Files
granite-4.1-8b-GGUF/scores/granite-4.1-8b-Q1_L.md
ModelHub XC a947aa221e 初始化项目,由ModelHub XC社区提供模型
Model: eaddario/granite-4.1-8b-GGUF
Source: Original Platform
2026-06-14 00:38:20 +08:00

109 KiB

granite-4.1-8b-WIP/granite-4.1-8b-Q1_L.gguf - GGUF Internal File Dump

  • Endian: LITTLE endian

Key Value Metadata Store

There are 42 key-value pairs in this file

POS TYPE Count Key Value
1 UINT32 1 GGUF.version 3
2 UINT64 1 GGUF.tensor_count 363
3 UINT64 1 GGUF.kv_count 39
4 STRING 1 general.architecture granite
5 STRING 1 general.type model
6 STRING 1 general.name Granite 4.1 8b
7 STRING 1 general.basename granite-4.1
8 STRING 1 general.size_label 8B
9 STRING 1 general.license apache-2.0
10 [STRING] 2 general.tags [ language, granite-4.1 ]
11 UINT32 1 granite.block_count 40
12 UINT32 1 granite.context_length 131072
13 UINT32 1 granite.embedding_length 4096
14 UINT32 1 granite.feed_forward_length 12800
15 UINT32 1 granite.attention.head_count 32
16 UINT32 1 granite.attention.head_count_kv 8
17 FLOAT32 1 granite.rope.freq_base 10000000.0
18 FLOAT32 1 granite.attention.layer_norm_rms_epsilon 1e-05
19 UINT32 1 granite.vocab_size 100352
20 UINT32 1 granite.rope.dimension_count 128
21 FLOAT32 1 granite.attention.scale 0.0078125
22 FLOAT32 1 granite.embedding_scale 12.0
23 FLOAT32 1 granite.residual_scale 0.22
24 FLOAT32 1 granite.logit_scale 16.0
25 STRING 1 tokenizer.ggml.model gpt2
26 STRING 1 tokenizer.ggml.pre granite-docling
27 [STRING] 100352 tokenizer.ggml.tokens [ !, ", #, $, %, ... ]
28 [INT32] 100352 tokenizer.ggml.token_type [ 1, 1, 1, 1, 1, 1, 1, ... ]
29 [STRING] 100000 tokenizer.ggml.merges [ Ġ Ġ, ĠĠ ĠĠ, i n, Ġ t, ĠĠĠĠ ĠĠĠĠ, ... ]
30 UINT32 1 tokenizer.ggml.bos_token_id 100257
31 UINT32 1 tokenizer.ggml.eos_token_id 100257
32 UINT32 1 tokenizer.ggml.unknown_token_id 100269
33 UINT32 1 tokenizer.ggml.padding_token_id 100256
34 BOOL 1 tokenizer.ggml.add_bos_token False
35 STRING 1 tokenizer.chat_template {%- set tools_system_message_p...`end_of_role
36 BOOL 1 tokenizer.ggml.add_space_prefix False
37 UINT32 1 general.quantization_version 2
38 UINT32 1 general.file_type 31
39 STRING 1 quantize.imatrix.file imatrix/imatrix-granite-4.1-8b-medium.gguf
40 STRING 1 quantize.imatrix.dataset ../../datasets/imatrix/combined_all_medium.txt
41 UINT32 1 quantize.imatrix.entries_count 280
42 UINT32 1 quantize.imatrix.chunks_count 3601

Tensors Overview ~9B Elements

Total number of elements in all tensors: 8791592960 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 0x367400 0x80a0000
1 output_norm.weight 0x8407400 0x4000
2 token_embd.weight 0x840b400 0x80a0000
3 blk.0.attn_k.weight 0x104ab400 0xc8000
4 blk.0.attn_norm.weight 0x10573400 0x4000
5 blk.0.attn_output.weight 0x10577400 0x380000
6 blk.0.attn_q.weight 0x108f7400 0x320000
7 blk.0.attn_v.weight 0x10c17400 0xc8000
8 blk.0.ffn_down.weight 0x10cdf400 0x9c4000
9 blk.0.ffn_gate.weight 0x116a3400 0x9c4000
10 blk.0.ffn_norm.weight 0x12067400 0x4000
11 blk.0.ffn_up.weight 0x1206b400 0x9c4000
12 blk.1.attn_k.weight 0x12a2f400 0xc8000
13 blk.1.attn_norm.weight 0x12af7400 0x4000
14 blk.1.attn_output.weight 0x12afb400 0x4a0000
15 blk.1.attn_q.weight 0x12f9b400 0x320000
16 blk.1.attn_v.weight 0x132bb400 0xe0000
17 blk.1.ffn_down.weight 0x1339b400 0xce4000
18 blk.1.ffn_gate.weight 0x1407f400 0x9c4000
19 blk.1.ffn_norm.weight 0x14a43400 0x4000
20 blk.1.ffn_up.weight 0x14a47400 0x9c4000
21 blk.2.attn_k.weight 0x1540b400 0xc8000
22 blk.2.attn_norm.weight 0x154d3400 0x4000
23 blk.2.attn_output.weight 0x154d7400 0x520000
24 blk.2.attn_q.weight 0x159f7400 0x320000
25 blk.2.attn_v.weight 0x15d17400 0xc8000
26 blk.2.ffn_down.weight 0x15ddf400 0x9c4000
27 blk.2.ffn_gate.weight 0x167a3400 0x9c4000
28 blk.2.ffn_norm.weight 0x17167400 0x4000
29 blk.2.ffn_up.weight 0x1716b400 0x9c4000
30 blk.3.attn_k.weight 0x17b2f400 0xc8000
31 blk.3.attn_norm.weight 0x17bf7400 0x4000
32 blk.3.attn_output.weight 0x17bfb400 0x520000
33 blk.3.attn_q.weight 0x1811b400 0x320000
34 blk.3.attn_v.weight 0x1843b400 0xc8000
35 blk.3.ffn_down.weight 0x18503400 0x9c4000
36 blk.3.ffn_gate.weight 0x18ec7400 0x9c4000
37 blk.3.ffn_norm.weight 0x1988b400 0x4000
38 blk.3.ffn_up.weight 0x1988f400 0x9c4000
39 blk.4.attn_k.weight 0x1a253400 0xe0000
40 blk.4.attn_norm.weight 0x1a333400 0x4000
41 blk.4.attn_output.weight 0x1a337400 0x520000
42 blk.4.attn_q.weight 0x1a857400 0x380000
43 blk.4.attn_v.weight 0x1abd7400 0xe0000
44 blk.4.ffn_down.weight 0x1acb7400 0x9c4000
45 blk.4.ffn_gate.weight 0x1b67b400 0x9c4000
46 blk.4.ffn_norm.weight 0x1c03f400 0x4000
47 blk.4.ffn_up.weight 0x1c043400 0x9c4000
48 blk.5.attn_k.weight 0x1ca07400 0xc8000
49 blk.5.attn_norm.weight 0x1cacf400 0x4000
50 blk.5.attn_output.weight 0x1cad3400 0x520000
51 blk.5.attn_q.weight 0x1cff3400 0x320000
52 blk.5.attn_v.weight 0x1d313400 0xc8000
53 blk.5.ffn_down.weight 0x1d3db400 0xaf0000
54 blk.5.ffn_gate.weight 0x1decb400 0x9c4000
55 blk.5.ffn_norm.weight 0x1e88f400 0x4000
56 blk.5.ffn_up.weight 0x1e893400 0x9c4000
57 blk.6.attn_k.weight 0x1f257400 0xc8000
58 blk.6.attn_norm.weight 0x1f31f400 0x4000
59 blk.6.attn_output.weight 0x1f323400 0x4a0000
60 blk.6.attn_q.weight 0x1f7c3400 0x320000
61 blk.6.attn_v.weight 0x1fae3400 0xc8000
62 blk.6.ffn_down.weight 0x1fbab400 0x9c4000
63 blk.6.ffn_gate.weight 0x2056f400 0x9c4000
64 blk.6.ffn_norm.weight 0x20f33400 0x4000
65 blk.6.ffn_up.weight 0x20f37400 0x9c4000
66 blk.7.attn_k.weight 0x218fb400 0xe0000
67 blk.7.attn_norm.weight 0x219db400 0x4000
68 blk.7.attn_output.weight 0x219df400 0x4a0000
69 blk.7.attn_q.weight 0x21e7f400 0x380000
70 blk.7.attn_v.weight 0x221ff400 0xc8000
71 blk.7.ffn_down.weight 0x222c7400 0x9c4000
72 blk.7.ffn_gate.weight 0x22c8b400 0x9c4000
73 blk.7.ffn_norm.weight 0x2364f400 0x4000
74 blk.7.ffn_up.weight 0x23653400 0x9c4000
75 blk.8.attn_k.weight 0x24017400 0xc8000
76 blk.8.attn_norm.weight 0x240df400 0x4000
77 blk.8.attn_output.weight 0x240e3400 0x4a0000
78 blk.8.attn_q.weight 0x24583400 0x320000
79 blk.8.attn_v.weight 0x248a3400 0xc8000
80 blk.8.ffn_down.weight 0x2496b400 0x9c4000
81 blk.8.ffn_gate.weight 0x2532f400 0x9c4000
82 blk.8.ffn_norm.weight 0x25cf3400 0x4000
83 blk.8.ffn_up.weight 0x25cf7400 0x9c4000
84 blk.9.attn_k.weight 0x266bb400 0xc8000
85 blk.9.attn_norm.weight 0x26783400 0x4000
86 blk.9.attn_output.weight 0x26787400 0x520000
87 blk.9.attn_q.weight 0x26ca7400 0x320000
88 blk.9.attn_v.weight 0x26fc7400 0xc8000
89 blk.9.ffn_down.weight 0x2708f400 0x9c4000
90 blk.9.ffn_gate.weight 0x27a53400 0x9c4000
91 blk.9.ffn_norm.weight 0x28417400 0x4000
92 blk.9.ffn_up.weight 0x2841b400 0x9c4000
93 blk.10.attn_k.weight 0x28ddf400 0xc8000
94 blk.10.attn_norm.weight 0x28ea7400 0x4000
95 blk.10.attn_output.weight 0x28eab400 0x4a0000
96 blk.10.attn_q.weight 0x2934b400 0x320000
97 blk.10.attn_v.weight 0x2966b400 0xc8000
98 blk.10.ffn_down.weight 0x29733400 0x9c4000
99 blk.10.ffn_gate.weight 0x2a0f7400 0x9c4000
100 blk.10.ffn_norm.weight 0x2aabb400 0x4000
101 blk.10.ffn_up.weight 0x2aabf400 0x9c4000
102 blk.11.attn_k.weight 0x2b483400 0xc8000
103 blk.11.attn_norm.weight 0x2b54b400 0x4000
104 blk.11.attn_output.weight 0x2b54f400 0x4a0000
105 blk.11.attn_q.weight 0x2b9ef400 0x320000
106 blk.11.attn_v.weight 0x2bd0f400 0xc8000
107 blk.11.ffn_down.weight 0x2bdd7400 0x9c4000
108 blk.11.ffn_gate.weight 0x2c79b400 0x9c4000
109 blk.11.ffn_norm.weight 0x2d15f400 0x4000
110 blk.11.ffn_up.weight 0x2d163400 0x9c4000
111 blk.12.attn_k.weight 0x2db27400 0xc8000
112 blk.12.attn_norm.weight 0x2dbef400 0x4000
113 blk.12.attn_output.weight 0x2dbf3400 0x520000
114 blk.12.attn_q.weight 0x2e113400 0x320000
115 blk.12.attn_v.weight 0x2e433400 0xc8000
116 blk.12.ffn_down.weight 0x2e4fb400 0x9c4000
117 blk.12.ffn_gate.weight 0x2eebf400 0x9c4000
118 blk.12.ffn_norm.weight 0x2f883400 0x4000
119 blk.12.ffn_up.weight 0x2f887400 0x9c4000
120 blk.13.attn_k.weight 0x3024b400 0xc8000
121 blk.13.attn_norm.weight 0x30313400 0x4000
122 blk.13.attn_output.weight 0x30317400 0x4a0000
123 blk.13.attn_q.weight 0x307b7400 0x320000
124 blk.13.attn_v.weight 0x30ad7400 0xc8000
125 blk.13.ffn_down.weight 0x30b9f400 0x9c4000
126 blk.13.ffn_gate.weight 0x31563400 0x9c4000
127 blk.13.ffn_norm.weight 0x31f27400 0x4000
128 blk.13.ffn_up.weight 0x31f2b400 0x9c4000
129 blk.14.attn_k.weight 0x328ef400 0xc8000
130 blk.14.attn_norm.weight 0x329b7400 0x4000
131 blk.14.attn_output.weight 0x329bb400 0x4a0000
132 blk.14.attn_q.weight 0x32e5b400 0x320000
133 blk.14.attn_v.weight 0x3317b400 0xc8000
134 blk.14.ffn_down.weight 0x33243400 0x9c4000
135 blk.14.ffn_gate.weight 0x33c07400 0x9c4000
136 blk.14.ffn_norm.weight 0x345cb400 0x4000
137 blk.14.ffn_up.weight 0x345cf400 0x9c4000
138 blk.15.attn_k.weight 0x34f93400 0xe0000
139 blk.15.attn_norm.weight 0x35073400 0x4000
140 blk.15.attn_output.weight 0x35077400 0x4a0000
141 blk.15.attn_q.weight 0x35517400 0x380000
142 blk.15.attn_v.weight 0x35897400 0xc8000
143 blk.15.ffn_down.weight 0x3595f400 0xaf0000
144 blk.15.ffn_gate.weight 0x3644f400 0x9c4000
145 blk.15.ffn_norm.weight 0x36e13400 0x4000
146 blk.15.ffn_up.weight 0x36e17400 0x9c4000
147 blk.16.attn_k.weight 0x377db400 0xe0000
148 blk.16.attn_norm.weight 0x378bb400 0x4000
149 blk.16.attn_output.weight 0x378bf400 0x4a0000
150 blk.16.attn_q.weight 0x37d5f400 0x380000
151 blk.16.attn_v.weight 0x380df400 0xc8000
152 blk.16.ffn_down.weight 0x381a7400 0xaf0000
153 blk.16.ffn_gate.weight 0x38c97400 0x9c4000
154 blk.16.ffn_norm.weight 0x3965b400 0x4000
155 blk.16.ffn_up.weight 0x3965f400 0x9c4000
156 blk.17.attn_k.weight 0x3a023400 0xc8000
157 blk.17.attn_norm.weight 0x3a0eb400 0x4000
158 blk.17.attn_output.weight 0x3a0ef400 0x4a0000
159 blk.17.attn_q.weight 0x3a58f400 0x320000
160 blk.17.attn_v.weight 0x3a8af400 0xc8000
161 blk.17.ffn_down.weight 0x3a977400 0x9c4000
162 blk.17.ffn_gate.weight 0x3b33b400 0x9c4000
163 blk.17.ffn_norm.weight 0x3bcff400 0x4000
164 blk.17.ffn_up.weight 0x3bd03400 0x9c4000
165 blk.18.attn_k.weight 0x3c6c7400 0xc8000
166 blk.18.attn_norm.weight 0x3c78f400 0x4000
167 blk.18.attn_output.weight 0x3c793400 0x4a0000
168 blk.18.attn_q.weight 0x3cc33400 0x320000
169 blk.18.attn_v.weight 0x3cf53400 0xc8000
170 blk.18.ffn_down.weight 0x3d01b400 0xaf0000
171 blk.18.ffn_gate.weight 0x3db0b400 0x9c4000
172 blk.18.ffn_norm.weight 0x3e4cf400 0x4000
173 blk.18.ffn_up.weight 0x3e4d3400 0x9c4000
174 blk.19.attn_k.weight 0x3ee97400 0xc8000
175 blk.19.attn_norm.weight 0x3ef5f400 0x4000
176 blk.19.attn_output.weight 0x3ef63400 0x4a0000
177 blk.19.attn_q.weight 0x3f403400 0x320000
178 blk.19.attn_v.weight 0x3f723400 0xc8000
179 blk.19.ffn_down.weight 0x3f7eb400 0xaf0000
180 blk.19.ffn_gate.weight 0x402db400 0x9c4000
181 blk.19.ffn_norm.weight 0x40c9f400 0x4000
182 blk.19.ffn_up.weight 0x40ca3400 0x9c4000
183 blk.20.attn_k.weight 0x41667400 0xc8000
184 blk.20.attn_norm.weight 0x4172f400 0x4000
185 blk.20.attn_output.weight 0x41733400 0x520000
186 blk.20.attn_q.weight 0x41c53400 0x320000
187 blk.20.attn_v.weight 0x41f73400 0xc8000
188 blk.20.ffn_down.weight 0x4203b400 0x9c4000
189 blk.20.ffn_gate.weight 0x429ff400 0x9c4000
190 blk.20.ffn_norm.weight 0x433c3400 0x4000
191 blk.20.ffn_up.weight 0x433c7400 0x9c4000
192 blk.21.attn_k.weight 0x43d8b400 0xc8000
193 blk.21.attn_norm.weight 0x43e53400 0x4000
194 blk.21.attn_output.weight 0x43e57400 0x520000
195 blk.21.attn_q.weight 0x44377400 0x320000
196 blk.21.attn_v.weight 0x44697400 0xc8000
197 blk.21.ffn_down.weight 0x4475f400 0xaf0000
198 blk.21.ffn_gate.weight 0x4524f400 0x9c4000
199 blk.21.ffn_norm.weight 0x45c13400 0x4000
200 blk.21.ffn_up.weight 0x45c17400 0x9c4000
201 blk.22.attn_k.weight 0x465db400 0xc8000
202 blk.22.attn_norm.weight 0x466a3400 0x4000
203 blk.22.attn_output.weight 0x466a7400 0x520000
204 blk.22.attn_q.weight 0x46bc7400 0x320000
205 blk.22.attn_v.weight 0x46ee7400 0xc8000
206 blk.22.ffn_down.weight 0x46faf400 0xaf0000
207 blk.22.ffn_gate.weight 0x47a9f400 0x9c4000
208 blk.22.ffn_norm.weight 0x48463400 0x4000
209 blk.22.ffn_up.weight 0x48467400 0x9c4000
210 blk.23.attn_k.weight 0x48e2b400 0xc8000
211 blk.23.attn_norm.weight 0x48ef3400 0x4000
212 blk.23.attn_output.weight 0x48ef7400 0x4a0000
213 blk.23.attn_q.weight 0x49397400 0x320000
214 blk.23.attn_v.weight 0x496b7400 0xc8000
215 blk.23.ffn_down.weight 0x4977f400 0x9c4000
216 blk.23.ffn_gate.weight 0x4a143400 0x9c4000
217 blk.23.ffn_norm.weight 0x4ab07400 0x4000
218 blk.23.ffn_up.weight 0x4ab0b400 0x9c4000
219 blk.24.attn_k.weight 0x4b4cf400 0xc8000
220 blk.24.attn_norm.weight 0x4b597400 0x4000
221 blk.24.attn_output.weight 0x4b59b400 0x520000
222 blk.24.attn_q.weight 0x4babb400 0x320000
223 blk.24.attn_v.weight 0x4bddb400 0xc8000
224 blk.24.ffn_down.weight 0x4bea3400 0xaf0000
225 blk.24.ffn_gate.weight 0x4c993400 0x9c4000
226 blk.24.ffn_norm.weight 0x4d357400 0x4000
227 blk.24.ffn_up.weight 0x4d35b400 0x9c4000
228 blk.25.attn_k.weight 0x4dd1f400 0xc8000
229 blk.25.attn_norm.weight 0x4dde7400 0x4000
230 blk.25.attn_output.weight 0x4ddeb400 0x4a0000
231 blk.25.attn_q.weight 0x4e28b400 0x320000
232 blk.25.attn_v.weight 0x4e5ab400 0xc8000
233 blk.25.ffn_down.weight 0x4e673400 0xaf0000
234 blk.25.ffn_gate.weight 0x4f163400 0x9c4000
235 blk.25.ffn_norm.weight 0x4fb27400 0x4000
236 blk.25.ffn_up.weight 0x4fb2b400 0x9c4000
237 blk.26.attn_k.weight 0x504ef400 0xc8000
238 blk.26.attn_norm.weight 0x505b7400 0x4000
239 blk.26.attn_output.weight 0x505bb400 0x520000
240 blk.26.attn_q.weight 0x50adb400 0x320000
241 blk.26.attn_v.weight 0x50dfb400 0xc8000
242 blk.26.ffn_down.weight 0x50ec3400 0xaf0000
243 blk.26.ffn_gate.weight 0x519b3400 0x9c4000
244 blk.26.ffn_norm.weight 0x52377400 0x4000
245 blk.26.ffn_up.weight 0x5237b400 0x9c4000
246 blk.27.attn_k.weight 0x52d3f400 0xe0000
247 blk.27.attn_norm.weight 0x52e1f400 0x4000
248 blk.27.attn_output.weight 0x52e23400 0x4a0000
249 blk.27.attn_q.weight 0x532c3400 0x320000
250 blk.27.attn_v.weight 0x535e3400 0xc8000
251 blk.27.ffn_down.weight 0x536ab400 0x9c4000
252 blk.27.ffn_gate.weight 0x5406f400 0x9c4000
253 blk.27.ffn_norm.weight 0x54a33400 0x4000
254 blk.27.ffn_up.weight 0x54a37400 0x9c4000
255 blk.28.attn_k.weight 0x553fb400 0xe0000
256 blk.28.attn_norm.weight 0x554db400 0x4000
257 blk.28.attn_output.weight 0x554df400 0x4a0000
258 blk.28.attn_q.weight 0x5597f400 0x380000
259 blk.28.attn_v.weight 0x55cff400 0xc8000
260 blk.28.ffn_down.weight 0x55dc7400 0xaf0000
261 blk.28.ffn_gate.weight 0x568b7400 0x9c4000
262 blk.28.ffn_norm.weight 0x5727b400 0x4000
263 blk.28.ffn_up.weight 0x5727f400 0x9c4000
264 blk.29.attn_k.weight 0x57c43400 0xc8000
265 blk.29.attn_norm.weight 0x57d0b400 0x4000
266 blk.29.attn_output.weight 0x57d0f400 0x4a0000
267 blk.29.attn_q.weight 0x581af400 0x320000
268 blk.29.attn_v.weight 0x584cf400 0xc8000
269 blk.29.ffn_down.weight 0x58597400 0x9c4000
270 blk.29.ffn_gate.weight 0x58f5b400 0x9c4000
271 blk.29.ffn_norm.weight 0x5991f400 0x4000
272 blk.29.ffn_up.weight 0x59923400 0x9c4000
273 blk.30.attn_k.weight 0x5a2e7400 0xe0000
274 blk.30.attn_norm.weight 0x5a3c7400 0x4000
275 blk.30.attn_output.weight 0x5a3cb400 0x4a0000
276 blk.30.attn_q.weight 0x5a86b400 0x380000
277 blk.30.attn_v.weight 0x5abeb400 0xc8000
278 blk.30.ffn_down.weight 0x5acb3400 0xaf0000
279 blk.30.ffn_gate.weight 0x5b7a3400 0x9c4000
280 blk.30.ffn_norm.weight 0x5c167400 0x4000
281 blk.30.ffn_up.weight 0x5c16b400 0x9c4000
282 blk.31.attn_k.weight 0x5cb2f400 0xc8000
283 blk.31.attn_norm.weight 0x5cbf7400 0x4000
284 blk.31.attn_output.weight 0x5cbfb400 0x520000
285 blk.31.attn_q.weight 0x5d11b400 0x320000
286 blk.31.attn_v.weight 0x5d43b400 0xc8000
287 blk.31.ffn_down.weight 0x5d503400 0xaf0000
288 blk.31.ffn_gate.weight 0x5dff3400 0x9c4000
289 blk.31.ffn_norm.weight 0x5e9b7400 0x4000
290 blk.31.ffn_up.weight 0x5e9bb400 0x9c4000
291 blk.32.attn_k.weight 0x5f37f400 0xc8000
292 blk.32.attn_norm.weight 0x5f447400 0x4000
293 blk.32.attn_output.weight 0x5f44b400 0x4a0000
294 blk.32.attn_q.weight 0x5f8eb400 0x320000
295 blk.32.attn_v.weight 0x5fc0b400 0xc8000
296 blk.32.ffn_down.weight 0x5fcd3400 0xaf0000
297 blk.32.ffn_gate.weight 0x607c3400 0x9c4000
298 blk.32.ffn_norm.weight 0x61187400 0x4000
299 blk.32.ffn_up.weight 0x6118b400 0x9c4000
300 blk.33.attn_k.weight 0x61b4f400 0xc8000
301 blk.33.attn_norm.weight 0x61c17400 0x4000
302 blk.33.attn_output.weight 0x61c1b400 0x520000
303 blk.33.attn_q.weight 0x6213b400 0x320000
304 blk.33.attn_v.weight 0x6245b400 0xc8000
305 blk.33.ffn_down.weight 0x62523400 0x9c4000
306 blk.33.ffn_gate.weight 0x62ee7400 0x9c4000
307 blk.33.ffn_norm.weight 0x638ab400 0x4000
308 blk.33.ffn_up.weight 0x638af400 0x9c4000
309 blk.34.attn_k.weight 0x64273400 0xc8000
310 blk.34.attn_norm.weight 0x6433b400 0x4000
311 blk.34.attn_output.weight 0x6433f400 0x4a0000
312 blk.34.attn_q.weight 0x647df400 0x320000
313 blk.34.attn_v.weight 0x64aff400 0xc8000
314 blk.34.ffn_down.weight 0x64bc7400 0xaf0000
315 blk.34.ffn_gate.weight 0x656b7400 0x9c4000
316 blk.34.ffn_norm.weight 0x6607b400 0x4000
317 blk.34.ffn_up.weight 0x6607f400 0x9c4000
318 blk.35.attn_k.weight 0x66a43400 0xc8000
319 blk.35.attn_norm.weight 0x66b0b400 0x4000
320 blk.35.attn_output.weight 0x66b0f400 0x520000
321 blk.35.attn_q.weight 0x6702f400 0x320000
322 blk.35.attn_v.weight 0x6734f400 0xc8000
323 blk.35.ffn_down.weight 0x67417400 0x9c4000
324 blk.35.ffn_gate.weight 0x67ddb400 0x9c4000
325 blk.35.ffn_norm.weight 0x6879f400 0x4000
326 blk.35.ffn_up.weight 0x687a3400 0x9c4000
327 blk.36.attn_k.weight 0x69167400 0xc8000
328 blk.36.attn_norm.weight 0x6922f400 0x4000
329 blk.36.attn_output.weight 0x69233400 0x520000
330 blk.36.attn_q.weight 0x69753400 0x320000
331 blk.36.attn_v.weight 0x69a73400 0xc8000
332 blk.36.ffn_down.weight 0x69b3b400 0x9c4000
333 blk.36.ffn_gate.weight 0x6a4ff400 0x9c4000
334 blk.36.ffn_norm.weight 0x6aec3400 0x4000
335 blk.36.ffn_up.weight 0x6aec7400 0x9c4000
336 blk.37.attn_k.weight 0x6b88b400 0xc8000
337 blk.37.attn_norm.weight 0x6b953400 0x4000
338 blk.37.attn_output.weight 0x6b957400 0x520000
339 blk.37.attn_q.weight 0x6be77400 0x320000
340 blk.37.attn_v.weight 0x6c197400 0xc8000
341 blk.37.ffn_down.weight 0x6c25f400 0x9c4000
342 blk.37.ffn_gate.weight 0x6cc23400 0x9c4000
343 blk.37.ffn_norm.weight 0x6d5e7400 0x4000
344 blk.37.ffn_up.weight 0x6d5eb400 0x9c4000
345 blk.38.attn_k.weight 0x6dfaf400 0xc8000
346 blk.38.attn_norm.weight 0x6e077400 0x4000
347 blk.38.attn_output.weight 0x6e07b400 0x520000
348 blk.38.attn_q.weight 0x6e59b400 0x320000
349 blk.38.attn_v.weight 0x6e8bb400 0xc8000
350 blk.38.ffn_down.weight 0x6e983400 0x9c4000
351 blk.38.ffn_gate.weight 0x6f347400 0x9c4000
352 blk.38.ffn_norm.weight 0x6fd0b400 0x4000
353 blk.38.ffn_up.weight 0x6fd0f400 0x9c4000
354 blk.39.attn_k.weight 0x706d3400 0xc8000
355 blk.39.attn_norm.weight 0x7079b400 0x4000
356 blk.39.attn_output.weight 0x7079f400 0x4a0000
357 blk.39.attn_q.weight 0x70c3f400 0x320000
358 blk.39.attn_v.weight 0x70f5f400 0xc8000
359 blk.39.ffn_down.weight 0x71027400 0x9c4000
360 blk.39.ffn_gate.weight 0x719eb400 0x9c4000
361 blk.39.ffn_norm.weight 0x723af400 0x4000
362 blk.39.ffn_up.weight 0x723b3400 0x9c4000

Base Tensor Group : ~822M Elements

T_ID Tensor Layer Name Human Friendly Tensor Layer Name Elements Shape Type BPW
0 output.weight Output (W) (~411M) 411041792 4096 x 100352 x 1 x 1 Q2_K 2.6250
1 output_norm.weight Output Normalization (W) ( ~4K) 4096 4096 x 1 x 1 x 1 F32 32.0000
2 token_embd.weight Token Embedding (W) (~411M) 411041792 4096 x 100352 x 1 x 1 Q2_K 2.6250
  • Total elements in base: (~822M) 822087680
  • Percentage of total elements: 9.35%
  • Bits per Weight (BPW) for base: 2.6251 bits

Block 0 Tensor Group : ~199M Elements

T_ID Tensor Layer Name Human Friendly Tensor Layer Name Elements Shape Type BPW
3 blk.0.attn_k.weight Block 0 Attention Key (W) ( ~4M) 4194304 4096 x 1024 x 1 x 1 IQ1_S 1.5625
4 blk.0.attn_norm.weight Block 0 Attention Normalization (W) ( ~4K) 4096 4096 x 1 x 1 x 1 F32 32.0000
5 blk.0.attn_output.weight Block 0 Attention Output (W) (~17M) 16777216 4096 x 4096 x 1 x 1 IQ1_M 1.7500
6 blk.0.attn_q.weight Block 0 Attention Query (W) (~17M) 16777216 4096 x 4096 x 1 x 1 IQ1_S 1.5625
7 blk.0.attn_v.weight Block 0 Attention Value (W) ( ~4M) 4194304 4096 x 1024 x 1 x 1 IQ1_S 1.5625
8 blk.0.ffn_down.weight Block 0 Feed-Forward Network "Down" (W) (~52M) 52428800 12800 x 4096 x 1 x 1 IQ1_S 1.5625
9 blk.0.ffn_gate.weight Block 0 Feed-Forward Network "Gate" (W) (~52M) 52428800 4096 x 12800 x 1 x 1 IQ1_S 1.5625
10 blk.0.ffn_norm.weight Block 0 Feed-Forward Network Normalization (W) ( ~4K) 4096 4096 x 1 x 1 x 1 F32 32.0000
11 blk.0.ffn_up.weight Block 0 Feed-Forward Network "Up" (W) (~52M) 52428800 4096 x 12800 x 1 x 1 IQ1_S 1.5625
  • Total elements in blk.0: (~199M) 199237632
  • Percentage of total elements: 2.27%
  • Bits per Weight (BPW) for blk.0: 1.5795 bits

Block 1 Tensor Group : ~199M Elements

T_ID Tensor Layer Name Human Friendly Tensor Layer Name Elements Shape Type BPW
12 blk.1.attn_k.weight Block 1 Attention Key (W) ( ~4M) 4194304 4096 x 1024 x 1 x 1 IQ1_S 1.5625
13 blk.1.attn_norm.weight Block 1 Attention Normalization (W) ( ~4K) 4096 4096 x 1 x 1 x 1 F32 32.0000
14 blk.1.attn_output.weight Block 1 Attention Output (W) (~17M) 16777216 4096 x 4096 x 1 x 1 IQ2_XS 2.3125
15 blk.1.attn_q.weight Block 1 Attention Query (W) (~17M) 16777216 4096 x 4096 x 1 x 1 IQ1_S 1.5625
16 blk.1.attn_v.weight Block 1 Attention Value (W) ( ~4M) 4194304 4096 x 1024 x 1 x 1 IQ1_M 1.7500
17 blk.1.ffn_down.weight Block 1 Feed-Forward Network "Down" (W) (~52M) 52428800 12800 x 4096 x 1 x 1 IQ2_XXS 2.0625
18 blk.1.ffn_gate.weight Block 1 Feed-Forward Network "Gate" (W) (~52M) 52428800 4096 x 12800 x 1 x 1 IQ1_S 1.5625
19 blk.1.ffn_norm.weight Block 1 Feed-Forward Network Normalization (W) ( ~4K) 4096 4096 x 1 x 1 x 1 F32 32.0000
20 blk.1.ffn_up.weight Block 1 Feed-Forward Network "Up" (W) (~52M) 52428800 4096 x 12800 x 1 x 1 IQ1_S 1.5625
  • Total elements in blk.1: (~199M) 199237632
  • Percentage of total elements: 2.27%
  • Bits per Weight (BPW) for blk.1: 1.7624 bits

Block 2 Tensor Group : ~199M Elements

T_ID Tensor Layer Name Human Friendly Tensor Layer Name Elements Shape Type BPW
21 blk.2.attn_k.weight Block 2 Attention Key (W) ( ~4M) 4194304 4096 x 1024 x 1 x 1 IQ1_S 1.5625
22 blk.2.attn_norm.weight Block 2 Attention Normalization (W) ( ~4K) 4096 4096 x 1 x 1 x 1 F32 32.0000
23 blk.2.attn_output.weight Block 2 Attention Output (W) (~17M) 16777216 4096 x 4096 x 1 x 1 IQ2_S 2.5625
24 blk.2.attn_q.weight Block 2 Attention Query (W) (~17M) 16777216 4096 x 4096 x 1 x 1 IQ1_S 1.5625
25 blk.2.attn_v.weight Block 2 Attention Value (W) ( ~4M) 4194304 4096 x 1024 x 1 x 1 IQ1_S 1.5625
26 blk.2.ffn_down.weight Block 2 Feed-Forward Network "Down" (W) (~52M) 52428800 12800 x 4096 x 1 x 1 IQ1_S 1.5625
27 blk.2.ffn_gate.weight Block 2 Feed-Forward Network "Gate" (W) (~52M) 52428800 4096 x 12800 x 1 x 1 IQ1_S 1.5625
28 blk.2.ffn_norm.weight Block 2 Feed-Forward Network Normalization (W) ( ~4K) 4096 4096 x 1 x 1 x 1 F32 32.0000
29 blk.2.ffn_up.weight Block 2 Feed-Forward Network "Up" (W) (~52M) 52428800 4096 x 12800 x 1 x 1 IQ1_S 1.5625
  • Total elements in blk.2: (~199M) 199237632
  • Percentage of total elements: 2.27%
  • Bits per Weight (BPW) for blk.2: 1.6480 bits

Block 3 Tensor Group : ~199M Elements

T_ID Tensor Layer Name Human Friendly Tensor Layer Name Elements Shape Type BPW
30 blk.3.attn_k.weight Block 3 Attention Key (W) ( ~4M) 4194304 4096 x 1024 x 1 x 1 IQ1_S 1.5625
31 blk.3.attn_norm.weight Block 3 Attention Normalization (W) ( ~4K) 4096 4096 x 1 x 1 x 1 F32 32.0000
32 blk.3.attn_output.weight Block 3 Attention Output (W) (~17M) 16777216 4096 x 4096 x 1 x 1 IQ2_S 2.5625
33 blk.3.attn_q.weight Block 3 Attention Query (W) (~17M) 16777216 4096 x 4096 x 1 x 1 IQ1_S 1.5625
34 blk.3.attn_v.weight Block 3 Attention Value (W) ( ~4M) 4194304 4096 x 1024 x 1 x 1 IQ1_S 1.5625
35 blk.3.ffn_down.weight Block 3 Feed-Forward Network "Down" (W) (~52M) 52428800 12800 x 4096 x 1 x 1 IQ1_S 1.5625
36 blk.3.ffn_gate.weight Block 3 Feed-Forward Network "Gate" (W) (~52M) 52428800 4096 x 12800 x 1 x 1 IQ1_S 1.5625
37 blk.3.ffn_norm.weight Block 3 Feed-Forward Network Normalization (W) ( ~4K) 4096 4096 x 1 x 1 x 1 F32 32.0000
38 blk.3.ffn_up.weight Block 3 Feed-Forward Network "Up" (W) (~52M) 52428800 4096 x 12800 x 1 x 1 IQ1_S 1.5625
  • Total elements in blk.3: (~199M) 199237632
  • Percentage of total elements: 2.27%
  • Bits per Weight (BPW) for blk.3: 1.6480 bits

Block 4 Tensor Group : ~199M Elements

T_ID Tensor Layer Name Human Friendly Tensor Layer Name Elements Shape Type BPW
39 blk.4.attn_k.weight Block 4 Attention Key (W) ( ~4M) 4194304 4096 x 1024 x 1 x 1 IQ1_M 1.7500
40 blk.4.attn_norm.weight Block 4 Attention Normalization (W) ( ~4K) 4096 4096 x 1 x 1 x 1 F32 32.0000
41 blk.4.attn_output.weight Block 4 Attention Output (W) (~17M) 16777216 4096 x 4096 x 1 x 1 IQ2_S 2.5625
42 blk.4.attn_q.weight Block 4 Attention Query (W) (~17M) 16777216 4096 x 4096 x 1 x 1 IQ1_M 1.7500
43 blk.4.attn_v.weight Block 4 Attention Value (W) ( ~4M) 4194304 4096 x 1024 x 1 x 1 IQ1_M 1.7500
44 blk.4.ffn_down.weight Block 4 Feed-Forward Network "Down" (W) (~52M) 52428800 12800 x 4096 x 1 x 1 IQ1_S 1.5625
45 blk.4.ffn_gate.weight Block 4 Feed-Forward Network "Gate" (W) (~52M) 52428800 4096 x 12800 x 1 x 1 IQ1_S 1.5625
46 blk.4.ffn_norm.weight Block 4 Feed-Forward Network Normalization (W) ( ~4K) 4096 4096 x 1 x 1 x 1 F32 32.0000
47 blk.4.ffn_up.weight Block 4 Feed-Forward Network "Up" (W) (~52M) 52428800 4096 x 12800 x 1 x 1 IQ1_S 1.5625
  • Total elements in blk.4: (~199M) 199237632
  • Percentage of total elements: 2.27%
  • Bits per Weight (BPW) for blk.4: 1.6716 bits

Block 5 Tensor Group : ~199M Elements

T_ID Tensor Layer Name Human Friendly Tensor Layer Name Elements Shape Type BPW
48 blk.5.attn_k.weight Block 5 Attention Key (W) ( ~4M) 4194304 4096 x 1024 x 1 x 1 IQ1_S 1.5625
49 blk.5.attn_norm.weight Block 5 Attention Normalization (W) ( ~4K) 4096 4096 x 1 x 1 x 1 F32 32.0000
50 blk.5.attn_output.weight Block 5 Attention Output (W) (~17M) 16777216 4096 x 4096 x 1 x 1 IQ2_S 2.5625
51 blk.5.attn_q.weight Block 5 Attention Query (W) (~17M) 16777216 4096 x 4096 x 1 x 1 IQ1_S 1.5625
52 blk.5.attn_v.weight Block 5 Attention Value (W) ( ~4M) 4194304 4096 x 1024 x 1 x 1 IQ1_S 1.5625
53 blk.5.ffn_down.weight Block 5 Feed-Forward Network "Down" (W) (~52M) 52428800 12800 x 4096 x 1 x 1 IQ1_M 1.7500
54 blk.5.ffn_gate.weight Block 5 Feed-Forward Network "Gate" (W) (~52M) 52428800 4096 x 12800 x 1 x 1 IQ1_S 1.5625
55 blk.5.ffn_norm.weight Block 5 Feed-Forward Network Normalization (W) ( ~4K) 4096 4096 x 1 x 1 x 1 F32 32.0000
56 blk.5.ffn_up.weight Block 5 Feed-Forward Network "Up" (W) (~52M) 52428800 4096 x 12800 x 1 x 1 IQ1_S 1.5625
  • Total elements in blk.5: (~199M) 199237632
  • Percentage of total elements: 2.27%
  • Bits per Weight (BPW) for blk.5: 1.6973 bits

Block 6 Tensor Group : ~199M Elements

T_ID Tensor Layer Name Human Friendly Tensor Layer Name Elements Shape Type BPW
57 blk.6.attn_k.weight Block 6 Attention Key (W) ( ~4M) 4194304 4096 x 1024 x 1 x 1 IQ1_S 1.5625
58 blk.6.attn_norm.weight Block 6 Attention Normalization (W) ( ~4K) 4096 4096 x 1 x 1 x 1 F32 32.0000
59 blk.6.attn_output.weight Block 6 Attention Output (W) (~17M) 16777216 4096 x 4096 x 1 x 1 IQ2_XS 2.3125
60 blk.6.attn_q.weight Block 6 Attention Query (W) (~17M) 16777216 4096 x 4096 x 1 x 1 IQ1_S 1.5625
61 blk.6.attn_v.weight Block 6 Attention Value (W) ( ~4M) 4194304 4096 x 1024 x 1 x 1 IQ1_S 1.5625
62 blk.6.ffn_down.weight Block 6 Feed-Forward Network "Down" (W) (~52M) 52428800 12800 x 4096 x 1 x 1 IQ1_S 1.5625
63 blk.6.ffn_gate.weight Block 6 Feed-Forward Network "Gate" (W) (~52M) 52428800 4096 x 12800 x 1 x 1 IQ1_S 1.5625
64 blk.6.ffn_norm.weight Block 6 Feed-Forward Network Normalization (W) ( ~4K) 4096 4096 x 1 x 1 x 1 F32 32.0000
65 blk.6.ffn_up.weight Block 6 Feed-Forward Network "Up" (W) (~52M) 52428800 4096 x 12800 x 1 x 1 IQ1_S 1.5625
  • Total elements in blk.6: (~199M) 199237632
  • Percentage of total elements: 2.27%
  • Bits per Weight (BPW) for blk.6: 1.6269 bits

Block 7 Tensor Group : ~199M Elements

T_ID Tensor Layer Name Human Friendly Tensor Layer Name Elements Shape Type BPW
66 blk.7.attn_k.weight Block 7 Attention Key (W) ( ~4M) 4194304 4096 x 1024 x 1 x 1 IQ1_M 1.7500
67 blk.7.attn_norm.weight Block 7 Attention Normalization (W) ( ~4K) 4096 4096 x 1 x 1 x 1 F32 32.0000
68 blk.7.attn_output.weight Block 7 Attention Output (W) (~17M) 16777216 4096 x 4096 x 1 x 1 IQ2_XS 2.3125
69 blk.7.attn_q.weight Block 7 Attention Query (W) (~17M) 16777216 4096 x 4096 x 1 x 1 IQ1_M 1.7500
70 blk.7.attn_v.weight Block 7 Attention Value (W) ( ~4M) 4194304 4096 x 1024 x 1 x 1 IQ1_S 1.5625
71 blk.7.ffn_down.weight Block 7 Feed-Forward Network "Down" (W) (~52M) 52428800 12800 x 4096 x 1 x 1 IQ1_S 1.5625
72 blk.7.ffn_gate.weight Block 7 Feed-Forward Network "Gate" (W) (~52M) 52428800 4096 x 12800 x 1 x 1 IQ1_S 1.5625
73 blk.7.ffn_norm.weight Block 7 Feed-Forward Network Normalization (W) ( ~4K) 4096 4096 x 1 x 1 x 1 F32 32.0000
74 blk.7.ffn_up.weight Block 7 Feed-Forward Network "Up" (W) (~52M) 52428800 4096 x 12800 x 1 x 1 IQ1_S 1.5625
  • Total elements in blk.7: (~199M) 199237632
  • Percentage of total elements: 2.27%
  • Bits per Weight (BPW) for blk.7: 1.6466 bits

Block 8 Tensor Group : ~199M Elements

T_ID Tensor Layer Name Human Friendly Tensor Layer Name Elements Shape Type BPW
75 blk.8.attn_k.weight Block 8 Attention Key (W) ( ~4M) 4194304 4096 x 1024 x 1 x 1 IQ1_S 1.5625
76 blk.8.attn_norm.weight Block 8 Attention Normalization (W) ( ~4K) 4096 4096 x 1 x 1 x 1 F32 32.0000
77 blk.8.attn_output.weight Block 8 Attention Output (W) (~17M) 16777216 4096 x 4096 x 1 x 1 IQ2_XS 2.3125
78 blk.8.attn_q.weight Block 8 Attention Query (W) (~17M) 16777216 4096 x 4096 x 1 x 1 IQ1_S 1.5625
79 blk.8.attn_v.weight Block 8 Attention Value (W) ( ~4M) 4194304 4096 x 1024 x 1 x 1 IQ1_S 1.5625
80 blk.8.ffn_down.weight Block 8 Feed-Forward Network "Down" (W) (~52M) 52428800 12800 x 4096 x 1 x 1 IQ1_S 1.5625
81 blk.8.ffn_gate.weight Block 8 Feed-Forward Network "Gate" (W) (~52M) 52428800 4096 x 12800 x 1 x 1 IQ1_S 1.5625
82 blk.8.ffn_norm.weight Block 8 Feed-Forward Network Normalization (W) ( ~4K) 4096 4096 x 1 x 1 x 1 F32 32.0000
83 blk.8.ffn_up.weight Block 8 Feed-Forward Network "Up" (W) (~52M) 52428800 4096 x 12800 x 1 x 1 IQ1_S 1.5625
  • Total elements in blk.8: (~199M) 199237632
  • Percentage of total elements: 2.27%
  • Bits per Weight (BPW) for blk.8: 1.6269 bits

Block 9 Tensor Group : ~199M Elements

T_ID Tensor Layer Name Human Friendly Tensor Layer Name Elements Shape Type BPW
84 blk.9.attn_k.weight Block 9 Attention Key (W) ( ~4M) 4194304 4096 x 1024 x 1 x 1 IQ1_S 1.5625
85 blk.9.attn_norm.weight Block 9 Attention Normalization (W) ( ~4K) 4096 4096 x 1 x 1 x 1 F32 32.0000
86 blk.9.attn_output.weight Block 9 Attention Output (W) (~17M) 16777216 4096 x 4096 x 1 x 1 IQ2_S 2.5625
87 blk.9.attn_q.weight Block 9 Attention Query (W) (~17M) 16777216 4096 x 4096 x 1 x 1 IQ1_S 1.5625
88 blk.9.attn_v.weight Block 9 Attention Value (W) ( ~4M) 4194304 4096 x 1024 x 1 x 1 IQ1_S 1.5625
89 blk.9.ffn_down.weight Block 9 Feed-Forward Network "Down" (W) (~52M) 52428800 12800 x 4096 x 1 x 1 IQ1_S 1.5625
90 blk.9.ffn_gate.weight Block 9 Feed-Forward Network "Gate" (W) (~52M) 52428800 4096 x 12800 x 1 x 1 IQ1_S 1.5625
91 blk.9.ffn_norm.weight Block 9 Feed-Forward Network Normalization (W) ( ~4K) 4096 4096 x 1 x 1 x 1 F32 32.0000
92 blk.9.ffn_up.weight Block 9 Feed-Forward Network "Up" (W) (~52M) 52428800 4096 x 12800 x 1 x 1 IQ1_S 1.5625
  • Total elements in blk.9: (~199M) 199237632
  • Percentage of total elements: 2.27%
  • Bits per Weight (BPW) for blk.9: 1.6480 bits

Block 10 Tensor Group : ~199M Elements

T_ID Tensor Layer Name Human Friendly Tensor Layer Name Elements Shape Type BPW
93 blk.10.attn_k.weight Block 10 Attention Key (W) ( ~4M) 4194304 4096 x 1024 x 1 x 1 IQ1_S 1.5625
94 blk.10.attn_norm.weight Block 10 Attention Normalization (W) ( ~4K) 4096 4096 x 1 x 1 x 1 F32 32.0000
95 blk.10.attn_output.weight Block 10 Attention Output (W) (~17M) 16777216 4096 x 4096 x 1 x 1 IQ2_XS 2.3125
96 blk.10.attn_q.weight Block 10 Attention Query (W) (~17M) 16777216 4096 x 4096 x 1 x 1 IQ1_S 1.5625
97 blk.10.attn_v.weight Block 10 Attention Value (W) ( ~4M) 4194304 4096 x 1024 x 1 x 1 IQ1_S 1.5625
98 blk.10.ffn_down.weight Block 10 Feed-Forward Network "Down" (W) (~52M) 52428800 12800 x 4096 x 1 x 1 IQ1_S 1.5625
99 blk.10.ffn_gate.weight Block 10 Feed-Forward Network "Gate" (W) (~52M) 52428800 4096 x 12800 x 1 x 1 IQ1_S 1.5625
100 blk.10.ffn_norm.weight Block 10 Feed-Forward Network Normalization (W) ( ~4K) 4096 4096 x 1 x 1 x 1 F32 32.0000
101 blk.10.ffn_up.weight Block 10 Feed-Forward Network "Up" (W) (~52M) 52428800 4096 x 12800 x 1 x 1 IQ1_S 1.5625
  • Total elements in blk.10: (~199M) 199237632
  • Percentage of total elements: 2.27%
  • Bits per Weight (BPW) for blk.10: 1.6269 bits

Block 11 Tensor Group : ~199M Elements

T_ID Tensor Layer Name Human Friendly Tensor Layer Name Elements Shape Type BPW
102 blk.11.attn_k.weight Block 11 Attention Key (W) ( ~4M) 4194304 4096 x 1024 x 1 x 1 IQ1_S 1.5625
103 blk.11.attn_norm.weight Block 11 Attention Normalization (W) ( ~4K) 4096 4096 x 1 x 1 x 1 F32 32.0000
104 blk.11.attn_output.weight Block 11 Attention Output (W) (~17M) 16777216 4096 x 4096 x 1 x 1 IQ2_XS 2.3125
105 blk.11.attn_q.weight Block 11 Attention Query (W) (~17M) 16777216 4096 x 4096 x 1 x 1 IQ1_S 1.5625
106 blk.11.attn_v.weight Block 11 Attention Value (W) ( ~4M) 4194304 4096 x 1024 x 1 x 1 IQ1_S 1.5625
107 blk.11.ffn_down.weight Block 11 Feed-Forward Network "Down" (W) (~52M) 52428800 12800 x 4096 x 1 x 1 IQ1_S 1.5625
108 blk.11.ffn_gate.weight Block 11 Feed-Forward Network "Gate" (W) (~52M) 52428800 4096 x 12800 x 1 x 1 IQ1_S 1.5625
109 blk.11.ffn_norm.weight Block 11 Feed-Forward Network Normalization (W) ( ~4K) 4096 4096 x 1 x 1 x 1 F32 32.0000
110 blk.11.ffn_up.weight Block 11 Feed-Forward Network "Up" (W) (~52M) 52428800 4096 x 12800 x 1 x 1 IQ1_S 1.5625
  • Total elements in blk.11: (~199M) 199237632
  • Percentage of total elements: 2.27%
  • Bits per Weight (BPW) for blk.11: 1.6269 bits

Block 12 Tensor Group : ~199M Elements

T_ID Tensor Layer Name Human Friendly Tensor Layer Name Elements Shape Type BPW
111 blk.12.attn_k.weight Block 12 Attention Key (W) ( ~4M) 4194304 4096 x 1024 x 1 x 1 IQ1_S 1.5625
112 blk.12.attn_norm.weight Block 12 Attention Normalization (W) ( ~4K) 4096 4096 x 1 x 1 x 1 F32 32.0000
113 blk.12.attn_output.weight Block 12 Attention Output (W) (~17M) 16777216 4096 x 4096 x 1 x 1 IQ2_S 2.5625
114 blk.12.attn_q.weight Block 12 Attention Query (W) (~17M) 16777216 4096 x 4096 x 1 x 1 IQ1_S 1.5625
115 blk.12.attn_v.weight Block 12 Attention Value (W) ( ~4M) 4194304 4096 x 1024 x 1 x 1 IQ1_S 1.5625
116 blk.12.ffn_down.weight Block 12 Feed-Forward Network "Down" (W) (~52M) 52428800 12800 x 4096 x 1 x 1 IQ1_S 1.5625
117 blk.12.ffn_gate.weight Block 12 Feed-Forward Network "Gate" (W) (~52M) 52428800 4096 x 12800 x 1 x 1 IQ1_S 1.5625
118 blk.12.ffn_norm.weight Block 12 Feed-Forward Network Normalization (W) ( ~4K) 4096 4096 x 1 x 1 x 1 F32 32.0000
119 blk.12.ffn_up.weight Block 12 Feed-Forward Network "Up" (W) (~52M) 52428800 4096 x 12800 x 1 x 1 IQ1_S 1.5625
  • Total elements in blk.12: (~199M) 199237632
  • Percentage of total elements: 2.27%
  • Bits per Weight (BPW) for blk.12: 1.6480 bits

Block 13 Tensor Group : ~199M Elements

T_ID Tensor Layer Name Human Friendly Tensor Layer Name Elements Shape Type BPW
120 blk.13.attn_k.weight Block 13 Attention Key (W) ( ~4M) 4194304 4096 x 1024 x 1 x 1 IQ1_S 1.5625
121 blk.13.attn_norm.weight Block 13 Attention Normalization (W) ( ~4K) 4096 4096 x 1 x 1 x 1 F32 32.0000
122 blk.13.attn_output.weight Block 13 Attention Output (W) (~17M) 16777216 4096 x 4096 x 1 x 1 IQ2_XS 2.3125
123 blk.13.attn_q.weight Block 13 Attention Query (W) (~17M) 16777216 4096 x 4096 x 1 x 1 IQ1_S 1.5625
124 blk.13.attn_v.weight Block 13 Attention Value (W) ( ~4M) 4194304 4096 x 1024 x 1 x 1 IQ1_S 1.5625
125 blk.13.ffn_down.weight Block 13 Feed-Forward Network "Down" (W) (~52M) 52428800 12800 x 4096 x 1 x 1 IQ1_S 1.5625
126 blk.13.ffn_gate.weight Block 13 Feed-Forward Network "Gate" (W) (~52M) 52428800 4096 x 12800 x 1 x 1 IQ1_S 1.5625
127 blk.13.ffn_norm.weight Block 13 Feed-Forward Network Normalization (W) ( ~4K) 4096 4096 x 1 x 1 x 1 F32 32.0000
128 blk.13.ffn_up.weight Block 13 Feed-Forward Network "Up" (W) (~52M) 52428800 4096 x 12800 x 1 x 1 IQ1_S 1.5625
  • Total elements in blk.13: (~199M) 199237632
  • Percentage of total elements: 2.27%
  • Bits per Weight (BPW) for blk.13: 1.6269 bits

Block 14 Tensor Group : ~199M Elements

T_ID Tensor Layer Name Human Friendly Tensor Layer Name Elements Shape Type BPW
129 blk.14.attn_k.weight Block 14 Attention Key (W) ( ~4M) 4194304 4096 x 1024 x 1 x 1 IQ1_S 1.5625
130 blk.14.attn_norm.weight Block 14 Attention Normalization (W) ( ~4K) 4096 4096 x 1 x 1 x 1 F32 32.0000
131 blk.14.attn_output.weight Block 14 Attention Output (W) (~17M) 16777216 4096 x 4096 x 1 x 1 IQ2_XS 2.3125
132 blk.14.attn_q.weight Block 14 Attention Query (W) (~17M) 16777216 4096 x 4096 x 1 x 1 IQ1_S 1.5625
133 blk.14.attn_v.weight Block 14 Attention Value (W) ( ~4M) 4194304 4096 x 1024 x 1 x 1 IQ1_S 1.5625
134 blk.14.ffn_down.weight Block 14 Feed-Forward Network "Down" (W) (~52M) 52428800 12800 x 4096 x 1 x 1 IQ1_S 1.5625
135 blk.14.ffn_gate.weight Block 14 Feed-Forward Network "Gate" (W) (~52M) 52428800 4096 x 12800 x 1 x 1 IQ1_S 1.5625
136 blk.14.ffn_norm.weight Block 14 Feed-Forward Network Normalization (W) ( ~4K) 4096 4096 x 1 x 1 x 1 F32 32.0000
137 blk.14.ffn_up.weight Block 14 Feed-Forward Network "Up" (W) (~52M) 52428800 4096 x 12800 x 1 x 1 IQ1_S 1.5625
  • Total elements in blk.14: (~199M) 199237632
  • Percentage of total elements: 2.27%
  • Bits per Weight (BPW) for blk.14: 1.6269 bits

Block 15 Tensor Group : ~199M Elements

T_ID Tensor Layer Name Human Friendly Tensor Layer Name Elements Shape Type BPW
138 blk.15.attn_k.weight Block 15 Attention Key (W) ( ~4M) 4194304 4096 x 1024 x 1 x 1 IQ1_M 1.7500
139 blk.15.attn_norm.weight Block 15 Attention Normalization (W) ( ~4K) 4096 4096 x 1 x 1 x 1 F32 32.0000
140 blk.15.attn_output.weight Block 15 Attention Output (W) (~17M) 16777216 4096 x 4096 x 1 x 1 IQ2_XS 2.3125
141 blk.15.attn_q.weight Block 15 Attention Query (W) (~17M) 16777216 4096 x 4096 x 1 x 1 IQ1_M 1.7500
142 blk.15.attn_v.weight Block 15 Attention Value (W) ( ~4M) 4194304 4096 x 1024 x 1 x 1 IQ1_S 1.5625
143 blk.15.ffn_down.weight Block 15 Feed-Forward Network "Down" (W) (~52M) 52428800 12800 x 4096 x 1 x 1 IQ1_M 1.7500
144 blk.15.ffn_gate.weight Block 15 Feed-Forward Network "Gate" (W) (~52M) 52428800 4096 x 12800 x 1 x 1 IQ1_S 1.5625
145 blk.15.ffn_norm.weight Block 15 Feed-Forward Network Normalization (W) ( ~4K) 4096 4096 x 1 x 1 x 1 F32 32.0000
146 blk.15.ffn_up.weight Block 15 Feed-Forward Network "Up" (W) (~52M) 52428800 4096 x 12800 x 1 x 1 IQ1_S 1.5625
  • Total elements in blk.15: (~199M) 199237632
  • Percentage of total elements: 2.27%
  • Bits per Weight (BPW) for blk.15: 1.6960 bits

Block 16 Tensor Group : ~199M Elements

T_ID Tensor Layer Name Human Friendly Tensor Layer Name Elements Shape Type BPW
147 blk.16.attn_k.weight Block 16 Attention Key (W) ( ~4M) 4194304 4096 x 1024 x 1 x 1 IQ1_M 1.7500
148 blk.16.attn_norm.weight Block 16 Attention Normalization (W) ( ~4K) 4096 4096 x 1 x 1 x 1 F32 32.0000
149 blk.16.attn_output.weight Block 16 Attention Output (W) (~17M) 16777216 4096 x 4096 x 1 x 1 IQ2_XS 2.3125
150 blk.16.attn_q.weight Block 16 Attention Query (W) (~17M) 16777216 4096 x 4096 x 1 x 1 IQ1_M 1.7500
151 blk.16.attn_v.weight Block 16 Attention Value (W) ( ~4M) 4194304 4096 x 1024 x 1 x 1 IQ1_S 1.5625
152 blk.16.ffn_down.weight Block 16 Feed-Forward Network "Down" (W) (~52M) 52428800 12800 x 4096 x 1 x 1 IQ1_M 1.7500
153 blk.16.ffn_gate.weight Block 16 Feed-Forward Network "Gate" (W) (~52M) 52428800 4096 x 12800 x 1 x 1 IQ1_S 1.5625
154 blk.16.ffn_norm.weight Block 16 Feed-Forward Network Normalization (W) ( ~4K) 4096 4096 x 1 x 1 x 1 F32 32.0000
155 blk.16.ffn_up.weight Block 16 Feed-Forward Network "Up" (W) (~52M) 52428800 4096 x 12800 x 1 x 1 IQ1_S 1.5625
  • Total elements in blk.16: (~199M) 199237632
  • Percentage of total elements: 2.27%
  • Bits per Weight (BPW) for blk.16: 1.6960 bits

Block 17 Tensor Group : ~199M Elements

T_ID Tensor Layer Name Human Friendly Tensor Layer Name Elements Shape Type BPW
156 blk.17.attn_k.weight Block 17 Attention Key (W) ( ~4M) 4194304 4096 x 1024 x 1 x 1 IQ1_S 1.5625
157 blk.17.attn_norm.weight Block 17 Attention Normalization (W) ( ~4K) 4096 4096 x 1 x 1 x 1 F32 32.0000
158 blk.17.attn_output.weight Block 17 Attention Output (W) (~17M) 16777216 4096 x 4096 x 1 x 1 IQ2_XS 2.3125
159 blk.17.attn_q.weight Block 17 Attention Query (W) (~17M) 16777216 4096 x 4096 x 1 x 1 IQ1_S 1.5625
160 blk.17.attn_v.weight Block 17 Attention Value (W) ( ~4M) 4194304 4096 x 1024 x 1 x 1 IQ1_S 1.5625
161 blk.17.ffn_down.weight Block 17 Feed-Forward Network "Down" (W) (~52M) 52428800 12800 x 4096 x 1 x 1 IQ1_S 1.5625
162 blk.17.ffn_gate.weight Block 17 Feed-Forward Network "Gate" (W) (~52M) 52428800 4096 x 12800 x 1 x 1 IQ1_S 1.5625
163 blk.17.ffn_norm.weight Block 17 Feed-Forward Network Normalization (W) ( ~4K) 4096 4096 x 1 x 1 x 1 F32 32.0000
164 blk.17.ffn_up.weight Block 17 Feed-Forward Network "Up" (W) (~52M) 52428800 4096 x 12800 x 1 x 1 IQ1_S 1.5625
  • Total elements in blk.17: (~199M) 199237632
  • Percentage of total elements: 2.27%
  • Bits per Weight (BPW) for blk.17: 1.6269 bits

Block 18 Tensor Group : ~199M Elements

T_ID Tensor Layer Name Human Friendly Tensor Layer Name Elements Shape Type BPW
165 blk.18.attn_k.weight Block 18 Attention Key (W) ( ~4M) 4194304 4096 x 1024 x 1 x 1 IQ1_S 1.5625
166 blk.18.attn_norm.weight Block 18 Attention Normalization (W) ( ~4K) 4096 4096 x 1 x 1 x 1 F32 32.0000
167 blk.18.attn_output.weight Block 18 Attention Output (W) (~17M) 16777216 4096 x 4096 x 1 x 1 IQ2_XS 2.3125
168 blk.18.attn_q.weight Block 18 Attention Query (W) (~17M) 16777216 4096 x 4096 x 1 x 1 IQ1_S 1.5625
169 blk.18.attn_v.weight Block 18 Attention Value (W) ( ~4M) 4194304 4096 x 1024 x 1 x 1 IQ1_S 1.5625
170 blk.18.ffn_down.weight Block 18 Feed-Forward Network "Down" (W) (~52M) 52428800 12800 x 4096 x 1 x 1 IQ1_M 1.7500
171 blk.18.ffn_gate.weight Block 18 Feed-Forward Network "Gate" (W) (~52M) 52428800 4096 x 12800 x 1 x 1 IQ1_S 1.5625
172 blk.18.ffn_norm.weight Block 18 Feed-Forward Network Normalization (W) ( ~4K) 4096 4096 x 1 x 1 x 1 F32 32.0000
173 blk.18.ffn_up.weight Block 18 Feed-Forward Network "Up" (W) (~52M) 52428800 4096 x 12800 x 1 x 1 IQ1_S 1.5625
  • Total elements in blk.18: (~199M) 199237632
  • Percentage of total elements: 2.27%
  • Bits per Weight (BPW) for blk.18: 1.6762 bits

Block 19 Tensor Group : ~199M Elements

T_ID Tensor Layer Name Human Friendly Tensor Layer Name Elements Shape Type BPW
174 blk.19.attn_k.weight Block 19 Attention Key (W) ( ~4M) 4194304 4096 x 1024 x 1 x 1 IQ1_S 1.5625
175 blk.19.attn_norm.weight Block 19 Attention Normalization (W) ( ~4K) 4096 4096 x 1 x 1 x 1 F32 32.0000
176 blk.19.attn_output.weight Block 19 Attention Output (W) (~17M) 16777216 4096 x 4096 x 1 x 1 IQ2_XS 2.3125
177 blk.19.attn_q.weight Block 19 Attention Query (W) (~17M) 16777216 4096 x 4096 x 1 x 1 IQ1_S 1.5625
178 blk.19.attn_v.weight Block 19 Attention Value (W) ( ~4M) 4194304 4096 x 1024 x 1 x 1 IQ1_S 1.5625
179 blk.19.ffn_down.weight Block 19 Feed-Forward Network "Down" (W) (~52M) 52428800 12800 x 4096 x 1 x 1 IQ1_M 1.7500
180 blk.19.ffn_gate.weight Block 19 Feed-Forward Network "Gate" (W) (~52M) 52428800 4096 x 12800 x 1 x 1 IQ1_S 1.5625
181 blk.19.ffn_norm.weight Block 19 Feed-Forward Network Normalization (W) ( ~4K) 4096 4096 x 1 x 1 x 1 F32 32.0000
182 blk.19.ffn_up.weight Block 19 Feed-Forward Network "Up" (W) (~52M) 52428800 4096 x 12800 x 1 x 1 IQ1_S 1.5625
  • Total elements in blk.19: (~199M) 199237632
  • Percentage of total elements: 2.27%
  • Bits per Weight (BPW) for blk.19: 1.6762 bits

Block 20 Tensor Group : ~199M Elements

T_ID Tensor Layer Name Human Friendly Tensor Layer Name Elements Shape Type BPW
183 blk.20.attn_k.weight Block 20 Attention Key (W) ( ~4M) 4194304 4096 x 1024 x 1 x 1 IQ1_S 1.5625
184 blk.20.attn_norm.weight Block 20 Attention Normalization (W) ( ~4K) 4096 4096 x 1 x 1 x 1 F32 32.0000
185 blk.20.attn_output.weight Block 20 Attention Output (W) (~17M) 16777216 4096 x 4096 x 1 x 1 IQ2_S 2.5625
186 blk.20.attn_q.weight Block 20 Attention Query (W) (~17M) 16777216 4096 x 4096 x 1 x 1 IQ1_S 1.5625
187 blk.20.attn_v.weight Block 20 Attention Value (W) ( ~4M) 4194304 4096 x 1024 x 1 x 1 IQ1_S 1.5625
188 blk.20.ffn_down.weight Block 20 Feed-Forward Network "Down" (W) (~52M) 52428800 12800 x 4096 x 1 x 1 IQ1_S 1.5625
189 blk.20.ffn_gate.weight Block 20 Feed-Forward Network "Gate" (W) (~52M) 52428800 4096 x 12800 x 1 x 1 IQ1_S 1.5625
190 blk.20.ffn_norm.weight Block 20 Feed-Forward Network Normalization (W) ( ~4K) 4096 4096 x 1 x 1 x 1 F32 32.0000
191 blk.20.ffn_up.weight Block 20 Feed-Forward Network "Up" (W) (~52M) 52428800 4096 x 12800 x 1 x 1 IQ1_S 1.5625
  • Total elements in blk.20: (~199M) 199237632
  • Percentage of total elements: 2.27%
  • Bits per Weight (BPW) for blk.20: 1.6480 bits

Block 21 Tensor Group : ~199M Elements

T_ID Tensor Layer Name Human Friendly Tensor Layer Name Elements Shape Type BPW
192 blk.21.attn_k.weight Block 21 Attention Key (W) ( ~4M) 4194304 4096 x 1024 x 1 x 1 IQ1_S 1.5625
193 blk.21.attn_norm.weight Block 21 Attention Normalization (W) ( ~4K) 4096 4096 x 1 x 1 x 1 F32 32.0000
194 blk.21.attn_output.weight Block 21 Attention Output (W) (~17M) 16777216 4096 x 4096 x 1 x 1 IQ2_S 2.5625
195 blk.21.attn_q.weight Block 21 Attention Query (W) (~17M) 16777216 4096 x 4096 x 1 x 1 IQ1_S 1.5625
196 blk.21.attn_v.weight Block 21 Attention Value (W) ( ~4M) 4194304 4096 x 1024 x 1 x 1 IQ1_S 1.5625
197 blk.21.ffn_down.weight Block 21 Feed-Forward Network "Down" (W) (~52M) 52428800 12800 x 4096 x 1 x 1 IQ1_M 1.7500
198 blk.21.ffn_gate.weight Block 21 Feed-Forward Network "Gate" (W) (~52M) 52428800 4096 x 12800 x 1 x 1 IQ1_S 1.5625
199 blk.21.ffn_norm.weight Block 21 Feed-Forward Network Normalization (W) ( ~4K) 4096 4096 x 1 x 1 x 1 F32 32.0000
200 blk.21.ffn_up.weight Block 21 Feed-Forward Network "Up" (W) (~52M) 52428800 4096 x 12800 x 1 x 1 IQ1_S 1.5625
  • Total elements in blk.21: (~199M) 199237632
  • Percentage of total elements: 2.27%
  • Bits per Weight (BPW) for blk.21: 1.6973 bits

Block 22 Tensor Group : ~199M Elements

T_ID Tensor Layer Name Human Friendly Tensor Layer Name Elements Shape Type BPW
201 blk.22.attn_k.weight Block 22 Attention Key (W) ( ~4M) 4194304 4096 x 1024 x 1 x 1 IQ1_S 1.5625
202 blk.22.attn_norm.weight Block 22 Attention Normalization (W) ( ~4K) 4096 4096 x 1 x 1 x 1 F32 32.0000
203 blk.22.attn_output.weight Block 22 Attention Output (W) (~17M) 16777216 4096 x 4096 x 1 x 1 IQ2_S 2.5625
204 blk.22.attn_q.weight Block 22 Attention Query (W) (~17M) 16777216 4096 x 4096 x 1 x 1 IQ1_S 1.5625
205 blk.22.attn_v.weight Block 22 Attention Value (W) ( ~4M) 4194304 4096 x 1024 x 1 x 1 IQ1_S 1.5625
206 blk.22.ffn_down.weight Block 22 Feed-Forward Network "Down" (W) (~52M) 52428800 12800 x 4096 x 1 x 1 IQ1_M 1.7500
207 blk.22.ffn_gate.weight Block 22 Feed-Forward Network "Gate" (W) (~52M) 52428800 4096 x 12800 x 1 x 1 IQ1_S 1.5625
208 blk.22.ffn_norm.weight Block 22 Feed-Forward Network Normalization (W) ( ~4K) 4096 4096 x 1 x 1 x 1 F32 32.0000
209 blk.22.ffn_up.weight Block 22 Feed-Forward Network "Up" (W) (~52M) 52428800 4096 x 12800 x 1 x 1 IQ1_S 1.5625
  • Total elements in blk.22: (~199M) 199237632
  • Percentage of total elements: 2.27%
  • Bits per Weight (BPW) for blk.22: 1.6973 bits

Block 23 Tensor Group : ~199M Elements

T_ID Tensor Layer Name Human Friendly Tensor Layer Name Elements Shape Type BPW
210 blk.23.attn_k.weight Block 23 Attention Key (W) ( ~4M) 4194304 4096 x 1024 x 1 x 1 IQ1_S 1.5625
211 blk.23.attn_norm.weight Block 23 Attention Normalization (W) ( ~4K) 4096 4096 x 1 x 1 x 1 F32 32.0000
212 blk.23.attn_output.weight Block 23 Attention Output (W) (~17M) 16777216 4096 x 4096 x 1 x 1 IQ2_XS 2.3125
213 blk.23.attn_q.weight Block 23 Attention Query (W) (~17M) 16777216 4096 x 4096 x 1 x 1 IQ1_S 1.5625
214 blk.23.attn_v.weight Block 23 Attention Value (W) ( ~4M) 4194304 4096 x 1024 x 1 x 1 IQ1_S 1.5625
215 blk.23.ffn_down.weight Block 23 Feed-Forward Network "Down" (W) (~52M) 52428800 12800 x 4096 x 1 x 1 IQ1_S 1.5625
216 blk.23.ffn_gate.weight Block 23 Feed-Forward Network "Gate" (W) (~52M) 52428800 4096 x 12800 x 1 x 1 IQ1_S 1.5625
217 blk.23.ffn_norm.weight Block 23 Feed-Forward Network Normalization (W) ( ~4K) 4096 4096 x 1 x 1 x 1 F32 32.0000
218 blk.23.ffn_up.weight Block 23 Feed-Forward Network "Up" (W) (~52M) 52428800 4096 x 12800 x 1 x 1 IQ1_S 1.5625
  • Total elements in blk.23: (~199M) 199237632
  • Percentage of total elements: 2.27%
  • Bits per Weight (BPW) for blk.23: 1.6269 bits

Block 24 Tensor Group : ~199M Elements

T_ID Tensor Layer Name Human Friendly Tensor Layer Name Elements Shape Type BPW
219 blk.24.attn_k.weight Block 24 Attention Key (W) ( ~4M) 4194304 4096 x 1024 x 1 x 1 IQ1_S 1.5625
220 blk.24.attn_norm.weight Block 24 Attention Normalization (W) ( ~4K) 4096 4096 x 1 x 1 x 1 F32 32.0000
221 blk.24.attn_output.weight Block 24 Attention Output (W) (~17M) 16777216 4096 x 4096 x 1 x 1 IQ2_S 2.5625
222 blk.24.attn_q.weight Block 24 Attention Query (W) (~17M) 16777216 4096 x 4096 x 1 x 1 IQ1_S 1.5625
223 blk.24.attn_v.weight Block 24 Attention Value (W) ( ~4M) 4194304 4096 x 1024 x 1 x 1 IQ1_S 1.5625
224 blk.24.ffn_down.weight Block 24 Feed-Forward Network "Down" (W) (~52M) 52428800 12800 x 4096 x 1 x 1 IQ1_M 1.7500
225 blk.24.ffn_gate.weight Block 24 Feed-Forward Network "Gate" (W) (~52M) 52428800 4096 x 12800 x 1 x 1 IQ1_S 1.5625
226 blk.24.ffn_norm.weight Block 24 Feed-Forward Network Normalization (W) ( ~4K) 4096 4096 x 1 x 1 x 1 F32 32.0000
227 blk.24.ffn_up.weight Block 24 Feed-Forward Network "Up" (W) (~52M) 52428800 4096 x 12800 x 1 x 1 IQ1_S 1.5625
  • Total elements in blk.24: (~199M) 199237632
  • Percentage of total elements: 2.27%
  • Bits per Weight (BPW) for blk.24: 1.6973 bits

Block 25 Tensor Group : ~199M Elements

T_ID Tensor Layer Name Human Friendly Tensor Layer Name Elements Shape Type BPW
228 blk.25.attn_k.weight Block 25 Attention Key (W) ( ~4M) 4194304 4096 x 1024 x 1 x 1 IQ1_S 1.5625
229 blk.25.attn_norm.weight Block 25 Attention Normalization (W) ( ~4K) 4096 4096 x 1 x 1 x 1 F32 32.0000
230 blk.25.attn_output.weight Block 25 Attention Output (W) (~17M) 16777216 4096 x 4096 x 1 x 1 IQ2_XS 2.3125
231 blk.25.attn_q.weight Block 25 Attention Query (W) (~17M) 16777216 4096 x 4096 x 1 x 1 IQ1_S 1.5625
232 blk.25.attn_v.weight Block 25 Attention Value (W) ( ~4M) 4194304 4096 x 1024 x 1 x 1 IQ1_S 1.5625
233 blk.25.ffn_down.weight Block 25 Feed-Forward Network "Down" (W) (~52M) 52428800 12800 x 4096 x 1 x 1 IQ1_M 1.7500
234 blk.25.ffn_gate.weight Block 25 Feed-Forward Network "Gate" (W) (~52M) 52428800 4096 x 12800 x 1 x 1 IQ1_S 1.5625
235 blk.25.ffn_norm.weight Block 25 Feed-Forward Network Normalization (W) ( ~4K) 4096 4096 x 1 x 1 x 1 F32 32.0000
236 blk.25.ffn_up.weight Block 25 Feed-Forward Network "Up" (W) (~52M) 52428800 4096 x 12800 x 1 x 1 IQ1_S 1.5625
  • Total elements in blk.25: (~199M) 199237632
  • Percentage of total elements: 2.27%
  • Bits per Weight (BPW) for blk.25: 1.6762 bits

Block 26 Tensor Group : ~199M Elements

T_ID Tensor Layer Name Human Friendly Tensor Layer Name Elements Shape Type BPW
237 blk.26.attn_k.weight Block 26 Attention Key (W) ( ~4M) 4194304 4096 x 1024 x 1 x 1 IQ1_S 1.5625
238 blk.26.attn_norm.weight Block 26 Attention Normalization (W) ( ~4K) 4096 4096 x 1 x 1 x 1 F32 32.0000
239 blk.26.attn_output.weight Block 26 Attention Output (W) (~17M) 16777216 4096 x 4096 x 1 x 1 IQ2_S 2.5625
240 blk.26.attn_q.weight Block 26 Attention Query (W) (~17M) 16777216 4096 x 4096 x 1 x 1 IQ1_S 1.5625
241 blk.26.attn_v.weight Block 26 Attention Value (W) ( ~4M) 4194304 4096 x 1024 x 1 x 1 IQ1_S 1.5625
242 blk.26.ffn_down.weight Block 26 Feed-Forward Network "Down" (W) (~52M) 52428800 12800 x 4096 x 1 x 1 IQ1_M 1.7500
243 blk.26.ffn_gate.weight Block 26 Feed-Forward Network "Gate" (W) (~52M) 52428800 4096 x 12800 x 1 x 1 IQ1_S 1.5625
244 blk.26.ffn_norm.weight Block 26 Feed-Forward Network Normalization (W) ( ~4K) 4096 4096 x 1 x 1 x 1 F32 32.0000
245 blk.26.ffn_up.weight Block 26 Feed-Forward Network "Up" (W) (~52M) 52428800 4096 x 12800 x 1 x 1 IQ1_S 1.5625
  • Total elements in blk.26: (~199M) 199237632
  • Percentage of total elements: 2.27%
  • Bits per Weight (BPW) for blk.26: 1.6973 bits

Block 27 Tensor Group : ~199M Elements

T_ID Tensor Layer Name Human Friendly Tensor Layer Name Elements Shape Type BPW
246 blk.27.attn_k.weight Block 27 Attention Key (W) ( ~4M) 4194304 4096 x 1024 x 1 x 1 IQ1_M 1.7500
247 blk.27.attn_norm.weight Block 27 Attention Normalization (W) ( ~4K) 4096 4096 x 1 x 1 x 1 F32 32.0000
248 blk.27.attn_output.weight Block 27 Attention Output (W) (~17M) 16777216 4096 x 4096 x 1 x 1 IQ2_XS 2.3125
249 blk.27.attn_q.weight Block 27 Attention Query (W) (~17M) 16777216 4096 x 4096 x 1 x 1 IQ1_S 1.5625
250 blk.27.attn_v.weight Block 27 Attention Value (W) ( ~4M) 4194304 4096 x 1024 x 1 x 1 IQ1_S 1.5625
251 blk.27.ffn_down.weight Block 27 Feed-Forward Network "Down" (W) (~52M) 52428800 12800 x 4096 x 1 x 1 IQ1_S 1.5625
252 blk.27.ffn_gate.weight Block 27 Feed-Forward Network "Gate" (W) (~52M) 52428800 4096 x 12800 x 1 x 1 IQ1_S 1.5625
253 blk.27.ffn_norm.weight Block 27 Feed-Forward Network Normalization (W) ( ~4K) 4096 4096 x 1 x 1 x 1 F32 32.0000
254 blk.27.ffn_up.weight Block 27 Feed-Forward Network "Up" (W) (~52M) 52428800 4096 x 12800 x 1 x 1 IQ1_S 1.5625
  • Total elements in blk.27: (~199M) 199237632
  • Percentage of total elements: 2.27%
  • Bits per Weight (BPW) for blk.27: 1.6309 bits

Block 28 Tensor Group : ~199M Elements

T_ID Tensor Layer Name Human Friendly Tensor Layer Name Elements Shape Type BPW
255 blk.28.attn_k.weight Block 28 Attention Key (W) ( ~4M) 4194304 4096 x 1024 x 1 x 1 IQ1_M 1.7500
256 blk.28.attn_norm.weight Block 28 Attention Normalization (W) ( ~4K) 4096 4096 x 1 x 1 x 1 F32 32.0000
257 blk.28.attn_output.weight Block 28 Attention Output (W) (~17M) 16777216 4096 x 4096 x 1 x 1 IQ2_XS 2.3125
258 blk.28.attn_q.weight Block 28 Attention Query (W) (~17M) 16777216 4096 x 4096 x 1 x 1 IQ1_M 1.7500
259 blk.28.attn_v.weight Block 28 Attention Value (W) ( ~4M) 4194304 4096 x 1024 x 1 x 1 IQ1_S 1.5625
260 blk.28.ffn_down.weight Block 28 Feed-Forward Network "Down" (W) (~52M) 52428800 12800 x 4096 x 1 x 1 IQ1_M 1.7500
261 blk.28.ffn_gate.weight Block 28 Feed-Forward Network "Gate" (W) (~52M) 52428800 4096 x 12800 x 1 x 1 IQ1_S 1.5625
262 blk.28.ffn_norm.weight Block 28 Feed-Forward Network Normalization (W) ( ~4K) 4096 4096 x 1 x 1 x 1 F32 32.0000
263 blk.28.ffn_up.weight Block 28 Feed-Forward Network "Up" (W) (~52M) 52428800 4096 x 12800 x 1 x 1 IQ1_S 1.5625
  • Total elements in blk.28: (~199M) 199237632
  • Percentage of total elements: 2.27%
  • Bits per Weight (BPW) for blk.28: 1.6960 bits

Block 29 Tensor Group : ~199M Elements

T_ID Tensor Layer Name Human Friendly Tensor Layer Name Elements Shape Type BPW
264 blk.29.attn_k.weight Block 29 Attention Key (W) ( ~4M) 4194304 4096 x 1024 x 1 x 1 IQ1_S 1.5625
265 blk.29.attn_norm.weight Block 29 Attention Normalization (W) ( ~4K) 4096 4096 x 1 x 1 x 1 F32 32.0000
266 blk.29.attn_output.weight Block 29 Attention Output (W) (~17M) 16777216 4096 x 4096 x 1 x 1 IQ2_XS 2.3125
267 blk.29.attn_q.weight Block 29 Attention Query (W) (~17M) 16777216 4096 x 4096 x 1 x 1 IQ1_S 1.5625
268 blk.29.attn_v.weight Block 29 Attention Value (W) ( ~4M) 4194304 4096 x 1024 x 1 x 1 IQ1_S 1.5625
269 blk.29.ffn_down.weight Block 29 Feed-Forward Network "Down" (W) (~52M) 52428800 12800 x 4096 x 1 x 1 IQ1_S 1.5625
270 blk.29.ffn_gate.weight Block 29 Feed-Forward Network "Gate" (W) (~52M) 52428800 4096 x 12800 x 1 x 1 IQ1_S 1.5625
271 blk.29.ffn_norm.weight Block 29 Feed-Forward Network Normalization (W) ( ~4K) 4096 4096 x 1 x 1 x 1 F32 32.0000
272 blk.29.ffn_up.weight Block 29 Feed-Forward Network "Up" (W) (~52M) 52428800 4096 x 12800 x 1 x 1 IQ1_S 1.5625
  • Total elements in blk.29: (~199M) 199237632
  • Percentage of total elements: 2.27%
  • Bits per Weight (BPW) for blk.29: 1.6269 bits

Block 30 Tensor Group : ~199M Elements

T_ID Tensor Layer Name Human Friendly Tensor Layer Name Elements Shape Type BPW
273 blk.30.attn_k.weight Block 30 Attention Key (W) ( ~4M) 4194304 4096 x 1024 x 1 x 1 IQ1_M 1.7500
274 blk.30.attn_norm.weight Block 30 Attention Normalization (W) ( ~4K) 4096 4096 x 1 x 1 x 1 F32 32.0000
275 blk.30.attn_output.weight Block 30 Attention Output (W) (~17M) 16777216 4096 x 4096 x 1 x 1 IQ2_XS 2.3125
276 blk.30.attn_q.weight Block 30 Attention Query (W) (~17M) 16777216 4096 x 4096 x 1 x 1 IQ1_M 1.7500
277 blk.30.attn_v.weight Block 30 Attention Value (W) ( ~4M) 4194304 4096 x 1024 x 1 x 1 IQ1_S 1.5625
278 blk.30.ffn_down.weight Block 30 Feed-Forward Network "Down" (W) (~52M) 52428800 12800 x 4096 x 1 x 1 IQ1_M 1.7500
279 blk.30.ffn_gate.weight Block 30 Feed-Forward Network "Gate" (W) (~52M) 52428800 4096 x 12800 x 1 x 1 IQ1_S 1.5625
280 blk.30.ffn_norm.weight Block 30 Feed-Forward Network Normalization (W) ( ~4K) 4096 4096 x 1 x 1 x 1 F32 32.0000
281 blk.30.ffn_up.weight Block 30 Feed-Forward Network "Up" (W) (~52M) 52428800 4096 x 12800 x 1 x 1 IQ1_S 1.5625
  • Total elements in blk.30: (~199M) 199237632
  • Percentage of total elements: 2.27%
  • Bits per Weight (BPW) for blk.30: 1.6960 bits

Block 31 Tensor Group : ~199M Elements

T_ID Tensor Layer Name Human Friendly Tensor Layer Name Elements Shape Type BPW
282 blk.31.attn_k.weight Block 31 Attention Key (W) ( ~4M) 4194304 4096 x 1024 x 1 x 1 IQ1_S 1.5625
283 blk.31.attn_norm.weight Block 31 Attention Normalization (W) ( ~4K) 4096 4096 x 1 x 1 x 1 F32 32.0000
284 blk.31.attn_output.weight Block 31 Attention Output (W) (~17M) 16777216 4096 x 4096 x 1 x 1 IQ2_S 2.5625
285 blk.31.attn_q.weight Block 31 Attention Query (W) (~17M) 16777216 4096 x 4096 x 1 x 1 IQ1_S 1.5625
286 blk.31.attn_v.weight Block 31 Attention Value (W) ( ~4M) 4194304 4096 x 1024 x 1 x 1 IQ1_S 1.5625
287 blk.31.ffn_down.weight Block 31 Feed-Forward Network "Down" (W) (~52M) 52428800 12800 x 4096 x 1 x 1 IQ1_M 1.7500
288 blk.31.ffn_gate.weight Block 31 Feed-Forward Network "Gate" (W) (~52M) 52428800 4096 x 12800 x 1 x 1 IQ1_S 1.5625
289 blk.31.ffn_norm.weight Block 31 Feed-Forward Network Normalization (W) ( ~4K) 4096 4096 x 1 x 1 x 1 F32 32.0000
290 blk.31.ffn_up.weight Block 31 Feed-Forward Network "Up" (W) (~52M) 52428800 4096 x 12800 x 1 x 1 IQ1_S 1.5625
  • Total elements in blk.31: (~199M) 199237632
  • Percentage of total elements: 2.27%
  • Bits per Weight (BPW) for blk.31: 1.6973 bits

Block 32 Tensor Group : ~199M Elements

T_ID Tensor Layer Name Human Friendly Tensor Layer Name Elements Shape Type BPW
291 blk.32.attn_k.weight Block 32 Attention Key (W) ( ~4M) 4194304 4096 x 1024 x 1 x 1 IQ1_S 1.5625
292 blk.32.attn_norm.weight Block 32 Attention Normalization (W) ( ~4K) 4096 4096 x 1 x 1 x 1 F32 32.0000
293 blk.32.attn_output.weight Block 32 Attention Output (W) (~17M) 16777216 4096 x 4096 x 1 x 1 IQ2_XS 2.3125
294 blk.32.attn_q.weight Block 32 Attention Query (W) (~17M) 16777216 4096 x 4096 x 1 x 1 IQ1_S 1.5625
295 blk.32.attn_v.weight Block 32 Attention Value (W) ( ~4M) 4194304 4096 x 1024 x 1 x 1 IQ1_S 1.5625
296 blk.32.ffn_down.weight Block 32 Feed-Forward Network "Down" (W) (~52M) 52428800 12800 x 4096 x 1 x 1 IQ1_M 1.7500
297 blk.32.ffn_gate.weight Block 32 Feed-Forward Network "Gate" (W) (~52M) 52428800 4096 x 12800 x 1 x 1 IQ1_S 1.5625
298 blk.32.ffn_norm.weight Block 32 Feed-Forward Network Normalization (W) ( ~4K) 4096 4096 x 1 x 1 x 1 F32 32.0000
299 blk.32.ffn_up.weight Block 32 Feed-Forward Network "Up" (W) (~52M) 52428800 4096 x 12800 x 1 x 1 IQ1_S 1.5625
  • Total elements in blk.32: (~199M) 199237632
  • Percentage of total elements: 2.27%
  • Bits per Weight (BPW) for blk.32: 1.6762 bits

Block 33 Tensor Group : ~199M Elements

T_ID Tensor Layer Name Human Friendly Tensor Layer Name Elements Shape Type BPW
300 blk.33.attn_k.weight Block 33 Attention Key (W) ( ~4M) 4194304 4096 x 1024 x 1 x 1 IQ1_S 1.5625
301 blk.33.attn_norm.weight Block 33 Attention Normalization (W) ( ~4K) 4096 4096 x 1 x 1 x 1 F32 32.0000
302 blk.33.attn_output.weight Block 33 Attention Output (W) (~17M) 16777216 4096 x 4096 x 1 x 1 IQ2_S 2.5625
303 blk.33.attn_q.weight Block 33 Attention Query (W) (~17M) 16777216 4096 x 4096 x 1 x 1 IQ1_S 1.5625
304 blk.33.attn_v.weight Block 33 Attention Value (W) ( ~4M) 4194304 4096 x 1024 x 1 x 1 IQ1_S 1.5625
305 blk.33.ffn_down.weight Block 33 Feed-Forward Network "Down" (W) (~52M) 52428800 12800 x 4096 x 1 x 1 IQ1_S 1.5625
306 blk.33.ffn_gate.weight Block 33 Feed-Forward Network "Gate" (W) (~52M) 52428800 4096 x 12800 x 1 x 1 IQ1_S 1.5625
307 blk.33.ffn_norm.weight Block 33 Feed-Forward Network Normalization (W) ( ~4K) 4096 4096 x 1 x 1 x 1 F32 32.0000
308 blk.33.ffn_up.weight Block 33 Feed-Forward Network "Up" (W) (~52M) 52428800 4096 x 12800 x 1 x 1 IQ1_S 1.5625
  • Total elements in blk.33: (~199M) 199237632
  • Percentage of total elements: 2.27%
  • Bits per Weight (BPW) for blk.33: 1.6480 bits

Block 34 Tensor Group : ~199M Elements

T_ID Tensor Layer Name Human Friendly Tensor Layer Name Elements Shape Type BPW
309 blk.34.attn_k.weight Block 34 Attention Key (W) ( ~4M) 4194304 4096 x 1024 x 1 x 1 IQ1_S 1.5625
310 blk.34.attn_norm.weight Block 34 Attention Normalization (W) ( ~4K) 4096 4096 x 1 x 1 x 1 F32 32.0000
311 blk.34.attn_output.weight Block 34 Attention Output (W) (~17M) 16777216 4096 x 4096 x 1 x 1 IQ2_XS 2.3125
312 blk.34.attn_q.weight Block 34 Attention Query (W) (~17M) 16777216 4096 x 4096 x 1 x 1 IQ1_S 1.5625
313 blk.34.attn_v.weight Block 34 Attention Value (W) ( ~4M) 4194304 4096 x 1024 x 1 x 1 IQ1_S 1.5625
314 blk.34.ffn_down.weight Block 34 Feed-Forward Network "Down" (W) (~52M) 52428800 12800 x 4096 x 1 x 1 IQ1_M 1.7500
315 blk.34.ffn_gate.weight Block 34 Feed-Forward Network "Gate" (W) (~52M) 52428800 4096 x 12800 x 1 x 1 IQ1_S 1.5625
316 blk.34.ffn_norm.weight Block 34 Feed-Forward Network Normalization (W) ( ~4K) 4096 4096 x 1 x 1 x 1 F32 32.0000
317 blk.34.ffn_up.weight Block 34 Feed-Forward Network "Up" (W) (~52M) 52428800 4096 x 12800 x 1 x 1 IQ1_S 1.5625
  • Total elements in blk.34: (~199M) 199237632
  • Percentage of total elements: 2.27%
  • Bits per Weight (BPW) for blk.34: 1.6762 bits

Block 35 Tensor Group : ~199M Elements

T_ID Tensor Layer Name Human Friendly Tensor Layer Name Elements Shape Type BPW
318 blk.35.attn_k.weight Block 35 Attention Key (W) ( ~4M) 4194304 4096 x 1024 x 1 x 1 IQ1_S 1.5625
319 blk.35.attn_norm.weight Block 35 Attention Normalization (W) ( ~4K) 4096 4096 x 1 x 1 x 1 F32 32.0000
320 blk.35.attn_output.weight Block 35 Attention Output (W) (~17M) 16777216 4096 x 4096 x 1 x 1 IQ2_S 2.5625
321 blk.35.attn_q.weight Block 35 Attention Query (W) (~17M) 16777216 4096 x 4096 x 1 x 1 IQ1_S 1.5625
322 blk.35.attn_v.weight Block 35 Attention Value (W) ( ~4M) 4194304 4096 x 1024 x 1 x 1 IQ1_S 1.5625
323 blk.35.ffn_down.weight Block 35 Feed-Forward Network "Down" (W) (~52M) 52428800 12800 x 4096 x 1 x 1 IQ1_S 1.5625
324 blk.35.ffn_gate.weight Block 35 Feed-Forward Network "Gate" (W) (~52M) 52428800 4096 x 12800 x 1 x 1 IQ1_S 1.5625
325 blk.35.ffn_norm.weight Block 35 Feed-Forward Network Normalization (W) ( ~4K) 4096 4096 x 1 x 1 x 1 F32 32.0000
326 blk.35.ffn_up.weight Block 35 Feed-Forward Network "Up" (W) (~52M) 52428800 4096 x 12800 x 1 x 1 IQ1_S 1.5625
  • Total elements in blk.35: (~199M) 199237632
  • Percentage of total elements: 2.27%
  • Bits per Weight (BPW) for blk.35: 1.6480 bits

Block 36 Tensor Group : ~199M Elements

T_ID Tensor Layer Name Human Friendly Tensor Layer Name Elements Shape Type BPW
327 blk.36.attn_k.weight Block 36 Attention Key (W) ( ~4M) 4194304 4096 x 1024 x 1 x 1 IQ1_S 1.5625
328 blk.36.attn_norm.weight Block 36 Attention Normalization (W) ( ~4K) 4096 4096 x 1 x 1 x 1 F32 32.0000
329 blk.36.attn_output.weight Block 36 Attention Output (W) (~17M) 16777216 4096 x 4096 x 1 x 1 IQ2_S 2.5625
330 blk.36.attn_q.weight Block 36 Attention Query (W) (~17M) 16777216 4096 x 4096 x 1 x 1 IQ1_S 1.5625
331 blk.36.attn_v.weight Block 36 Attention Value (W) ( ~4M) 4194304 4096 x 1024 x 1 x 1 IQ1_S 1.5625
332 blk.36.ffn_down.weight Block 36 Feed-Forward Network "Down" (W) (~52M) 52428800 12800 x 4096 x 1 x 1 IQ1_S 1.5625
333 blk.36.ffn_gate.weight Block 36 Feed-Forward Network "Gate" (W) (~52M) 52428800 4096 x 12800 x 1 x 1 IQ1_S 1.5625
334 blk.36.ffn_norm.weight Block 36 Feed-Forward Network Normalization (W) ( ~4K) 4096 4096 x 1 x 1 x 1 F32 32.0000
335 blk.36.ffn_up.weight Block 36 Feed-Forward Network "Up" (W) (~52M) 52428800 4096 x 12800 x 1 x 1 IQ1_S 1.5625
  • Total elements in blk.36: (~199M) 199237632
  • Percentage of total elements: 2.27%
  • Bits per Weight (BPW) for blk.36: 1.6480 bits

Block 37 Tensor Group : ~199M Elements

T_ID Tensor Layer Name Human Friendly Tensor Layer Name Elements Shape Type BPW
336 blk.37.attn_k.weight Block 37 Attention Key (W) ( ~4M) 4194304 4096 x 1024 x 1 x 1 IQ1_S 1.5625
337 blk.37.attn_norm.weight Block 37 Attention Normalization (W) ( ~4K) 4096 4096 x 1 x 1 x 1 F32 32.0000
338 blk.37.attn_output.weight Block 37 Attention Output (W) (~17M) 16777216 4096 x 4096 x 1 x 1 IQ2_S 2.5625
339 blk.37.attn_q.weight Block 37 Attention Query (W) (~17M) 16777216 4096 x 4096 x 1 x 1 IQ1_S 1.5625
340 blk.37.attn_v.weight Block 37 Attention Value (W) ( ~4M) 4194304 4096 x 1024 x 1 x 1 IQ1_S 1.5625
341 blk.37.ffn_down.weight Block 37 Feed-Forward Network "Down" (W) (~52M) 52428800 12800 x 4096 x 1 x 1 IQ1_S 1.5625
342 blk.37.ffn_gate.weight Block 37 Feed-Forward Network "Gate" (W) (~52M) 52428800 4096 x 12800 x 1 x 1 IQ1_S 1.5625
343 blk.37.ffn_norm.weight Block 37 Feed-Forward Network Normalization (W) ( ~4K) 4096 4096 x 1 x 1 x 1 F32 32.0000
344 blk.37.ffn_up.weight Block 37 Feed-Forward Network "Up" (W) (~52M) 52428800 4096 x 12800 x 1 x 1 IQ1_S 1.5625
  • Total elements in blk.37: (~199M) 199237632
  • Percentage of total elements: 2.27%
  • Bits per Weight (BPW) for blk.37: 1.6480 bits

Block 38 Tensor Group : ~199M Elements

T_ID Tensor Layer Name Human Friendly Tensor Layer Name Elements Shape Type BPW
345 blk.38.attn_k.weight Block 38 Attention Key (W) ( ~4M) 4194304 4096 x 1024 x 1 x 1 IQ1_S 1.5625
346 blk.38.attn_norm.weight Block 38 Attention Normalization (W) ( ~4K) 4096 4096 x 1 x 1 x 1 F32 32.0000
347 blk.38.attn_output.weight Block 38 Attention Output (W) (~17M) 16777216 4096 x 4096 x 1 x 1 IQ2_S 2.5625
348 blk.38.attn_q.weight Block 38 Attention Query (W) (~17M) 16777216 4096 x 4096 x 1 x 1 IQ1_S 1.5625
349 blk.38.attn_v.weight Block 38 Attention Value (W) ( ~4M) 4194304 4096 x 1024 x 1 x 1 IQ1_S 1.5625
350 blk.38.ffn_down.weight Block 38 Feed-Forward Network "Down" (W) (~52M) 52428800 12800 x 4096 x 1 x 1 IQ1_S 1.5625
351 blk.38.ffn_gate.weight Block 38 Feed-Forward Network "Gate" (W) (~52M) 52428800 4096 x 12800 x 1 x 1 IQ1_S 1.5625
352 blk.38.ffn_norm.weight Block 38 Feed-Forward Network Normalization (W) ( ~4K) 4096 4096 x 1 x 1 x 1 F32 32.0000
353 blk.38.ffn_up.weight Block 38 Feed-Forward Network "Up" (W) (~52M) 52428800 4096 x 12800 x 1 x 1 IQ1_S 1.5625
  • Total elements in blk.38: (~199M) 199237632
  • Percentage of total elements: 2.27%
  • Bits per Weight (BPW) for blk.38: 1.6480 bits

Block 39 Tensor Group : ~199M Elements

T_ID Tensor Layer Name Human Friendly Tensor Layer Name Elements Shape Type BPW
354 blk.39.attn_k.weight Block 39 Attention Key (W) ( ~4M) 4194304 4096 x 1024 x 1 x 1 IQ1_S 1.5625
355 blk.39.attn_norm.weight Block 39 Attention Normalization (W) ( ~4K) 4096 4096 x 1 x 1 x 1 F32 32.0000
356 blk.39.attn_output.weight Block 39 Attention Output (W) (~17M) 16777216 4096 x 4096 x 1 x 1 IQ2_XS 2.3125
357 blk.39.attn_q.weight Block 39 Attention Query (W) (~17M) 16777216 4096 x 4096 x 1 x 1 IQ1_S 1.5625
358 blk.39.attn_v.weight Block 39 Attention Value (W) ( ~4M) 4194304 4096 x 1024 x 1 x 1 IQ1_S 1.5625
359 blk.39.ffn_down.weight Block 39 Feed-Forward Network "Down" (W) (~52M) 52428800 12800 x 4096 x 1 x 1 IQ1_S 1.5625
360 blk.39.ffn_gate.weight Block 39 Feed-Forward Network "Gate" (W) (~52M) 52428800 4096 x 12800 x 1 x 1 IQ1_S 1.5625
361 blk.39.ffn_norm.weight Block 39 Feed-Forward Network Normalization (W) ( ~4K) 4096 4096 x 1 x 1 x 1 F32 32.0000
362 blk.39.ffn_up.weight Block 39 Feed-Forward Network "Up" (W) (~52M) 52428800 4096 x 12800 x 1 x 1 IQ1_S 1.5625
  • Total elements in blk.39: (~199M) 199237632
  • Percentage of total elements: 2.27%
  • Bits per Weight (BPW) for blk.39: 1.6269 bits

Total BPW for granite-4.1-8b-Q1_L.gguf: 1.7500 bits