5120 x 1 x 1 x 1 F32
329 blk.36.attn_output.weight Block 36 Attention Output (W) ( ~21M) 20971520 4096 x 5120 x 1 x 1 IQ3_S
330 blk.36.attn_q.weight Block 36 Attention Query (W) ( ~21M) 20971520 5120 x 4096 x 1 x 1 IQ3_S
331 blk.36.attn_v.weight Block 36 Attention Value (W) ( ~5M) 5242880 5120 x 1024 x 1 x 1 IQ3_S
332 blk.36.ffn_down.weight Block 36 Feed-Forward Network "Down" (W) (~168M) 167772160 32768 x 5120 x 1 x 1 IQ3_S
333 blk.36.ffn_gate.weight Block 36 Feed-Forward Network "Gate" (W) (~168M) 167772160 5120 x 32768 x 1 x 1 IQ3_S
334 blk.36.ffn_norm.weight Block 36 Feed-Forward Network Normalization (W) ( ~5K) 5120 5120 x 1 x 1 x 1 F32
335 blk.36.ffn_up.weight Block 36 Feed-Forward Network "Up" (W) (~168M) 167772160 5120 x 32768 x 1 x 1 IQ3_S
  • Total elements in blk.36: (~556M) 555755520
  • Percentage of total elements: 2.47%

Block 37 Tensor Group : ~556M Elements

T_ID Tensor Layer Name Human Friendly Tensor Layer Name Elements Shape Type
336 blk.37.attn_k.weight Block 37 Attention Key (W) ( ~5M) 5242880 5120 x 1024 x 1 x 1 IQ3_S
337 blk.37.attn_norm.weight Block 37 Attention Normalization (W) ( ~5K) 5120 5120 x 1 x 1 x 1 F32
338 blk.37.attn_output.weight Block 37 Attention Output (W) ( ~21M) 20971520 4096 x 5120 x 1 x 1 IQ3_S
339 blk.37.attn_q.weight Block 37 Attention Query (W) ( ~21M) 20971520 5120 x 4096 x 1 x 1 IQ3_S
340 blk.37.attn_v.weight Block 37 Attention Value (W) ( ~5M) 5242880 5120 x 1024 x 1 x 1 IQ3_S
341 blk.37.ffn_down.weight Block 37 Feed-Forward Network "Down" (W) (~168M) 167772160 32768 x 5120 x 1 x 1 IQ3_S
342 blk.37.ffn_gate.weight Block 37 Feed-Forward Network "Gate" (W) (~168M) 167772160 5120 x 32768 x 1 x 1 IQ3_S
343 blk.37.ffn_norm.weight Block 37 Feed-Forward Network Normalization (W) ( ~5K) 5120 5120 x 1 x 1 x 1 F32
344 blk.37.ffn_up.weight Block 37 Feed-Forward Network "Up" (W) (~168M) 167772160 5120 x 32768 x 1 x 1 IQ3_S
  • Total elements in blk.37: (~556M) 555755520
  • Percentage of total elements: 2.47%