# gemma-3-12b-it-F16.gguf - GGUF Internal File Dump - Endian: LITTLE endian ## Key Value Metadata Store There are 43 key-value pairs in this file | POS | TYPE | Count | Key | Value | |----:|:----------|-------:|:----------------------------------------|:-----------------------------------------------------------------------| | 1 | UINT32 | 1 | GGUF.version | 3 | | 2 | UINT64 | 1 | GGUF.tensor_count | 626 | | 3 | UINT64 | 1 | GGUF.kv_count | 40 | | 4 | STRING | 1 | general.architecture | `gemma3` | | 5 | STRING | 1 | general.type | `model` | | 6 | STRING | 1 | general.name | `Gemma 3 12b It` | | 7 | STRING | 1 | general.finetune | `it` | | 8 | STRING | 1 | general.basename | `gemma-3` | | 9 | STRING | 1 | general.size_label | `12B` | | 10 | STRING | 1 | general.license | `gemma` | | 11 | UINT32 | 1 | general.base_model.count | 1 | | 12 | STRING | 1 | general.base_model.0.name | `Gemma 3 12b Pt` | | 13 | STRING | 1 | general.base_model.0.organization | `Google` | | 14 | STRING | 1 | general.base_model.0.repo_url | `https://huggingface.co/google/gemma-3-12b-pt` | | 15 | [STRING] | 1 | general.tags | [ `image-text-to-text` ] | | 16 | UINT32 | 1 | gemma3.context_length | 131072 | | 17 | UINT32 | 1 | gemma3.embedding_length | 3840 | | 18 | UINT32 | 1 | gemma3.block_count | 48 | | 19 | UINT32 | 1 | gemma3.feed_forward_length | 15360 | | 20 | UINT32 | 1 | gemma3.attention.head_count | 16 | | 21 | FLOAT32 | 1 | gemma3.attention.layer_norm_rms_epsilon | 1e-06 | | 22 | UINT32 | 1 | gemma3.attention.key_length | 256 | | 23 | UINT32 | 1 | gemma3.attention.value_length | 256 | | 24 | UINT32 | 1 | general.file_type | 1 | | 25 | FLOAT32 | 1 | gemma3.rope.freq_base | 1000000.0 | | 26 | UINT32 | 1 | gemma3.attention.sliding_window | 1024 | | 27 | UINT32 | 1 | gemma3.attention.head_count_kv | 8 | | 28 | STRING | 1 | gemma3.rope.scaling.type | `linear` | | 29 | FLOAT32 | 1 | gemma3.rope.scaling.factor | 8.0 | | 30 | UINT32 | 1 | general.quantization_version | 2 | | 31 | STRING | 1 | tokenizer.ggml.model | `llama` | | 32 | STRING | 1 | tokenizer.ggml.pre | `default` | | 33 | [STRING] | 262144 | tokenizer.ggml.tokens | [ ``, ``, ``, ``, ``, ... ] | | 34 | [FLOAT32] | 262144 | tokenizer.ggml.scores | [ -1000.0, -1000.0, -1000.0, -1000.0, -1000.0, -1000.0, -1000.0, ... ] | | 35 | [INT32] | 262144 | tokenizer.ggml.token_type | [ 3, 3, 3, 3, 3, 4, 3, ... ] | | 36 | UINT32 | 1 | tokenizer.ggml.bos_token_id | 2 | | 37 | UINT32 | 1 | tokenizer.ggml.eos_token_id | 1 | | 38 | UINT32 | 1 | tokenizer.ggml.unknown_token_id | 3 | | 39 | UINT32 | 1 | tokenizer.ggml.padding_token_id | 0 | | 40 | BOOL | 1 | tokenizer.ggml.add_bos_token | True | | 41 | BOOL | 1 | tokenizer.ggml.add_eos_token | False | | 42 | STRING | 1 | tokenizer.chat_template | `{{ bos_token }}{%- if message`...`_turn>model'}}{%- endif -%}` | | 43 | BOOL | 1 | tokenizer.ggml.add_space_prefix | False | ## Tensors Overview ~12B Elements Total number of elements in all tensors: 11765788416 Elements - [gemma-3-12b-it-F16.gguf - GGUF Internal File Dump](#gemma-3-12b-it-f16gguf---gguf-internal-file-dump) - [Key Value Metadata Store](#key-value-metadata-store) - [Tensors Overview ~12B Elements](#tensors-overview-12b-elements) - [Tensor Data Offset](#tensor-data-offset) - [Base Tensor Group : ~1B Elements](#base-tensor-group--1b-elements) - [Block 0 Tensor Group : ~224M Elements](#block-0-tensor-group--224m-elements) - [Block 1 Tensor Group : ~224M Elements](#block-1-tensor-group--224m-elements) - [Block 2 Tensor Group : ~224M Elements](#block-2-tensor-group--224m-elements) - [Block 3 Tensor Group : ~224M Elements](#block-3-tensor-group--224m-elements) - [Block 4 Tensor Group : ~224M Elements](#block-4-tensor-group--224m-elements) - [Block 10 Tensor Group : ~224M Elements](#block-10-tensor-group--224m-elements) - [Block 11 Tensor Group : ~224M Elements](#block-11-tensor-group--224m-elements) - [Block 12 Tensor Group : ~224M Elements](#block-12-tensor-group--224m-elements) - [Block 13 Tensor Group : ~224M Elements](#block-13-tensor-group--224m-elements) - [Block 14 Tensor Group : ~224M Elements](#block-14-tensor-group--224m-elements) - [Block 15 Tensor Group : ~224M Elements](#block-15-tensor-group--224m-elements) - [Block 5 Tensor Group : ~224M Elements](#block-5-tensor-group--224m-elements) - [Block 6 Tensor Group : ~224M Elements](#block-6-tensor-group--224m-elements) - [Block 7 Tensor Group : ~224M Elements](#block-7-tensor-group--224m-elements) - [Block 8 Tensor Group : ~224M Elements](#block-8-tensor-group--224m-elements) - [Block 9 Tensor Group : ~224M Elements](#block-9-tensor-group--224m-elements) - [Block 16 Tensor Group : ~224M Elements](#block-16-tensor-group--224m-elements) - [Block 17 Tensor Group : ~224M Elements](#block-17-tensor-group--224m-elements) - [Block 18 Tensor Group : ~224M Elements](#block-18-tensor-group--224m-elements) - [Block 19 Tensor Group : ~224M Elements](#block-19-tensor-group--224m-elements) - [Block 20 Tensor Group : ~224M Elements](#block-20-tensor-group--224m-elements) - [Block 21 Tensor Group : ~224M Elements](#block-21-tensor-group--224m-elements) - [Block 22 Tensor Group : ~224M Elements](#block-22-tensor-group--224m-elements) - [Block 23 Tensor Group : ~224M Elements](#block-23-tensor-group--224m-elements) - [Block 24 Tensor Group : ~224M Elements](#block-24-tensor-group--224m-elements) - [Block 25 Tensor Group : ~224M Elements](#block-25-tensor-group--224m-elements) - [Block 26 Tensor Group : ~224M Elements](#block-26-tensor-group--224m-elements) - [Block 27 Tensor Group : ~224M Elements](#block-27-tensor-group--224m-elements) - [Block 28 Tensor Group : ~224M Elements](#block-28-tensor-group--224m-elements) - [Block 29 Tensor Group : ~224M Elements](#block-29-tensor-group--224m-elements) - [Block 30 Tensor Group : ~224M Elements](#block-30-tensor-group--224m-elements) - [Block 31 Tensor Group : ~224M Elements](#block-31-tensor-group--224m-elements) - [Block 32 Tensor Group : ~224M Elements](#block-32-tensor-group--224m-elements) - [Block 33 Tensor Group : ~224M Elements](#block-33-tensor-group--224m-elements) - [Block 34 Tensor Group : ~224M Elements](#block-34-tensor-group--224m-elements) - [Block 35 Tensor Group : ~224M Elements](#block-35-tensor-group--224m-elements) - [Block 36 Tensor Group : ~224M Elements](#block-36-tensor-group--224m-elements) - [Block 37 Tensor Group : ~224M Elements](#block-37-tensor-group--224m-elements) - [Block 38 Tensor Group : ~224M Elements](#block-38-tensor-group--224m-elements) - [Block 39 Tensor Group : ~224M Elements](#block-39-tensor-group--224m-elements) - [Block 40 Tensor Group : ~224M Elements](#block-40-tensor-group--224m-elements) - [Block 41 Tensor Group : ~224M Elements](#block-41-tensor-group--224m-elements) - [Block 42 Tensor Group : ~224M Elements](#block-42-tensor-group--224m-elements) - [Block 43 Tensor Group : ~224M Elements](#block-43-tensor-group--224m-elements) - [Block 44 Tensor Group : ~224M Elements](#block-44-tensor-group--224m-elements) - [Block 45 Tensor Group : ~224M Elements](#block-45-tensor-group--224m-elements) - [Block 46 Tensor Group : ~224M Elements](#block-46-tensor-group--224m-elements) - [Block 47 Tensor Group : ~224M Elements](#block-47-tensor-group--224m-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 | token_embd.weight | 0x63f300 | 0x78000000 | | 1 | blk.0.attn_norm.weight | 0x7863f300 | 0x3c00 | | 2 | blk.0.ffn_down.weight | 0x78642f00 | 0x7080000 | | 3 | blk.0.ffn_gate.weight | 0x7f6c2f00 | 0x7080000 | | 4 | blk.0.ffn_up.weight | 0x86742f00 | 0x7080000 | | 5 | blk.0.post_attention_norm.weight | 0x8d7c2f00 | 0x3c00 | | 6 | blk.0.post_ffw_norm.weight | 0x8d7c6b00 | 0x3c00 | | 7 | blk.0.ffn_norm.weight | 0x8d7ca700 | 0x3c00 | | 8 | blk.0.attn_k_norm.weight | 0x8d7ce300 | 0x400 | | 9 | blk.0.attn_k.weight | 0x8d7ce700 | 0xf00000 | | 10 | blk.0.attn_output.weight | 0x8e6ce700 | 0x1e00000 | | 11 | blk.0.attn_q_norm.weight | 0x904ce700 | 0x400 | | 12 | blk.0.attn_q.weight | 0x904ceb00 | 0x1e00000 | | 13 | blk.0.attn_v.weight | 0x922ceb00 | 0xf00000 | | 14 | blk.1.attn_norm.weight | 0x931ceb00 | 0x3c00 | | 15 | blk.1.ffn_down.weight | 0x931d2700 | 0x7080000 | | 16 | blk.1.ffn_gate.weight | 0x9a252700 | 0x7080000 | | 17 | blk.1.ffn_up.weight | 0xa12d2700 | 0x7080000 | | 18 | blk.1.post_attention_norm.weight | 0xa8352700 | 0x3c00 | | 19 | blk.1.post_ffw_norm.weight | 0xa8356300 | 0x3c00 | | 20 | blk.1.ffn_norm.weight | 0xa8359f00 | 0x3c00 | | 21 | blk.1.attn_k_norm.weight | 0xa835db00 | 0x400 | | 22 | blk.1.attn_k.weight | 0xa835df00 | 0xf00000 | | 23 | blk.1.attn_output.weight | 0xa925df00 | 0x1e00000 | | 24 | blk.1.attn_q_norm.weight | 0xab05df00 | 0x400 | | 25 | blk.1.attn_q.weight | 0xab05e300 | 0x1e00000 | | 26 | blk.1.attn_v.weight | 0xace5e300 | 0xf00000 | | 27 | blk.2.attn_norm.weight | 0xadd5e300 | 0x3c00 | | 28 | blk.2.ffn_down.weight | 0xadd61f00 | 0x7080000 | | 29 | blk.2.ffn_gate.weight | 0xb4de1f00 | 0x7080000 | | 30 | blk.2.ffn_up.weight | 0xbbe61f00 | 0x7080000 | | 31 | blk.2.post_attention_norm.weight | 0xc2ee1f00 | 0x3c00 | | 32 | blk.2.post_ffw_norm.weight | 0xc2ee5b00 | 0x3c00 | | 33 | blk.2.ffn_norm.weight | 0xc2ee9700 | 0x3c00 | | 34 | blk.2.attn_k_norm.weight | 0xc2eed300 | 0x400 | | 35 | blk.2.attn_k.weight | 0xc2eed700 | 0xf00000 | | 36 | blk.2.attn_output.weight | 0xc3ded700 | 0x1e00000 | | 37 | blk.2.attn_q_norm.weight | 0xc5bed700 | 0x400 | | 38 | blk.2.attn_q.weight | 0xc5bedb00 | 0x1e00000 | | 39 | blk.2.attn_v.weight | 0xc79edb00 | 0xf00000 | | 40 | blk.3.attn_norm.weight | 0xc88edb00 | 0x3c00 | | 41 | blk.3.ffn_down.weight | 0xc88f1700 | 0x7080000 | | 42 | blk.3.ffn_gate.weight | 0xcf971700 | 0x7080000 | | 43 | blk.3.ffn_up.weight | 0xd69f1700 | 0x7080000 | | 44 | blk.3.post_attention_norm.weight | 0xdda71700 | 0x3c00 | | 45 | blk.3.post_ffw_norm.weight | 0xdda75300 | 0x3c00 | | 46 | blk.3.ffn_norm.weight | 0xdda78f00 | 0x3c00 | | 47 | blk.3.attn_k_norm.weight | 0xdda7cb00 | 0x400 | | 48 | blk.3.attn_k.weight | 0xdda7cf00 | 0xf00000 | | 49 | blk.3.attn_output.weight | 0xde97cf00 | 0x1e00000 | | 50 | blk.3.attn_q_norm.weight | 0xe077cf00 | 0x400 | | 51 | blk.3.attn_q.weight | 0xe077d300 | 0x1e00000 | | 52 | blk.3.attn_v.weight | 0xe257d300 | 0xf00000 | | 53 | blk.4.ffn_gate.weight | 0xe347d300 | 0x7080000 | | 54 | blk.4.ffn_up.weight | 0xea4fd300 | 0x7080000 | | 55 | blk.4.attn_k_norm.weight | 0xf157d300 | 0x400 | | 56 | blk.4.attn_k.weight | 0xf157d700 | 0xf00000 | | 57 | blk.4.attn_output.weight | 0xf247d700 | 0x1e00000 | | 58 | blk.4.attn_q_norm.weight | 0xf427d700 | 0x400 | | 59 | blk.4.attn_q.weight | 0xf427db00 | 0x1e00000 | | 60 | blk.4.attn_v.weight | 0xf607db00 | 0xf00000 | | 61 | blk.10.attn_norm.weight | 0xf6f7db00 | 0x3c00 | | 62 | blk.10.ffn_down.weight | 0xf6f81700 | 0x7080000 | | 63 | blk.10.ffn_gate.weight | 0xfe001700 | 0x7080000 | | 64 | blk.10.ffn_up.weight | 0x105081700 | 0x7080000 | | 65 | blk.10.post_attention_norm.weight | 0x10c101700 | 0x3c00 | | 66 | blk.10.post_ffw_norm.weight | 0x10c105300 | 0x3c00 | | 67 | blk.10.ffn_norm.weight | 0x10c108f00 | 0x3c00 | | 68 | blk.10.attn_k_norm.weight | 0x10c10cb00 | 0x400 | | 69 | blk.10.attn_k.weight | 0x10c10cf00 | 0xf00000 | | 70 | blk.10.attn_output.weight | 0x10d00cf00 | 0x1e00000 | | 71 | blk.10.attn_q_norm.weight | 0x10ee0cf00 | 0x400 | | 72 | blk.10.attn_q.weight | 0x10ee0d300 | 0x1e00000 | | 73 | blk.10.attn_v.weight | 0x110c0d300 | 0xf00000 | | 74 | blk.11.attn_norm.weight | 0x111b0d300 | 0x3c00 | | 75 | blk.11.ffn_down.weight | 0x111b10f00 | 0x7080000 | | 76 | blk.11.ffn_gate.weight | 0x118b90f00 | 0x7080000 | | 77 | blk.11.ffn_up.weight | 0x11fc10f00 | 0x7080000 | | 78 | blk.11.post_attention_norm.weight | 0x126c90f00 | 0x3c00 | | 79 | blk.11.post_ffw_norm.weight | 0x126c94b00 | 0x3c00 | | 80 | blk.11.ffn_norm.weight | 0x126c98700 | 0x3c00 | | 81 | blk.11.attn_k_norm.weight | 0x126c9c300 | 0x400 | | 82 | blk.11.attn_k.weight | 0x126c9c700 | 0xf00000 | | 83 | blk.11.attn_output.weight | 0x127b9c700 | 0x1e00000 | | 84 | blk.11.attn_q_norm.weight | 0x12999c700 | 0x400 | | 85 | blk.11.attn_q.weight | 0x12999cb00 | 0x1e00000 | | 86 | blk.11.attn_v.weight | 0x12b79cb00 | 0xf00000 | | 87 | blk.12.attn_norm.weight | 0x12c69cb00 | 0x3c00 | | 88 | blk.12.ffn_down.weight | 0x12c6a0700 | 0x7080000 | | 89 | blk.12.ffn_gate.weight | 0x133720700 | 0x7080000 | | 90 | blk.12.ffn_up.weight | 0x13a7a0700 | 0x7080000 | | 91 | blk.12.post_attention_norm.weight | 0x141820700 | 0x3c00 | | 92 | blk.12.post_ffw_norm.weight | 0x141824300 | 0x3c00 | | 93 | blk.12.ffn_norm.weight | 0x141827f00 | 0x3c00 | | 94 | blk.12.attn_k_norm.weight | 0x14182bb00 | 0x400 | | 95 | blk.12.attn_k.weight | 0x14182bf00 | 0xf00000 | | 96 | blk.12.attn_output.weight | 0x14272bf00 | 0x1e00000 | | 97 | blk.12.attn_q_norm.weight | 0x14452bf00 | 0x400 | | 98 | blk.12.attn_q.weight | 0x14452c300 | 0x1e00000 | | 99 | blk.12.attn_v.weight | 0x14632c300 | 0xf00000 | | 100 | blk.13.attn_norm.weight | 0x14722c300 | 0x3c00 | | 101 | blk.13.ffn_down.weight | 0x14722ff00 | 0x7080000 | | 102 | blk.13.ffn_gate.weight | 0x14e2aff00 | 0x7080000 | | 103 | blk.13.ffn_up.weight | 0x15532ff00 | 0x7080000 | | 104 | blk.13.post_attention_norm.weight | 0x15c3aff00 | 0x3c00 | | 105 | blk.13.post_ffw_norm.weight | 0x15c3b3b00 | 0x3c00 | | 106 | blk.13.ffn_norm.weight | 0x15c3b7700 | 0x3c00 | | 107 | blk.13.attn_k_norm.weight | 0x15c3bb300 | 0x400 | | 108 | blk.13.attn_k.weight | 0x15c3bb700 | 0xf00000 | | 109 | blk.13.attn_output.weight | 0x15d2bb700 | 0x1e00000 | | 110 | blk.13.attn_q_norm.weight | 0x15f0bb700 | 0x400 | | 111 | blk.13.attn_q.weight | 0x15f0bbb00 | 0x1e00000 | | 112 | blk.13.attn_v.weight | 0x160ebbb00 | 0xf00000 | | 113 | blk.14.attn_norm.weight | 0x161dbbb00 | 0x3c00 | | 114 | blk.14.ffn_down.weight | 0x161dbf700 | 0x7080000 | | 115 | blk.14.ffn_gate.weight | 0x168e3f700 | 0x7080000 | | 116 | blk.14.ffn_up.weight | 0x16febf700 | 0x7080000 | | 117 | blk.14.post_attention_norm.weight | 0x176f3f700 | 0x3c00 | | 118 | blk.14.post_ffw_norm.weight | 0x176f43300 | 0x3c00 | | 119 | blk.14.ffn_norm.weight | 0x176f46f00 | 0x3c00 | | 120 | blk.14.attn_k_norm.weight | 0x176f4ab00 | 0x400 | | 121 | blk.14.attn_k.weight | 0x176f4af00 | 0xf00000 | | 122 | blk.14.attn_output.weight | 0x177e4af00 | 0x1e00000 | | 123 | blk.14.attn_q_norm.weight | 0x179c4af00 | 0x400 | | 124 | blk.14.attn_q.weight | 0x179c4b300 | 0x1e00000 | | 125 | blk.14.attn_v.weight | 0x17ba4b300 | 0xf00000 | | 126 | blk.15.ffn_gate.weight | 0x17c94b300 | 0x7080000 | | 127 | blk.15.ffn_up.weight | 0x1839cb300 | 0x7080000 | | 128 | blk.15.attn_k_norm.weight | 0x18aa4b300 | 0x400 | | 129 | blk.15.attn_k.weight | 0x18aa4b700 | 0xf00000 | | 130 | blk.15.attn_output.weight | 0x18b94b700 | 0x1e00000 | | 131 | blk.15.attn_q_norm.weight | 0x18d74b700 | 0x400 | | 132 | blk.15.attn_q.weight | 0x18d74bb00 | 0x1e00000 | | 133 | blk.15.attn_v.weight | 0x18f54bb00 | 0xf00000 | | 134 | blk.4.attn_norm.weight | 0x19044bb00 | 0x3c00 | | 135 | blk.4.ffn_down.weight | 0x19044f700 | 0x7080000 | | 136 | blk.4.post_attention_norm.weight | 0x1974cf700 | 0x3c00 | | 137 | blk.4.post_ffw_norm.weight | 0x1974d3300 | 0x3c00 | | 138 | blk.4.ffn_norm.weight | 0x1974d6f00 | 0x3c00 | | 139 | blk.5.attn_norm.weight | 0x1974dab00 | 0x3c00 | | 140 | blk.5.ffn_down.weight | 0x1974de700 | 0x7080000 | | 141 | blk.5.ffn_gate.weight | 0x19e55e700 | 0x7080000 | | 142 | blk.5.ffn_up.weight | 0x1a55de700 | 0x7080000 | | 143 | blk.5.post_attention_norm.weight | 0x1ac65e700 | 0x3c00 | | 144 | blk.5.post_ffw_norm.weight | 0x1ac662300 | 0x3c00 | | 145 | blk.5.ffn_norm.weight | 0x1ac665f00 | 0x3c00 | | 146 | blk.5.attn_k_norm.weight | 0x1ac669b00 | 0x400 | | 147 | blk.5.attn_k.weight | 0x1ac669f00 | 0xf00000 | | 148 | blk.5.attn_output.weight | 0x1ad569f00 | 0x1e00000 | | 149 | blk.5.attn_q_norm.weight | 0x1af369f00 | 0x400 | | 150 | blk.5.attn_q.weight | 0x1af36a300 | 0x1e00000 | | 151 | blk.5.attn_v.weight | 0x1b116a300 | 0xf00000 | | 152 | blk.6.attn_norm.weight | 0x1b206a300 | 0x3c00 | | 153 | blk.6.ffn_down.weight | 0x1b206df00 | 0x7080000 | | 154 | blk.6.ffn_gate.weight | 0x1b90edf00 | 0x7080000 | | 155 | blk.6.ffn_up.weight | 0x1c016df00 | 0x7080000 | | 156 | blk.6.post_attention_norm.weight | 0x1c71edf00 | 0x3c00 | | 157 | blk.6.post_ffw_norm.weight | 0x1c71f1b00 | 0x3c00 | | 158 | blk.6.ffn_norm.weight | 0x1c71f5700 | 0x3c00 | | 159 | blk.6.attn_k_norm.weight | 0x1c71f9300 | 0x400 | | 160 | blk.6.attn_k.weight | 0x1c71f9700 | 0xf00000 | | 161 | blk.6.attn_output.weight | 0x1c80f9700 | 0x1e00000 | | 162 | blk.6.attn_q_norm.weight | 0x1c9ef9700 | 0x400 | | 163 | blk.6.attn_q.weight | 0x1c9ef9b00 | 0x1e00000 | | 164 | blk.6.attn_v.weight | 0x1cbcf9b00 | 0xf00000 | | 165 | blk.7.attn_norm.weight | 0x1ccbf9b00 | 0x3c00 | | 166 | blk.7.ffn_down.weight | 0x1ccbfd700 | 0x7080000 | | 167 | blk.7.ffn_gate.weight | 0x1d3c7d700 | 0x7080000 | | 168 | blk.7.ffn_up.weight | 0x1dacfd700 | 0x7080000 | | 169 | blk.7.post_attention_norm.weight | 0x1e1d7d700 | 0x3c00 | | 170 | blk.7.post_ffw_norm.weight | 0x1e1d81300 | 0x3c00 | | 171 | blk.7.ffn_norm.weight | 0x1e1d84f00 | 0x3c00 | | 172 | blk.7.attn_k_norm.weight | 0x1e1d88b00 | 0x400 | | 173 | blk.7.attn_k.weight | 0x1e1d88f00 | 0xf00000 | | 174 | blk.7.attn_output.weight | 0x1e2c88f00 | 0x1e00000 | | 175 | blk.7.attn_q_norm.weight | 0x1e4a88f00 | 0x400 | | 176 | blk.7.attn_q.weight | 0x1e4a89300 | 0x1e00000 | | 177 | blk.7.attn_v.weight | 0x1e6889300 | 0xf00000 | | 178 | blk.8.attn_norm.weight | 0x1e7789300 | 0x3c00 | | 179 | blk.8.ffn_down.weight | 0x1e778cf00 | 0x7080000 | | 180 | blk.8.ffn_gate.weight | 0x1ee80cf00 | 0x7080000 | | 181 | blk.8.ffn_up.weight | 0x1f588cf00 | 0x7080000 | | 182 | blk.8.post_attention_norm.weight | 0x1fc90cf00 | 0x3c00 | | 183 | blk.8.post_ffw_norm.weight | 0x1fc910b00 | 0x3c00 | | 184 | blk.8.ffn_norm.weight | 0x1fc914700 | 0x3c00 | | 185 | blk.8.attn_k_norm.weight | 0x1fc918300 | 0x400 | | 186 | blk.8.attn_k.weight | 0x1fc918700 | 0xf00000 | | 187 | blk.8.attn_output.weight | 0x1fd818700 | 0x1e00000 | | 188 | blk.8.attn_q_norm.weight | 0x1ff618700 | 0x400 | | 189 | blk.8.attn_q.weight | 0x1ff618b00 | 0x1e00000 | | 190 | blk.8.attn_v.weight | 0x201418b00 | 0xf00000 | | 191 | blk.9.attn_norm.weight | 0x202318b00 | 0x3c00 | | 192 | blk.9.ffn_down.weight | 0x20231c700 | 0x7080000 | | 193 | blk.9.ffn_gate.weight | 0x20939c700 | 0x7080000 | | 194 | blk.9.ffn_up.weight | 0x21041c700 | 0x7080000 | | 195 | blk.9.post_attention_norm.weight | 0x21749c700 | 0x3c00 | | 196 | blk.9.post_ffw_norm.weight | 0x2174a0300 | 0x3c00 | | 197 | blk.9.ffn_norm.weight | 0x2174a3f00 | 0x3c00 | | 198 | blk.9.attn_k_norm.weight | 0x2174a7b00 | 0x400 | | 199 | blk.9.attn_k.weight | 0x2174a7f00 | 0xf00000 | | 200 | blk.9.attn_output.weight | 0x2183a7f00 | 0x1e00000 | | 201 | blk.9.attn_q_norm.weight | 0x21a1a7f00 | 0x400 | | 202 | blk.9.attn_q.weight | 0x21a1a8300 | 0x1e00000 | | 203 | blk.9.attn_v.weight | 0x21bfa8300 | 0xf00000 | | 204 | blk.15.attn_norm.weight | 0x21cea8300 | 0x3c00 | | 205 | blk.15.ffn_down.weight | 0x21ceabf00 | 0x7080000 | | 206 | blk.15.post_attention_norm.weight | 0x223f2bf00 | 0x3c00 | | 207 | blk.15.post_ffw_norm.weight | 0x223f2fb00 | 0x3c00 | | 208 | blk.15.ffn_norm.weight | 0x223f33700 | 0x3c00 | | 209 | blk.16.attn_norm.weight | 0x223f37300 | 0x3c00 | | 210 | blk.16.ffn_down.weight | 0x223f3af00 | 0x7080000 | | 211 | blk.16.ffn_gate.weight | 0x22afbaf00 | 0x7080000 | | 212 | blk.16.ffn_up.weight | 0x23203af00 | 0x7080000 | | 213 | blk.16.post_attention_norm.weight | 0x2390baf00 | 0x3c00 | | 214 | blk.16.post_ffw_norm.weight | 0x2390beb00 | 0x3c00 | | 215 | blk.16.ffn_norm.weight | 0x2390c2700 | 0x3c00 | | 216 | blk.16.attn_k_norm.weight | 0x2390c6300 | 0x400 | | 217 | blk.16.attn_k.weight | 0x2390c6700 | 0xf00000 | | 218 | blk.16.attn_output.weight | 0x239fc6700 | 0x1e00000 | | 219 | blk.16.attn_q_norm.weight | 0x23bdc6700 | 0x400 | | 220 | blk.16.attn_q.weight | 0x23bdc6b00 | 0x1e00000 | | 221 | blk.16.attn_v.weight | 0x23dbc6b00 | 0xf00000 | | 222 | blk.17.attn_norm.weight | 0x23eac6b00 | 0x3c00 | | 223 | blk.17.ffn_down.weight | 0x23eaca700 | 0x7080000 | | 224 | blk.17.ffn_gate.weight | 0x245b4a700 | 0x7080000 | | 225 | blk.17.ffn_up.weight | 0x24cbca700 | 0x7080000 | | 226 | blk.17.post_attention_norm.weight | 0x253c4a700 | 0x3c00 | | 227 | blk.17.post_ffw_norm.weight | 0x253c4e300 | 0x3c00 | | 228 | blk.17.ffn_norm.weight | 0x253c51f00 | 0x3c00 | | 229 | blk.17.attn_k_norm.weight | 0x253c55b00 | 0x400 | | 230 | blk.17.attn_k.weight | 0x253c55f00 | 0xf00000 | | 231 | blk.17.attn_output.weight | 0x254b55f00 | 0x1e00000 | | 232 | blk.17.attn_q_norm.weight | 0x256955f00 | 0x400 | | 233 | blk.17.attn_q.weight | 0x256956300 | 0x1e00000 | | 234 | blk.17.attn_v.weight | 0x258756300 | 0xf00000 | | 235 | blk.18.attn_norm.weight | 0x259656300 | 0x3c00 | | 236 | blk.18.ffn_down.weight | 0x259659f00 | 0x7080000 | | 237 | blk.18.ffn_gate.weight | 0x2606d9f00 | 0x7080000 | | 238 | blk.18.ffn_up.weight | 0x267759f00 | 0x7080000 | | 239 | blk.18.post_attention_norm.weight | 0x26e7d9f00 | 0x3c00 | | 240 | blk.18.post_ffw_norm.weight | 0x26e7ddb00 | 0x3c00 | | 241 | blk.18.ffn_norm.weight | 0x26e7e1700 | 0x3c00 | | 242 | blk.18.attn_k_norm.weight | 0x26e7e5300 | 0x400 | | 243 | blk.18.attn_k.weight | 0x26e7e5700 | 0xf00000 | | 244 | blk.18.attn_output.weight | 0x26f6e5700 | 0x1e00000 | | 245 | blk.18.attn_q_norm.weight | 0x2714e5700 | 0x400 | | 246 | blk.18.attn_q.weight | 0x2714e5b00 | 0x1e00000 | | 247 | blk.18.attn_v.weight | 0x2732e5b00 | 0xf00000 | | 248 | blk.19.attn_norm.weight | 0x2741e5b00 | 0x3c00 | | 249 | blk.19.ffn_down.weight | 0x2741e9700 | 0x7080000 | | 250 | blk.19.ffn_gate.weight | 0x27b269700 | 0x7080000 | | 251 | blk.19.ffn_up.weight | 0x2822e9700 | 0x7080000 | | 252 | blk.19.post_attention_norm.weight | 0x289369700 | 0x3c00 | | 253 | blk.19.post_ffw_norm.weight | 0x28936d300 | 0x3c00 | | 254 | blk.19.ffn_norm.weight | 0x289370f00 | 0x3c00 | | 255 | blk.19.attn_k_norm.weight | 0x289374b00 | 0x400 | | 256 | blk.19.attn_k.weight | 0x289374f00 | 0xf00000 | | 257 | blk.19.attn_output.weight | 0x28a274f00 | 0x1e00000 | | 258 | blk.19.attn_q_norm.weight | 0x28c074f00 | 0x400 | | 259 | blk.19.attn_q.weight | 0x28c075300 | 0x1e00000 | | 260 | blk.19.attn_v.weight | 0x28de75300 | 0xf00000 | | 261 | blk.20.attn_norm.weight | 0x28ed75300 | 0x3c00 | | 262 | blk.20.ffn_down.weight | 0x28ed78f00 | 0x7080000 | | 263 | blk.20.ffn_gate.weight | 0x295df8f00 | 0x7080000 | | 264 | blk.20.ffn_up.weight | 0x29ce78f00 | 0x7080000 | | 265 | blk.20.post_attention_norm.weight | 0x2a3ef8f00 | 0x3c00 | | 266 | blk.20.post_ffw_norm.weight | 0x2a3efcb00 | 0x3c00 | | 267 | blk.20.ffn_norm.weight | 0x2a3f00700 | 0x3c00 | | 268 | blk.20.attn_k_norm.weight | 0x2a3f04300 | 0x400 | | 269 | blk.20.attn_k.weight | 0x2a3f04700 | 0xf00000 | | 270 | blk.20.attn_output.weight | 0x2a4e04700 | 0x1e00000 | | 271 | blk.20.attn_q_norm.weight | 0x2a6c04700 | 0x400 | | 272 | blk.20.attn_q.weight | 0x2a6c04b00 | 0x1e00000 | | 273 | blk.20.attn_v.weight | 0x2a8a04b00 | 0xf00000 | | 274 | blk.21.attn_norm.weight | 0x2a9904b00 | 0x3c00 | | 275 | blk.21.ffn_down.weight | 0x2a9908700 | 0x7080000 | | 276 | blk.21.ffn_gate.weight | 0x2b0988700 | 0x7080000 | | 277 | blk.21.ffn_up.weight | 0x2b7a08700 | 0x7080000 | | 278 | blk.21.post_attention_norm.weight | 0x2bea88700 | 0x3c00 | | 279 | blk.21.post_ffw_norm.weight | 0x2bea8c300 | 0x3c00 | | 280 | blk.21.ffn_norm.weight | 0x2bea8ff00 | 0x3c00 | | 281 | blk.21.attn_k_norm.weight | 0x2bea93b00 | 0x400 | | 282 | blk.21.attn_k.weight | 0x2bea93f00 | 0xf00000 | | 283 | blk.21.attn_output.weight | 0x2bf993f00 | 0x1e00000 | | 284 | blk.21.attn_q_norm.weight | 0x2c1793f00 | 0x400 | | 285 | blk.21.attn_q.weight | 0x2c1794300 | 0x1e00000 | | 286 | blk.21.attn_v.weight | 0x2c3594300 | 0xf00000 | | 287 | blk.22.attn_norm.weight | 0x2c4494300 | 0x3c00 | | 288 | blk.22.ffn_down.weight | 0x2c4497f00 | 0x7080000 | | 289 | blk.22.ffn_gate.weight | 0x2cb517f00 | 0x7080000 | | 290 | blk.22.ffn_up.weight | 0x2d2597f00 | 0x7080000 | | 291 | blk.22.post_attention_norm.weight | 0x2d9617f00 | 0x3c00 | | 292 | blk.22.post_ffw_norm.weight | 0x2d961bb00 | 0x3c00 | | 293 | blk.22.ffn_norm.weight | 0x2d961f700 | 0x3c00 | | 294 | blk.22.attn_k_norm.weight | 0x2d9623300 | 0x400 | | 295 | blk.22.attn_k.weight | 0x2d9623700 | 0xf00000 | | 296 | blk.22.attn_output.weight | 0x2da523700 | 0x1e00000 | | 297 | blk.22.attn_q_norm.weight | 0x2dc323700 | 0x400 | | 298 | blk.22.attn_q.weight | 0x2dc323b00 | 0x1e00000 | | 299 | blk.22.attn_v.weight | 0x2de123b00 | 0xf00000 | | 300 | blk.23.attn_norm.weight | 0x2df023b00 | 0x3c00 | | 301 | blk.23.ffn_down.weight | 0x2df027700 | 0x7080000 | | 302 | blk.23.ffn_gate.weight | 0x2e60a7700 | 0x7080000 | | 303 | blk.23.ffn_up.weight | 0x2ed127700 | 0x7080000 | | 304 | blk.23.post_attention_norm.weight | 0x2f41a7700 | 0x3c00 | | 305 | blk.23.post_ffw_norm.weight | 0x2f41ab300 | 0x3c00 | | 306 | blk.23.ffn_norm.weight | 0x2f41aef00 | 0x3c00 | | 307 | blk.23.attn_k_norm.weight | 0x2f41b2b00 | 0x400 | | 308 | blk.23.attn_k.weight | 0x2f41b2f00 | 0xf00000 | | 309 | blk.23.attn_output.weight | 0x2f50b2f00 | 0x1e00000 | | 310 | blk.23.attn_q_norm.weight | 0x2f6eb2f00 | 0x400 | | 311 | blk.23.attn_q.weight | 0x2f6eb3300 | 0x1e00000 | | 312 | blk.23.attn_v.weight | 0x2f8cb3300 | 0xf00000 | | 313 | blk.24.attn_norm.weight | 0x2f9bb3300 | 0x3c00 | | 314 | blk.24.ffn_down.weight | 0x2f9bb6f00 | 0x7080000 | | 315 | blk.24.ffn_gate.weight | 0x300c36f00 | 0x7080000 | | 316 | blk.24.ffn_up.weight | 0x307cb6f00 | 0x7080000 | | 317 | blk.24.post_attention_norm.weight | 0x30ed36f00 | 0x3c00 | | 318 | blk.24.post_ffw_norm.weight | 0x30ed3ab00 | 0x3c00 | | 319 | blk.24.ffn_norm.weight | 0x30ed3e700 | 0x3c00 | | 320 | blk.24.attn_k_norm.weight | 0x30ed42300 | 0x400 | | 321 | blk.24.attn_k.weight | 0x30ed42700 | 0xf00000 | | 322 | blk.24.attn_output.weight | 0x30fc42700 | 0x1e00000 | | 323 | blk.24.attn_q_norm.weight | 0x311a42700 | 0x400 | | 324 | blk.24.attn_q.weight | 0x311a42b00 | 0x1e00000 | | 325 | blk.24.attn_v.weight | 0x313842b00 | 0xf00000 | | 326 | blk.25.attn_norm.weight | 0x314742b00 | 0x3c00 | | 327 | blk.25.ffn_down.weight | 0x314746700 | 0x7080000 | | 328 | blk.25.ffn_gate.weight | 0x31b7c6700 | 0x7080000 | | 329 | blk.25.ffn_up.weight | 0x322846700 | 0x7080000 | | 330 | blk.25.post_attention_norm.weight | 0x3298c6700 | 0x3c00 | | 331 | blk.25.post_ffw_norm.weight | 0x3298ca300 | 0x3c00 | | 332 | blk.25.ffn_norm.weight | 0x3298cdf00 | 0x3c00 | | 333 | blk.25.attn_k_norm.weight | 0x3298d1b00 | 0x400 | | 334 | blk.25.attn_k.weight | 0x3298d1f00 | 0xf00000 | | 335 | blk.25.attn_output.weight | 0x32a7d1f00 | 0x1e00000 | | 336 | blk.25.attn_q_norm.weight | 0x32c5d1f00 | 0x400 | | 337 | blk.25.attn_q.weight | 0x32c5d2300 | 0x1e00000 | | 338 | blk.25.attn_v.weight | 0x32e3d2300 | 0xf00000 | | 339 | blk.26.ffn_gate.weight | 0x32f2d2300 | 0x7080000 | | 340 | blk.26.ffn_up.weight | 0x336352300 | 0x7080000 | | 341 | blk.26.attn_k_norm.weight | 0x33d3d2300 | 0x400 | | 342 | blk.26.attn_k.weight | 0x33d3d2700 | 0xf00000 | | 343 | blk.26.attn_output.weight | 0x33e2d2700 | 0x1e00000 | | 344 | blk.26.attn_q_norm.weight | 0x3400d2700 | 0x400 | | 345 | blk.26.attn_q.weight | 0x3400d2b00 | 0x1e00000 | | 346 | blk.26.attn_v.weight | 0x341ed2b00 | 0xf00000 | | 347 | blk.26.attn_norm.weight | 0x342dd2b00 | 0x3c00 | | 348 | blk.26.ffn_down.weight | 0x342dd6700 | 0x7080000 | | 349 | blk.26.post_attention_norm.weight | 0x349e56700 | 0x3c00 | | 350 | blk.26.post_ffw_norm.weight | 0x349e5a300 | 0x3c00 | | 351 | blk.26.ffn_norm.weight | 0x349e5df00 | 0x3c00 | | 352 | blk.27.attn_norm.weight | 0x349e61b00 | 0x3c00 | | 353 | blk.27.ffn_down.weight | 0x349e65700 | 0x7080000 | | 354 | blk.27.ffn_gate.weight | 0x350ee5700 | 0x7080000 | | 355 | blk.27.ffn_up.weight | 0x357f65700 | 0x7080000 | | 356 | blk.27.post_attention_norm.weight | 0x35efe5700 | 0x3c00 | | 357 | blk.27.post_ffw_norm.weight | 0x35efe9300 | 0x3c00 | | 358 | blk.27.ffn_norm.weight | 0x35efecf00 | 0x3c00 | | 359 | blk.27.attn_k_norm.weight | 0x35eff0b00 | 0x400 | | 360 | blk.27.attn_k.weight | 0x35eff0f00 | 0xf00000 | | 361 | blk.27.attn_output.weight | 0x35fef0f00 | 0x1e00000 | | 362 | blk.27.attn_q_norm.weight | 0x361cf0f00 | 0x400 | | 363 | blk.27.attn_q.weight | 0x361cf1300 | 0x1e00000 | | 364 | blk.27.attn_v.weight | 0x363af1300 | 0xf00000 | | 365 | blk.28.attn_norm.weight | 0x3649f1300 | 0x3c00 | | 366 | blk.28.ffn_down.weight | 0x3649f4f00 | 0x7080000 | | 367 | blk.28.ffn_gate.weight | 0x36ba74f00 | 0x7080000 | | 368 | blk.28.ffn_up.weight | 0x372af4f00 | 0x7080000 | | 369 | blk.28.post_attention_norm.weight | 0x379b74f00 | 0x3c00 | | 370 | blk.28.post_ffw_norm.weight | 0x379b78b00 | 0x3c00 | | 371 | blk.28.ffn_norm.weight | 0x379b7c700 | 0x3c00 | | 372 | blk.28.attn_k_norm.weight | 0x379b80300 | 0x400 | | 373 | blk.28.attn_k.weight | 0x379b80700 | 0xf00000 | | 374 | blk.28.attn_output.weight | 0x37aa80700 | 0x1e00000 | | 375 | blk.28.attn_q_norm.weight | 0x37c880700 | 0x400 | | 376 | blk.28.attn_q.weight | 0x37c880b00 | 0x1e00000 | | 377 | blk.28.attn_v.weight | 0x37e680b00 | 0xf00000 | | 378 | blk.29.attn_norm.weight | 0x37f580b00 | 0x3c00 | | 379 | blk.29.ffn_down.weight | 0x37f584700 | 0x7080000 | | 380 | blk.29.ffn_gate.weight | 0x386604700 | 0x7080000 | | 381 | blk.29.ffn_up.weight | 0x38d684700 | 0x7080000 | | 382 | blk.29.post_attention_norm.weight | 0x394704700 | 0x3c00 | | 383 | blk.29.post_ffw_norm.weight | 0x394708300 | 0x3c00 | | 384 | blk.29.ffn_norm.weight | 0x39470bf00 | 0x3c00 | | 385 | blk.29.attn_k_norm.weight | 0x39470fb00 | 0x400 | | 386 | blk.29.attn_k.weight | 0x39470ff00 | 0xf00000 | | 387 | blk.29.attn_output.weight | 0x39560ff00 | 0x1e00000 | | 388 | blk.29.attn_q_norm.weight | 0x39740ff00 | 0x400 | | 389 | blk.29.attn_q.weight | 0x397410300 | 0x1e00000 | | 390 | blk.29.attn_v.weight | 0x399210300 | 0xf00000 | | 391 | blk.30.attn_norm.weight | 0x39a110300 | 0x3c00 | | 392 | blk.30.ffn_down.weight | 0x39a113f00 | 0x7080000 | | 393 | blk.30.ffn_gate.weight | 0x3a1193f00 | 0x7080000 | | 394 | blk.30.ffn_up.weight | 0x3a8213f00 | 0x7080000 | | 395 | blk.30.post_attention_norm.weight | 0x3af293f00 | 0x3c00 | | 396 | blk.30.post_ffw_norm.weight | 0x3af297b00 | 0x3c00 | | 397 | blk.30.ffn_norm.weight | 0x3af29b700 | 0x3c00 | | 398 | blk.30.attn_k_norm.weight | 0x3af29f300 | 0x400 | | 399 | blk.30.attn_k.weight | 0x3af29f700 | 0xf00000 | | 400 | blk.30.attn_output.weight | 0x3b019f700 | 0x1e00000 | | 401 | blk.30.attn_q_norm.weight | 0x3b1f9f700 | 0x400 | | 402 | blk.30.attn_q.weight | 0x3b1f9fb00 | 0x1e00000 | | 403 | blk.30.attn_v.weight | 0x3b3d9fb00 | 0xf00000 | | 404 | blk.31.attn_norm.weight | 0x3b4c9fb00 | 0x3c00 | | 405 | blk.31.ffn_down.weight | 0x3b4ca3700 | 0x7080000 | | 406 | blk.31.ffn_gate.weight | 0x3bbd23700 | 0x7080000 | | 407 | blk.31.ffn_up.weight | 0x3c2da3700 | 0x7080000 | | 408 | blk.31.post_attention_norm.weight | 0x3c9e23700 | 0x3c00 | | 409 | blk.31.post_ffw_norm.weight | 0x3c9e27300 | 0x3c00 | | 410 | blk.31.ffn_norm.weight | 0x3c9e2af00 | 0x3c00 | | 411 | blk.31.attn_k_norm.weight | 0x3c9e2eb00 | 0x400 | | 412 | blk.31.attn_k.weight | 0x3c9e2ef00 | 0xf00000 | | 413 | blk.31.attn_output.weight | 0x3cad2ef00 | 0x1e00000 | | 414 | blk.31.attn_q_norm.weight | 0x3ccb2ef00 | 0x400 | | 415 | blk.31.attn_q.weight | 0x3ccb2f300 | 0x1e00000 | | 416 | blk.31.attn_v.weight | 0x3ce92f300 | 0xf00000 | | 417 | blk.32.attn_norm.weight | 0x3cf82f300 | 0x3c00 | | 418 | blk.32.ffn_down.weight | 0x3cf832f00 | 0x7080000 | | 419 | blk.32.ffn_gate.weight | 0x3d68b2f00 | 0x7080000 | | 420 | blk.32.ffn_up.weight | 0x3dd932f00 | 0x7080000 | | 421 | blk.32.post_attention_norm.weight | 0x3e49b2f00 | 0x3c00 | | 422 | blk.32.post_ffw_norm.weight | 0x3e49b6b00 | 0x3c00 | | 423 | blk.32.ffn_norm.weight | 0x3e49ba700 | 0x3c00 | | 424 | blk.32.attn_k_norm.weight | 0x3e49be300 | 0x400 | | 425 | blk.32.attn_k.weight | 0x3e49be700 | 0xf00000 | | 426 | blk.32.attn_output.weight | 0x3e58be700 | 0x1e00000 | | 427 | blk.32.attn_q_norm.weight | 0x3e76be700 | 0x400 | | 428 | blk.32.attn_q.weight | 0x3e76beb00 | 0x1e00000 | | 429 | blk.32.attn_v.weight | 0x3e94beb00 | 0xf00000 | | 430 | blk.33.attn_norm.weight | 0x3ea3beb00 | 0x3c00 | | 431 | blk.33.ffn_down.weight | 0x3ea3c2700 | 0x7080000 | | 432 | blk.33.ffn_gate.weight | 0x3f1442700 | 0x7080000 | | 433 | blk.33.ffn_up.weight | 0x3f84c2700 | 0x7080000 | | 434 | blk.33.post_attention_norm.weight | 0x3ff542700 | 0x3c00 | | 435 | blk.33.post_ffw_norm.weight | 0x3ff546300 | 0x3c00 | | 436 | blk.33.ffn_norm.weight | 0x3ff549f00 | 0x3c00 | | 437 | blk.33.attn_k_norm.weight | 0x3ff54db00 | 0x400 | | 438 | blk.33.attn_k.weight | 0x3ff54df00 | 0xf00000 | | 439 | blk.33.attn_output.weight | 0x40044df00 | 0x1e00000 | | 440 | blk.33.attn_q_norm.weight | 0x40224df00 | 0x400 | | 441 | blk.33.attn_q.weight | 0x40224e300 | 0x1e00000 | | 442 | blk.33.attn_v.weight | 0x40404e300 | 0xf00000 | | 443 | blk.34.attn_norm.weight | 0x404f4e300 | 0x3c00 | | 444 | blk.34.ffn_down.weight | 0x404f51f00 | 0x7080000 | | 445 | blk.34.ffn_gate.weight | 0x40bfd1f00 | 0x7080000 | | 446 | blk.34.ffn_up.weight | 0x413051f00 | 0x7080000 | | 447 | blk.34.post_attention_norm.weight | 0x41a0d1f00 | 0x3c00 | | 448 | blk.34.post_ffw_norm.weight | 0x41a0d5b00 | 0x3c00 | | 449 | blk.34.ffn_norm.weight | 0x41a0d9700 | 0x3c00 | | 450 | blk.34.attn_k_norm.weight | 0x41a0dd300 | 0x400 | | 451 | blk.34.attn_k.weight | 0x41a0dd700 | 0xf00000 | | 452 | blk.34.attn_output.weight | 0x41afdd700 | 0x1e00000 | | 453 | blk.34.attn_q_norm.weight | 0x41cddd700 | 0x400 | | 454 | blk.34.attn_q.weight | 0x41cdddb00 | 0x1e00000 | | 455 | blk.34.attn_v.weight | 0x41ebddb00 | 0xf00000 | | 456 | blk.35.attn_norm.weight | 0x41faddb00 | 0x3c00 | | 457 | blk.35.ffn_down.weight | 0x41fae1700 | 0x7080000 | | 458 | blk.35.ffn_gate.weight | 0x426b61700 | 0x7080000 | | 459 | blk.35.ffn_up.weight | 0x42dbe1700 | 0x7080000 | | 460 | blk.35.post_attention_norm.weight | 0x434c61700 | 0x3c00 | | 461 | blk.35.post_ffw_norm.weight | 0x434c65300 | 0x3c00 | | 462 | blk.35.ffn_norm.weight | 0x434c68f00 | 0x3c00 | | 463 | blk.35.attn_k_norm.weight | 0x434c6cb00 | 0x400 | | 464 | blk.35.attn_k.weight | 0x434c6cf00 | 0xf00000 | | 465 | blk.35.attn_output.weight | 0x435b6cf00 | 0x1e00000 | | 466 | blk.35.attn_q_norm.weight | 0x43796cf00 | 0x400 | | 467 | blk.35.attn_q.weight | 0x43796d300 | 0x1e00000 | | 468 | blk.35.attn_v.weight | 0x43976d300 | 0xf00000 | | 469 | blk.36.attn_norm.weight | 0x43a66d300 | 0x3c00 | | 470 | blk.36.ffn_down.weight | 0x43a670f00 | 0x7080000 | | 471 | blk.36.ffn_gate.weight | 0x4416f0f00 | 0x7080000 | | 472 | blk.36.ffn_up.weight | 0x448770f00 | 0x7080000 | | 473 | blk.36.post_attention_norm.weight | 0x44f7f0f00 | 0x3c00 | | 474 | blk.36.post_ffw_norm.weight | 0x44f7f4b00 | 0x3c00 | | 475 | blk.36.ffn_norm.weight | 0x44f7f8700 | 0x3c00 | | 476 | blk.36.attn_k_norm.weight | 0x44f7fc300 | 0x400 | | 477 | blk.36.attn_k.weight | 0x44f7fc700 | 0xf00000 | | 478 | blk.36.attn_output.weight | 0x4506fc700 | 0x1e00000 | | 479 | blk.36.attn_q_norm.weight | 0x4524fc700 | 0x400 | | 480 | blk.36.attn_q.weight | 0x4524fcb00 | 0x1e00000 | | 481 | blk.36.attn_v.weight | 0x4542fcb00 | 0xf00000 | | 482 | blk.37.ffn_gate.weight | 0x4551fcb00 | 0x7080000 | | 483 | blk.37.ffn_up.weight | 0x45c27cb00 | 0x7080000 | | 484 | blk.37.attn_k_norm.weight | 0x4632fcb00 | 0x400 | | 485 | blk.37.attn_k.weight | 0x4632fcf00 | 0xf00000 | | 486 | blk.37.attn_output.weight | 0x4641fcf00 | 0x1e00000 | | 487 | blk.37.attn_q_norm.weight | 0x465ffcf00 | 0x400 | | 488 | blk.37.attn_q.weight | 0x465ffd300 | 0x1e00000 | | 489 | blk.37.attn_v.weight | 0x467dfd300 | 0xf00000 | | 490 | blk.37.attn_norm.weight | 0x468cfd300 | 0x3c00 | | 491 | blk.37.ffn_down.weight | 0x468d00f00 | 0x7080000 | | 492 | blk.37.post_attention_norm.weight | 0x46fd80f00 | 0x3c00 | | 493 | blk.37.post_ffw_norm.weight | 0x46fd84b00 | 0x3c00 | | 494 | blk.37.ffn_norm.weight | 0x46fd88700 | 0x3c00 | | 495 | blk.38.attn_norm.weight | 0x46fd8c300 | 0x3c00 | | 496 | blk.38.ffn_down.weight | 0x46fd8ff00 | 0x7080000 | | 497 | blk.38.ffn_gate.weight | 0x476e0ff00 | 0x7080000 | | 498 | blk.38.ffn_up.weight | 0x47de8ff00 | 0x7080000 | | 499 | blk.38.post_attention_norm.weight | 0x484f0ff00 | 0x3c00 | | 500 | blk.38.post_ffw_norm.weight | 0x484f13b00 | 0x3c00 | | 501 | blk.38.ffn_norm.weight | 0x484f17700 | 0x3c00 | | 502 | blk.38.attn_k_norm.weight | 0x484f1b300 | 0x400 | | 503 | blk.38.attn_k.weight | 0x484f1b700 | 0xf00000 | | 504 | blk.38.attn_output.weight | 0x485e1b700 | 0x1e00000 | | 505 | blk.38.attn_q_norm.weight | 0x487c1b700 | 0x400 | | 506 | blk.38.attn_q.weight | 0x487c1bb00 | 0x1e00000 | | 507 | blk.38.attn_v.weight | 0x489a1bb00 | 0xf00000 | | 508 | blk.39.attn_norm.weight | 0x48a91bb00 | 0x3c00 | | 509 | blk.39.ffn_down.weight | 0x48a91f700 | 0x7080000 | | 510 | blk.39.ffn_gate.weight | 0x49199f700 | 0x7080000 | | 511 | blk.39.ffn_up.weight | 0x498a1f700 | 0x7080000 | | 512 | blk.39.post_attention_norm.weight | 0x49fa9f700 | 0x3c00 | | 513 | blk.39.post_ffw_norm.weight | 0x49faa3300 | 0x3c00 | | 514 | blk.39.ffn_norm.weight | 0x49faa6f00 | 0x3c00 | | 515 | blk.39.attn_k_norm.weight | 0x49faaab00 | 0x400 | | 516 | blk.39.attn_k.weight | 0x49faaaf00 | 0xf00000 | | 517 | blk.39.attn_output.weight | 0x4a09aaf00 | 0x1e00000 | | 518 | blk.39.attn_q_norm.weight | 0x4a27aaf00 | 0x400 | | 519 | blk.39.attn_q.weight | 0x4a27ab300 | 0x1e00000 | | 520 | blk.39.attn_v.weight | 0x4a45ab300 | 0xf00000 | | 521 | blk.40.attn_norm.weight | 0x4a54ab300 | 0x3c00 | | 522 | blk.40.ffn_down.weight | 0x4a54aef00 | 0x7080000 | | 523 | blk.40.ffn_gate.weight | 0x4ac52ef00 | 0x7080000 | | 524 | blk.40.ffn_up.weight | 0x4b35aef00 | 0x7080000 | | 525 | blk.40.post_attention_norm.weight | 0x4ba62ef00 | 0x3c00 | | 526 | blk.40.post_ffw_norm.weight | 0x4ba632b00 | 0x3c00 | | 527 | blk.40.ffn_norm.weight | 0x4ba636700 | 0x3c00 | | 528 | blk.40.attn_k_norm.weight | 0x4ba63a300 | 0x400 | | 529 | blk.40.attn_k.weight | 0x4ba63a700 | 0xf00000 | | 530 | blk.40.attn_output.weight | 0x4bb53a700 | 0x1e00000 | | 531 | blk.40.attn_q_norm.weight | 0x4bd33a700 | 0x400 | | 532 | blk.40.attn_q.weight | 0x4bd33ab00 | 0x1e00000 | | 533 | blk.40.attn_v.weight | 0x4bf13ab00 | 0xf00000 | | 534 | blk.41.attn_norm.weight | 0x4c003ab00 | 0x3c00 | | 535 | blk.41.ffn_down.weight | 0x4c003e700 | 0x7080000 | | 536 | blk.41.ffn_gate.weight | 0x4c70be700 | 0x7080000 | | 537 | blk.41.ffn_up.weight | 0x4ce13e700 | 0x7080000 | | 538 | blk.41.post_attention_norm.weight | 0x4d51be700 | 0x3c00 | | 539 | blk.41.post_ffw_norm.weight | 0x4d51c2300 | 0x3c00 | | 540 | blk.41.ffn_norm.weight | 0x4d51c5f00 | 0x3c00 | | 541 | blk.41.attn_k_norm.weight | 0x4d51c9b00 | 0x400 | | 542 | blk.41.attn_k.weight | 0x4d51c9f00 | 0xf00000 | | 543 | blk.41.attn_output.weight | 0x4d60c9f00 | 0x1e00000 | | 544 | blk.41.attn_q_norm.weight | 0x4d7ec9f00 | 0x400 | | 545 | blk.41.attn_q.weight | 0x4d7eca300 | 0x1e00000 | | 546 | blk.41.attn_v.weight | 0x4d9cca300 | 0xf00000 | | 547 | blk.42.attn_norm.weight | 0x4dabca300 | 0x3c00 | | 548 | blk.42.ffn_down.weight | 0x4dabcdf00 | 0x7080000 | | 549 | blk.42.ffn_gate.weight | 0x4e1c4df00 | 0x7080000 | | 550 | blk.42.ffn_up.weight | 0x4e8ccdf00 | 0x7080000 | | 551 | blk.42.post_attention_norm.weight | 0x4efd4df00 | 0x3c00 | | 552 | blk.42.post_ffw_norm.weight | 0x4efd51b00 | 0x3c00 | | 553 | blk.42.ffn_norm.weight | 0x4efd55700 | 0x3c00 | | 554 | blk.42.attn_k_norm.weight | 0x4efd59300 | 0x400 | | 555 | blk.42.attn_k.weight | 0x4efd59700 | 0xf00000 | | 556 | blk.42.attn_output.weight | 0x4f0c59700 | 0x1e00000 | | 557 | blk.42.attn_q_norm.weight | 0x4f2a59700 | 0x400 | | 558 | blk.42.attn_q.weight | 0x4f2a59b00 | 0x1e00000 | | 559 | blk.42.attn_v.weight | 0x4f4859b00 | 0xf00000 | | 560 | blk.43.attn_norm.weight | 0x4f5759b00 | 0x3c00 | | 561 | blk.43.ffn_down.weight | 0x4f575d700 | 0x7080000 | | 562 | blk.43.ffn_gate.weight | 0x4fc7dd700 | 0x7080000 | | 563 | blk.43.ffn_up.weight | 0x50385d700 | 0x7080000 | | 564 | blk.43.post_attention_norm.weight | 0x50a8dd700 | 0x3c00 | | 565 | blk.43.post_ffw_norm.weight | 0x50a8e1300 | 0x3c00 | | 566 | blk.43.ffn_norm.weight | 0x50a8e4f00 | 0x3c00 | | 567 | blk.43.attn_k_norm.weight | 0x50a8e8b00 | 0x400 | | 568 | blk.43.attn_k.weight | 0x50a8e8f00 | 0xf00000 | | 569 | blk.43.attn_output.weight | 0x50b7e8f00 | 0x1e00000 | | 570 | blk.43.attn_q_norm.weight | 0x50d5e8f00 | 0x400 | | 571 | blk.43.attn_q.weight | 0x50d5e9300 | 0x1e00000 | | 572 | blk.43.attn_v.weight | 0x50f3e9300 | 0xf00000 | | 573 | blk.44.attn_norm.weight | 0x5102e9300 | 0x3c00 | | 574 | blk.44.ffn_down.weight | 0x5102ecf00 | 0x7080000 | | 575 | blk.44.ffn_gate.weight | 0x51736cf00 | 0x7080000 | | 576 | blk.44.ffn_up.weight | 0x51e3ecf00 | 0x7080000 | | 577 | blk.44.post_attention_norm.weight | 0x52546cf00 | 0x3c00 | | 578 | blk.44.post_ffw_norm.weight | 0x525470b00 | 0x3c00 | | 579 | blk.44.ffn_norm.weight | 0x525474700 | 0x3c00 | | 580 | blk.44.attn_k_norm.weight | 0x525478300 | 0x400 | | 581 | blk.44.attn_k.weight | 0x525478700 | 0xf00000 | | 582 | blk.44.attn_output.weight | 0x526378700 | 0x1e00000 | | 583 | blk.44.attn_q_norm.weight | 0x528178700 | 0x400 | | 584 | blk.44.attn_q.weight | 0x528178b00 | 0x1e00000 | | 585 | blk.44.attn_v.weight | 0x529f78b00 | 0xf00000 | | 586 | blk.45.attn_norm.weight | 0x52ae78b00 | 0x3c00 | | 587 | blk.45.ffn_down.weight | 0x52ae7c700 | 0x7080000 | | 588 | blk.45.ffn_gate.weight | 0x531efc700 | 0x7080000 | | 589 | blk.45.ffn_up.weight | 0x538f7c700 | 0x7080000 | | 590 | blk.45.post_attention_norm.weight | 0x53fffc700 | 0x3c00 | | 591 | blk.45.post_ffw_norm.weight | 0x540000300 | 0x3c00 | | 592 | blk.45.ffn_norm.weight | 0x540003f00 | 0x3c00 | | 593 | blk.45.attn_k_norm.weight | 0x540007b00 | 0x400 | | 594 | blk.45.attn_k.weight | 0x540007f00 | 0xf00000 | | 595 | blk.45.attn_output.weight | 0x540f07f00 | 0x1e00000 | | 596 | blk.45.attn_q_norm.weight | 0x542d07f00 | 0x400 | | 597 | blk.45.attn_q.weight | 0x542d08300 | 0x1e00000 | | 598 | blk.45.attn_v.weight | 0x544b08300 | 0xf00000 | | 599 | blk.46.attn_norm.weight | 0x545a08300 | 0x3c00 | | 600 | blk.46.ffn_down.weight | 0x545a0bf00 | 0x7080000 | | 601 | blk.46.ffn_gate.weight | 0x54ca8bf00 | 0x7080000 | | 602 | blk.46.ffn_up.weight | 0x553b0bf00 | 0x7080000 | | 603 | blk.46.post_attention_norm.weight | 0x55ab8bf00 | 0x3c00 | | 604 | blk.46.post_ffw_norm.weight | 0x55ab8fb00 | 0x3c00 | | 605 | blk.46.ffn_norm.weight | 0x55ab93700 | 0x3c00 | | 606 | blk.46.attn_k_norm.weight | 0x55ab97300 | 0x400 | | 607 | blk.46.attn_k.weight | 0x55ab97700 | 0xf00000 | | 608 | blk.46.attn_output.weight | 0x55ba97700 | 0x1e00000 | | 609 | blk.46.attn_q_norm.weight | 0x55d897700 | 0x400 | | 610 | blk.46.attn_q.weight | 0x55d897b00 | 0x1e00000 | | 611 | blk.46.attn_v.weight | 0x55f697b00 | 0xf00000 | | 612 | blk.47.attn_norm.weight | 0x560597b00 | 0x3c00 | | 613 | blk.47.ffn_down.weight | 0x56059b700 | 0x7080000 | | 614 | blk.47.ffn_gate.weight | 0x56761b700 | 0x7080000 | | 615 | blk.47.ffn_up.weight | 0x56e69b700 | 0x7080000 | | 616 | blk.47.post_attention_norm.weight | 0x57571b700 | 0x3c00 | | 617 | blk.47.post_ffw_norm.weight | 0x57571f300 | 0x3c00 | | 618 | blk.47.ffn_norm.weight | 0x575722f00 | 0x3c00 | | 619 | blk.47.attn_k_norm.weight | 0x575726b00 | 0x400 | | 620 | blk.47.attn_k.weight | 0x575726f00 | 0xf00000 | | 621 | blk.47.attn_output.weight | 0x576626f00 | 0x1e00000 | | 622 | blk.47.attn_q_norm.weight | 0x578426f00 | 0x400 | | 623 | blk.47.attn_q.weight | 0x578427300 | 0x1e00000 | | 624 | blk.47.attn_v.weight | 0x57a227300 | 0xf00000 | | 625 | output_norm.weight | 0x57b127300 | 0x3c00 | ### Base Tensor Group : ~1B Elements | T_ID | Tensor Layer Name | Human Friendly Tensor Layer Name | Elements | Shape | Type | |-----:|:-------------------|:---------------------------------|:-----------------|:----------------------|:-----| | 0 | token_embd.weight | Token Embedding (W) | (~1B) 1006632960 | 3840 x 262144 x 1 x 1 | F16 | | 625 | output_norm.weight | Output Normalization (W) | (~4K) 3840 | 3840 x 1 x 1 x 1 | F32 | - Total elements in base: ( ~1B) 1006636800 - Percentage of total elements: 8.56% ### Block 0 Tensor Group : ~224M Elements | T_ID | Tensor Layer Name | Human Friendly Tensor Layer Name | Elements | Shape | Type | |-----:|:---------------------------------|:-----------------------------------------------|:----------------|:----------------------|:-----| | 1 | blk.0.attn_norm.weight | Block 0 Attention Normalization (W) | ( ~4K) 3840 | 3840 x 1 x 1 x 1 | F32 | | 2 | blk.0.ffn_down.weight | Block 0 Feed-Forward Network "Down" (W) | (~59M) 58982400 | 15360 x 3840 x 1 x 1 | F16 | | 3 | blk.0.ffn_gate.weight | Block 0 Feed-Forward Network "Gate" (W) | (~59M) 58982400 | 3840 x 15360 x 1 x 1 | F16 | | 4 | blk.0.ffn_up.weight | Block 0 Feed-Forward Network "Up" (W) | (~59M) 58982400 | 3840 x 15360 x 1 x 1 | F16 | | 5 | blk.0.post_attention_norm.weight | Block 0 Post_Attention_Norm (W) | ( ~4K) 3840 | 3840 x 1 x 1 x 1 | F32 | | 6 | blk.0.post_ffw_norm.weight | Block 0 Post_Ffw_Norm (W) | ( ~4K) 3840 | 3840 x 1 x 1 x 1 | F32 | | 7 | blk.0.ffn_norm.weight | Block 0 Feed-Forward Network Normalization (W) | ( ~4K) 3840 | 3840 x 1 x 1 x 1 | F32 | | 8 | blk.0.attn_k_norm.weight | Block 0 Attn_K_Norm (W) | ( 256) 256 | 256 x 1 x 1 x 1 | F32 | | 9 | blk.0.attn_k.weight | Block 0 Attention Key (W) | ( ~8M) 7864320 | 3840 x 2048 x 1 x 1 | F16 | | 10 | blk.0.attn_output.weight | Block 0 Attention Output (W) | (~16M) 15728640 | 4096 x 3840 x 1 x 1 | F16 | | 11 | blk.0.attn_q_norm.weight | Block 0 Attn_Q_Norm (W) | ( 256) 256 | 256 x 1 x 1 x 1 | F32 | | 12 | blk.0.attn_q.weight | Block 0 Attention Query (W) | (~16M) 15728640 | 3840 x 4096 x 1 x 1 | F16 | | 13 | blk.0.attn_v.weight | Block 0 Attention Value (W) | ( ~8M) 7864320 | 3840 x 2048 x 1 x 1 | F16 | - Total elements in blk.0: (~224M) 224148992 - Percentage of total elements: 1.91% ### Block 1 Tensor Group : ~224M Elements | T_ID | Tensor Layer Name | Human Friendly Tensor Layer Name | Elements | Shape | Type | |-----:|:---------------------------------|:-----------------------------------------------|:----------------|:----------------------|:-----| | 14 | blk.1.attn_norm.weight | Block 1 Attention Normalization (W) | ( ~4K) 3840 | 3840 x 1 x 1 x 1 | F32 | | 15 | blk.1.ffn_down.weight | Block 1 Feed-Forward Network "Down" (W) | (~59M) 58982400 | 15360 x 3840 x 1 x 1 | F16 | | 16 | blk.1.ffn_gate.weight | Block 1 Feed-Forward Network "Gate" (W) | (~59M) 58982400 | 3840 x 15360 x 1 x 1 | F16 | | 17 | blk.1.ffn_up.weight | Block 1 Feed-Forward Network "Up" (W) | (~59M) 58982400 | 3840 x 15360 x 1 x 1 | F16 | | 18 | blk.1.post_attention_norm.weight | Block 1 Post_Attention_Norm (W) | ( ~4K) 3840 | 3840 x 1 x 1 x 1 | F32 | | 19 | blk.1.post_ffw_norm.weight | Block 1 Post_Ffw_Norm (W) | ( ~4K) 3840 | 3840 x 1 x 1 x 1 | F32 | | 20 | blk.1.ffn_norm.weight | Block 1 Feed-Forward Network Normalization (W) | ( ~4K) 3840 | 3840 x 1 x 1 x 1 | F32 | | 21 | blk.1.attn_k_norm.weight | Block 1 Attn_K_Norm (W) | ( 256) 256 | 256 x 1 x 1 x 1 | F32 | | 22 | blk.1.attn_k.weight | Block 1 Attention Key (W) | ( ~8M) 7864320 | 3840 x 2048 x 1 x 1 | F16 | | 23 | blk.1.attn_output.weight | Block 1 Attention Output (W) | (~16M) 15728640 | 4096 x 3840 x 1 x 1 | F16 | | 24 | blk.1.attn_q_norm.weight | Block 1 Attn_Q_Norm (W) | ( 256) 256 | 256 x 1 x 1 x 1 | F32 | | 25 | blk.1.attn_q.weight | Block 1 Attention Query (W) | (~16M) 15728640 | 3840 x 4096 x 1 x 1 | F16 | | 26 | blk.1.attn_v.weight | Block 1 Attention Value (W) | ( ~8M) 7864320 | 3840 x 2048 x 1 x 1 | F16 | - Total elements in blk.1: (~224M) 224148992 - Percentage of total elements: 1.91% ### Block 2 Tensor Group : ~224M Elements | T_ID | Tensor Layer Name | Human Friendly Tensor Layer Name | Elements | Shape | Type | |-----:|:---------------------------------|:-----------------------------------------------|:----------------|:----------------------|:-----| | 27 | blk.2.attn_norm.weight | Block 2 Attention Normalization (W) | ( ~4K) 3840 | 3840 x 1 x 1 x 1 | F32 | | 28 | blk.2.ffn_down.weight | Block 2 Feed-Forward Network "Down" (W) | (~59M) 58982400 | 15360 x 3840 x 1 x 1 | F16 | | 29 | blk.2.ffn_gate.weight | Block 2 Feed-Forward Network "Gate" (W) | (~59M) 58982400 | 3840 x 15360 x 1 x 1 | F16 | | 30 | blk.2.ffn_up.weight | Block 2 Feed-Forward Network "Up" (W) | (~59M) 58982400 | 3840 x 15360 x 1 x 1 | F16 | | 31 | blk.2.post_attention_norm.weight | Block 2 Post_Attention_Norm (W) | ( ~4K) 3840 | 3840 x 1 x 1 x 1 | F32 | | 32 | blk.2.post_ffw_norm.weight | Block 2 Post_Ffw_Norm (W) | ( ~4K) 3840 | 3840 x 1 x 1 x 1 | F32 | | 33 | blk.2.ffn_norm.weight | Block 2 Feed-Forward Network Normalization (W) | ( ~4K) 3840 | 3840 x 1 x 1 x 1 | F32 | | 34 | blk.2.attn_k_norm.weight | Block 2 Attn_K_Norm (W) | ( 256) 256 | 256 x 1 x 1 x 1 | F32 | | 35 | blk.2.attn_k.weight | Block 2 Attention Key (W) | ( ~8M) 7864320 | 3840 x 2048 x 1 x 1 | F16 | | 36 | blk.2.attn_output.weight | Block 2 Attention Output (W) | (~16M) 15728640 | 4096 x 3840 x 1 x 1 | F16 | | 37 | blk.2.attn_q_norm.weight | Block 2 Attn_Q_Norm (W) | ( 256) 256 | 256 x 1 x 1 x 1 | F32 | | 38 | blk.2.attn_q.weight | Block 2 Attention Query (W) | (~16M) 15728640 | 3840 x 4096 x 1 x 1 | F16 | | 39 | blk.2.attn_v.weight | Block 2 Attention Value (W) | ( ~8M) 7864320 | 3840 x 2048 x 1 x 1 | F16 | - Total elements in blk.2: (~224M) 224148992 - Percentage of total elements: 1.91% ### Block 3 Tensor Group : ~224M Elements | T_ID | Tensor Layer Name | Human Friendly Tensor Layer Name | Elements | Shape | Type | |-----:|:---------------------------------|:-----------------------------------------------|:----------------|:----------------------|:-----| | 40 | blk.3.attn_norm.weight | Block 3 Attention Normalization (W) | ( ~4K) 3840 | 3840 x 1 x 1 x 1 | F32 | | 41 | blk.3.ffn_down.weight | Block 3 Feed-Forward Network "Down" (W) | (~59M) 58982400 | 15360 x 3840 x 1 x 1 | F16 | | 42 | blk.3.ffn_gate.weight | Block 3 Feed-Forward Network "Gate" (W) | (~59M) 58982400 | 3840 x 15360 x 1 x 1 | F16 | | 43 | blk.3.ffn_up.weight | Block 3 Feed-Forward Network "Up" (W) | (~59M) 58982400 | 3840 x 15360 x 1 x 1 | F16 | | 44 | blk.3.post_attention_norm.weight | Block 3 Post_Attention_Norm (W) | ( ~4K) 3840 | 3840 x 1 x 1 x 1 | F32 | | 45 | blk.3.post_ffw_norm.weight | Block 3 Post_Ffw_Norm (W) | ( ~4K) 3840 | 3840 x 1 x 1 x 1 | F32 | | 46 | blk.3.ffn_norm.weight | Block 3 Feed-Forward Network Normalization (W) | ( ~4K) 3840 | 3840 x 1 x 1 x 1 | F32 | | 47 | blk.3.attn_k_norm.weight | Block 3 Attn_K_Norm (W) | ( 256) 256 | 256 x 1 x 1 x 1 | F32 | | 48 | blk.3.attn_k.weight | Block 3 Attention Key (W) | ( ~8M) 7864320 | 3840 x 2048 x 1 x 1 | F16 | | 49 | blk.3.attn_output.weight | Block 3 Attention Output (W) | (~16M) 15728640 | 4096 x 3840 x 1 x 1 | F16 | | 50 | blk.3.attn_q_norm.weight | Block 3 Attn_Q_Norm (W) | ( 256) 256 | 256 x 1 x 1 x 1 | F32 | | 51 | blk.3.attn_q.weight | Block 3 Attention Query (W) | (~16M) 15728640 | 3840 x 4096 x 1 x 1 | F16 | | 52 | blk.3.attn_v.weight | Block 3 Attention Value (W) | ( ~8M) 7864320 | 3840 x 2048 x 1 x 1 | F16 | - Total elements in blk.3: (~224M) 224148992 - Percentage of total elements: 1.91% ### Block 4 Tensor Group : ~224M Elements | T_ID | Tensor Layer Name | Human Friendly Tensor Layer Name | Elements | Shape | Type | |-----:|:---------------------------------|:-----------------------------------------------|:----------------|:----------------------|:-----| | 53 | blk.4.ffn_gate.weight | Block 4 Feed-Forward Network "Gate" (W) | (~59M) 58982400 | 3840 x 15360 x 1 x 1 | F16 | | 54 | blk.4.ffn_up.weight | Block 4 Feed-Forward Network "Up" (W) | (~59M) 58982400 | 3840 x 15360 x 1 x 1 | F16 | | 55 | blk.4.attn_k_norm.weight | Block 4 Attn_K_Norm (W) | ( 256) 256 | 256 x 1 x 1 x 1 | F32 | | 56 | blk.4.attn_k.weight | Block 4 Attention Key (W) | ( ~8M) 7864320 | 3840 x 2048 x 1 x 1 | F16 | | 57 | blk.4.attn_output.weight | Block 4 Attention Output (W) | (~16M) 15728640 | 4096 x 3840 x 1 x 1 | F16 | | 58 | blk.4.attn_q_norm.weight | Block 4 Attn_Q_Norm (W) | ( 256) 256 | 256 x 1 x 1 x 1 | F32 | | 59 | blk.4.attn_q.weight | Block 4 Attention Query (W) | (~16M) 15728640 | 3840 x 4096 x 1 x 1 | F16 | | 60 | blk.4.attn_v.weight | Block 4 Attention Value (W) | ( ~8M) 7864320 | 3840 x 2048 x 1 x 1 | F16 | | 134 | blk.4.attn_norm.weight | Block 4 Attention Normalization (W) | ( ~4K) 3840 | 3840 x 1 x 1 x 1 | F32 | | 135 | blk.4.ffn_down.weight | Block 4 Feed-Forward Network "Down" (W) | (~59M) 58982400 | 15360 x 3840 x 1 x 1 | F16 | | 136 | blk.4.post_attention_norm.weight | Block 4 Post_Attention_Norm (W) | ( ~4K) 3840 | 3840 x 1 x 1 x 1 | F32 | | 137 | blk.4.post_ffw_norm.weight | Block 4 Post_Ffw_Norm (W) | ( ~4K) 3840 | 3840 x 1 x 1 x 1 | F32 | | 138 | blk.4.ffn_norm.weight | Block 4 Feed-Forward Network Normalization (W) | ( ~4K) 3840 | 3840 x 1 x 1 x 1 | F32 | - Total elements in blk.4: (~224M) 224148992 - Percentage of total elements: 1.91% ### Block 10 Tensor Group : ~224M Elements | T_ID | Tensor Layer Name | Human Friendly Tensor Layer Name | Elements | Shape | Type | |-----:|:----------------------------------|:------------------------------------------------|:----------------|:----------------------|:-----| | 61 | blk.10.attn_norm.weight | Block 10 Attention Normalization (W) | ( ~4K) 3840 | 3840 x 1 x 1 x 1 | F32 | | 62 | blk.10.ffn_down.weight | Block 10 Feed-Forward Network "Down" (W) | (~59M) 58982400 | 15360 x 3840 x 1 x 1 | F16 | | 63 | blk.10.ffn_gate.weight | Block 10 Feed-Forward Network "Gate" (W) | (~59M) 58982400 | 3840 x 15360 x 1 x 1 | F16 | | 64 | blk.10.ffn_up.weight | Block 10 Feed-Forward Network "Up" (W) | (~59M) 58982400 | 3840 x 15360 x 1 x 1 | F16 | | 65 | blk.10.post_attention_norm.weight | Block 10 Post_Attention_Norm (W) | ( ~4K) 3840 | 3840 x 1 x 1 x 1 | F32 | | 66 | blk.10.post_ffw_norm.weight | Block 10 Post_Ffw_Norm (W) | ( ~4K) 3840 | 3840 x 1 x 1 x 1 | F32 | | 67 | blk.10.ffn_norm.weight | Block 10 Feed-Forward Network Normalization (W) | ( ~4K) 3840 | 3840 x 1 x 1 x 1 | F32 | | 68 | blk.10.attn_k_norm.weight | Block 10 Attn_K_Norm (W) | ( 256) 256 | 256 x 1 x 1 x 1 | F32 | | 69 | blk.10.attn_k.weight | Block 10 Attention Key (W) | ( ~8M) 7864320 | 3840 x 2048 x 1 x 1 | F16 | | 70 | blk.10.attn_output.weight | Block 10 Attention Output (W) | (~16M) 15728640 | 4096 x 3840 x 1 x 1 | F16 | | 71 | blk.10.attn_q_norm.weight | Block 10 Attn_Q_Norm (W) | ( 256) 256 | 256 x 1 x 1 x 1 | F32 | | 72 | blk.10.attn_q.weight | Block 10 Attention Query (W) | (~16M) 15728640 | 3840 x 4096 x 1 x 1 | F16 | | 73 | blk.10.attn_v.weight | Block 10 Attention Value (W) | ( ~8M) 7864320 | 3840 x 2048 x 1 x 1 | F16 | - Total elements in blk.10: (~224M) 224148992 - Percentage of total elements: 1.91% ### Block 11 Tensor Group : ~224M Elements | T_ID | Tensor Layer Name | Human Friendly Tensor Layer Name | Elements | Shape | Type | |-----:|:----------------------------------|:------------------------------------------------|:----------------|:----------------------|:-----| | 74 | blk.11.attn_norm.weight | Block 11 Attention Normalization (W) | ( ~4K) 3840 | 3840 x 1 x 1 x 1 | F32 | | 75 | blk.11.ffn_down.weight | Block 11 Feed-Forward Network "Down" (W) | (~59M) 58982400 | 15360 x 3840 x 1 x 1 | F16 | | 76 | blk.11.ffn_gate.weight | Block 11 Feed-Forward Network "Gate" (W) | (~59M) 58982400 | 3840 x 15360 x 1 x 1 | F16 | | 77 | blk.11.ffn_up.weight | Block 11 Feed-Forward Network "Up" (W) | (~59M) 58982400 | 3840 x 15360 x 1 x 1 | F16 | | 78 | blk.11.post_attention_norm.weight | Block 11 Post_Attention_Norm (W) | ( ~4K) 3840 | 3840 x 1 x 1 x 1 | F32 | | 79 | blk.11.post_ffw_norm.weight | Block 11 Post_Ffw_Norm (W) | ( ~4K) 3840 | 3840 x 1 x 1 x 1 | F32 | | 80 | blk.11.ffn_norm.weight | Block 11 Feed-Forward Network Normalization (W) | ( ~4K) 3840 | 3840 x 1 x 1 x 1 | F32 | | 81 | blk.11.attn_k_norm.weight | Block 11 Attn_K_Norm (W) | ( 256) 256 | 256 x 1 x 1 x 1 | F32 | | 82 | blk.11.attn_k.weight | Block 11 Attention Key (W) | ( ~8M) 7864320 | 3840 x 2048 x 1 x 1 | F16 | | 83 | blk.11.attn_output.weight | Block 11 Attention Output (W) | (~16M) 15728640 | 4096 x 3840 x 1 x 1 | F16 | | 84 | blk.11.attn_q_norm.weight | Block 11 Attn_Q_Norm (W) | ( 256) 256 | 256 x 1 x 1 x 1 | F32 | | 85 | blk.11.attn_q.weight | Block 11 Attention Query (W) | (~16M) 15728640 | 3840 x 4096 x 1 x 1 | F16 | | 86 | blk.11.attn_v.weight | Block 11 Attention Value (W) | ( ~8M) 7864320 | 3840 x 2048 x 1 x 1 | F16 | - Total elements in blk.11: (~224M) 224148992 - Percentage of total elements: 1.91% ### Block 12 Tensor Group : ~224M Elements | T_ID | Tensor Layer Name | Human Friendly Tensor Layer Name | Elements | Shape | Type | |-----:|:----------------------------------|:------------------------------------------------|:----------------|:----------------------|:-----| | 87 | blk.12.attn_norm.weight | Block 12 Attention Normalization (W) | ( ~4K) 3840 | 3840 x 1 x 1 x 1 | F32 | | 88 | blk.12.ffn_down.weight | Block 12 Feed-Forward Network "Down" (W) | (~59M) 58982400 | 15360 x 3840 x 1 x 1 | F16 | | 89 | blk.12.ffn_gate.weight | Block 12 Feed-Forward Network "Gate" (W) | (~59M) 58982400 | 3840 x 15360 x 1 x 1 | F16 | | 90 | blk.12.ffn_up.weight | Block 12 Feed-Forward Network "Up" (W) | (~59M) 58982400 | 3840 x 15360 x 1 x 1 | F16 | | 91 | blk.12.post_attention_norm.weight | Block 12 Post_Attention_Norm (W) | ( ~4K) 3840 | 3840 x 1 x 1 x 1 | F32 | | 92 | blk.12.post_ffw_norm.weight | Block 12 Post_Ffw_Norm (W) | ( ~4K) 3840 | 3840 x 1 x 1 x 1 | F32 | | 93 | blk.12.ffn_norm.weight | Block 12 Feed-Forward Network Normalization (W) | ( ~4K) 3840 | 3840 x 1 x 1 x 1 | F32 | | 94 | blk.12.attn_k_norm.weight | Block 12 Attn_K_Norm (W) | ( 256) 256 | 256 x 1 x 1 x 1 | F32 | | 95 | blk.12.attn_k.weight | Block 12 Attention Key (W) | ( ~8M) 7864320 | 3840 x 2048 x 1 x 1 | F16 | | 96 | blk.12.attn_output.weight | Block 12 Attention Output (W) | (~16M) 15728640 | 4096 x 3840 x 1 x 1 | F16 | | 97 | blk.12.attn_q_norm.weight | Block 12 Attn_Q_Norm (W) | ( 256) 256 | 256 x 1 x 1 x 1 | F32 | | 98 | blk.12.attn_q.weight | Block 12 Attention Query (W) | (~16M) 15728640 | 3840 x 4096 x 1 x 1 | F16 | | 99 | blk.12.attn_v.weight | Block 12 Attention Value (W) | ( ~8M) 7864320 | 3840 x 2048 x 1 x 1 | F16 | - Total elements in blk.12: (~224M) 224148992 - Percentage of total elements: 1.91% ### Block 13 Tensor Group : ~224M Elements | T_ID | Tensor Layer Name | Human Friendly Tensor Layer Name | Elements | Shape | Type | |-----:|:----------------------------------|:------------------------------------------------|:----------------|:----------------------|:-----| | 100 | blk.13.attn_norm.weight | Block 13 Attention Normalization (W) | ( ~4K) 3840 | 3840 x 1 x 1 x 1 | F32 | | 101 | blk.13.ffn_down.weight | Block 13 Feed-Forward Network "Down" (W) | (~59M) 58982400 | 15360 x 3840 x 1 x 1 | F16 | | 102 | blk.13.ffn_gate.weight | Block 13 Feed-Forward Network "Gate" (W) | (~59M) 58982400 | 3840 x 15360 x 1 x 1 | F16 | | 103 | blk.13.ffn_up.weight | Block 13 Feed-Forward Network "Up" (W) | (~59M) 58982400 | 3840 x 15360 x 1 x 1 | F16 | | 104 | blk.13.post_attention_norm.weight | Block 13 Post_Attention_Norm (W) | ( ~4K) 3840 | 3840 x 1 x 1 x 1 | F32 | | 105 | blk.13.post_ffw_norm.weight | Block 13 Post_Ffw_Norm (W) | ( ~4K) 3840 | 3840 x 1 x 1 x 1 | F32 | | 106 | blk.13.ffn_norm.weight | Block 13 Feed-Forward Network Normalization (W) | ( ~4K) 3840 | 3840 x 1 x 1 x 1 | F32 | | 107 | blk.13.attn_k_norm.weight | Block 13 Attn_K_Norm (W) | ( 256) 256 | 256 x 1 x 1 x 1 | F32 | | 108 | blk.13.attn_k.weight | Block 13 Attention Key (W) | ( ~8M) 7864320 | 3840 x 2048 x 1 x 1 | F16 | | 109 | blk.13.attn_output.weight | Block 13 Attention Output (W) | (~16M) 15728640 | 4096 x 3840 x 1 x 1 | F16 | | 110 | blk.13.attn_q_norm.weight | Block 13 Attn_Q_Norm (W) | ( 256) 256 | 256 x 1 x 1 x 1 | F32 | | 111 | blk.13.attn_q.weight | Block 13 Attention Query (W) | (~16M) 15728640 | 3840 x 4096 x 1 x 1 | F16 | | 112 | blk.13.attn_v.weight | Block 13 Attention Value (W) | ( ~8M) 7864320 | 3840 x 2048 x 1 x 1 | F16 | - Total elements in blk.13: (~224M) 224148992 - Percentage of total elements: 1.91% ### Block 14 Tensor Group : ~224M Elements | T_ID | Tensor Layer Name | Human Friendly Tensor Layer Name | Elements | Shape | Type | |-----:|:----------------------------------|:------------------------------------------------|:----------------|:----------------------|:-----| | 113 | blk.14.attn_norm.weight | Block 14 Attention Normalization (W) | ( ~4K) 3840 | 3840 x 1 x 1 x 1 | F32 | | 114 | blk.14.ffn_down.weight | Block 14 Feed-Forward Network "Down" (W) | (~59M) 58982400 | 15360 x 3840 x 1 x 1 | F16 | | 115 | blk.14.ffn_gate.weight | Block 14 Feed-Forward Network "Gate" (W) | (~59M) 58982400 | 3840 x 15360 x 1 x 1 | F16 | | 116 | blk.14.ffn_up.weight | Block 14 Feed-Forward Network "Up" (W) | (~59M) 58982400 | 3840 x 15360 x 1 x 1 | F16 | | 117 | blk.14.post_attention_norm.weight | Block 14 Post_Attention_Norm (W) | ( ~4K) 3840 | 3840 x 1 x 1 x 1 | F32 | | 118 | blk.14.post_ffw_norm.weight | Block 14 Post_Ffw_Norm (W) | ( ~4K) 3840 | 3840 x 1 x 1 x 1 | F32 | | 119 | blk.14.ffn_norm.weight | Block 14 Feed-Forward Network Normalization (W) | ( ~4K) 3840 | 3840 x 1 x 1 x 1 | F32 | | 120 | blk.14.attn_k_norm.weight | Block 14 Attn_K_Norm (W) | ( 256) 256 | 256 x 1 x 1 x 1 | F32 | | 121 | blk.14.attn_k.weight | Block 14 Attention Key (W) | ( ~8M) 7864320 | 3840 x 2048 x 1 x 1 | F16 | | 122 | blk.14.attn_output.weight | Block 14 Attention Output (W) | (~16M) 15728640 | 4096 x 3840 x 1 x 1 | F16 | | 123 | blk.14.attn_q_norm.weight | Block 14 Attn_Q_Norm (W) | ( 256) 256 | 256 x 1 x 1 x 1 | F32 | | 124 | blk.14.attn_q.weight | Block 14 Attention Query (W) | (~16M) 15728640 | 3840 x 4096 x 1 x 1 | F16 | | 125 | blk.14.attn_v.weight | Block 14 Attention Value (W) | ( ~8M) 7864320 | 3840 x 2048 x 1 x 1 | F16 | - Total elements in blk.14: (~224M) 224148992 - Percentage of total elements: 1.91% ### Block 15 Tensor Group : ~224M Elements | T_ID | Tensor Layer Name | Human Friendly Tensor Layer Name | Elements | Shape | Type | |-----:|:----------------------------------|:------------------------------------------------|:----------------|:----------------------|:-----| | 126 | blk.15.ffn_gate.weight | Block 15 Feed-Forward Network "Gate" (W) | (~59M) 58982400 | 3840 x 15360 x 1 x 1 | F16 | | 127 | blk.15.ffn_up.weight | Block 15 Feed-Forward Network "Up" (W) | (~59M) 58982400 | 3840 x 15360 x 1 x 1 | F16 | | 128 | blk.15.attn_k_norm.weight | Block 15 Attn_K_Norm (W) | ( 256) 256 | 256 x 1 x 1 x 1 | F32 | | 129 | blk.15.attn_k.weight | Block 15 Attention Key (W) | ( ~8M) 7864320 | 3840 x 2048 x 1 x 1 | F16 | | 130 | blk.15.attn_output.weight | Block 15 Attention Output (W) | (~16M) 15728640 | 4096 x 3840 x 1 x 1 | F16 | | 131 | blk.15.attn_q_norm.weight | Block 15 Attn_Q_Norm (W) | ( 256) 256 | 256 x 1 x 1 x 1 | F32 | | 132 | blk.15.attn_q.weight | Block 15 Attention Query (W) | (~16M) 15728640 | 3840 x 4096 x 1 x 1 | F16 | | 133 | blk.15.attn_v.weight | Block 15 Attention Value (W) | ( ~8M) 7864320 | 3840 x 2048 x 1 x 1 | F16 | | 204 | blk.15.attn_norm.weight | Block 15 Attention Normalization (W) | ( ~4K) 3840 | 3840 x 1 x 1 x 1 | F32 | | 205 | blk.15.ffn_down.weight | Block 15 Feed-Forward Network "Down" (W) | (~59M) 58982400 | 15360 x 3840 x 1 x 1 | F16 | | 206 | blk.15.post_attention_norm.weight | Block 15 Post_Attention_Norm (W) | ( ~4K) 3840 | 3840 x 1 x 1 x 1 | F32 | | 207 | blk.15.post_ffw_norm.weight | Block 15 Post_Ffw_Norm (W) | ( ~4K) 3840 | 3840 x 1 x 1 x 1 | F32 | | 208 | blk.15.ffn_norm.weight | Block 15 Feed-Forward Network Normalization (W) | ( ~4K) 3840 | 3840 x 1 x 1 x 1 | F32 | - Total elements in blk.15: (~224M) 224148992 - Percentage of total elements: 1.91% ### Block 5 Tensor Group : ~224M Elements | T_ID | Tensor Layer Name | Human Friendly Tensor Layer Name | Elements | Shape | Type | |-----:|:---------------------------------|:-----------------------------------------------|:----------------|:----------------------|:-----| | 139 | blk.5.attn_norm.weight | Block 5 Attention Normalization (W) | ( ~4K) 3840 | 3840 x 1 x 1 x 1 | F32 | | 140 | blk.5.ffn_down.weight | Block 5 Feed-Forward Network "Down" (W) | (~59M) 58982400 | 15360 x 3840 x 1 x 1 | F16 | | 141 | blk.5.ffn_gate.weight | Block 5 Feed-Forward Network "Gate" (W) | (~59M) 58982400 | 3840 x 15360 x 1 x 1 | F16 | | 142 | blk.5.ffn_up.weight | Block 5 Feed-Forward Network "Up" (W) | (~59M) 58982400 | 3840 x 15360 x 1 x 1 | F16 | | 143 | blk.5.post_attention_norm.weight | Block 5 Post_Attention_Norm (W) | ( ~4K) 3840 | 3840 x 1 x 1 x 1 | F32 | | 144 | blk.5.post_ffw_norm.weight | Block 5 Post_Ffw_Norm (W) | ( ~4K) 3840 | 3840 x 1 x 1 x 1 | F32 | | 145 | blk.5.ffn_norm.weight | Block 5 Feed-Forward Network Normalization (W) | ( ~4K) 3840 | 3840 x 1 x 1 x 1 | F32 | | 146 | blk.5.attn_k_norm.weight | Block 5 Attn_K_Norm (W) | ( 256) 256 | 256 x 1 x 1 x 1 | F32 | | 147 | blk.5.attn_k.weight | Block 5 Attention Key (W) | ( ~8M) 7864320 | 3840 x 2048 x 1 x 1 | F16 | | 148 | blk.5.attn_output.weight | Block 5 Attention Output (W) | (~16M) 15728640 | 4096 x 3840 x 1 x 1 | F16 | | 149 | blk.5.attn_q_norm.weight | Block 5 Attn_Q_Norm (W) | ( 256) 256 | 256 x 1 x 1 x 1 | F32 | | 150 | blk.5.attn_q.weight | Block 5 Attention Query (W) | (~16M) 15728640 | 3840 x 4096 x 1 x 1 | F16 | | 151 | blk.5.attn_v.weight | Block 5 Attention Value (W) | ( ~8M) 7864320 | 3840 x 2048 x 1 x 1 | F16 | - Total elements in blk.5: (~224M) 224148992 - Percentage of total elements: 1.91% ### Block 6 Tensor Group : ~224M Elements | T_ID | Tensor Layer Name | Human Friendly Tensor Layer Name | Elements | Shape | Type | |-----:|:---------------------------------|:-----------------------------------------------|:----------------|:----------------------|:-----| | 152 | blk.6.attn_norm.weight | Block 6 Attention Normalization (W) | ( ~4K) 3840 | 3840 x 1 x 1 x 1 | F32 | | 153 | blk.6.ffn_down.weight | Block 6 Feed-Forward Network "Down" (W) | (~59M) 58982400 | 15360 x 3840 x 1 x 1 | F16 | | 154 | blk.6.ffn_gate.weight | Block 6 Feed-Forward Network "Gate" (W) | (~59M) 58982400 | 3840 x 15360 x 1 x 1 | F16 | | 155 | blk.6.ffn_up.weight | Block 6 Feed-Forward Network "Up" (W) | (~59M) 58982400 | 3840 x 15360 x 1 x 1 | F16 | | 156 | blk.6.post_attention_norm.weight | Block 6 Post_Attention_Norm (W) | ( ~4K) 3840 | 3840 x 1 x 1 x 1 | F32 | | 157 | blk.6.post_ffw_norm.weight | Block 6 Post_Ffw_Norm (W) | ( ~4K) 3840 | 3840 x 1 x 1 x 1 | F32 | | 158 | blk.6.ffn_norm.weight | Block 6 Feed-Forward Network Normalization (W) | ( ~4K) 3840 | 3840 x 1 x 1 x 1 | F32 | | 159 | blk.6.attn_k_norm.weight | Block 6 Attn_K_Norm (W) | ( 256) 256 | 256 x 1 x 1 x 1 | F32 | | 160 | blk.6.attn_k.weight | Block 6 Attention Key (W) | ( ~8M) 7864320 | 3840 x 2048 x 1 x 1 | F16 | | 161 | blk.6.attn_output.weight | Block 6 Attention Output (W) | (~16M) 15728640 | 4096 x 3840 x 1 x 1 | F16 | | 162 | blk.6.attn_q_norm.weight | Block 6 Attn_Q_Norm (W) | ( 256) 256 | 256 x 1 x 1 x 1 | F32 | | 163 | blk.6.attn_q.weight | Block 6 Attention Query (W) | (~16M) 15728640 | 3840 x 4096 x 1 x 1 | F16 | | 164 | blk.6.attn_v.weight | Block 6 Attention Value (W) | ( ~8M) 7864320 | 3840 x 2048 x 1 x 1 | F16 | - Total elements in blk.6: (~224M) 224148992 - Percentage of total elements: 1.91% ### Block 7 Tensor Group : ~224M Elements | T_ID | Tensor Layer Name | Human Friendly Tensor Layer Name | Elements | Shape | Type | |-----:|:---------------------------------|:-----------------------------------------------|:----------------|:----------------------|:-----| | 165 | blk.7.attn_norm.weight | Block 7 Attention Normalization (W) | ( ~4K) 3840 | 3840 x 1 x 1 x 1 | F32 | | 166 | blk.7.ffn_down.weight | Block 7 Feed-Forward Network "Down" (W) | (~59M) 58982400 | 15360 x 3840 x 1 x 1 | F16 | | 167 | blk.7.ffn_gate.weight | Block 7 Feed-Forward Network "Gate" (W) | (~59M) 58982400 | 3840 x 15360 x 1 x 1 | F16 | | 168 | blk.7.ffn_up.weight | Block 7 Feed-Forward Network "Up" (W) | (~59M) 58982400 | 3840 x 15360 x 1 x 1 | F16 | | 169 | blk.7.post_attention_norm.weight | Block 7 Post_Attention_Norm (W) | ( ~4K) 3840 | 3840 x 1 x 1 x 1 | F32 | | 170 | blk.7.post_ffw_norm.weight | Block 7 Post_Ffw_Norm (W) | ( ~4K) 3840 | 3840 x 1 x 1 x 1 | F32 | | 171 | blk.7.ffn_norm.weight | Block 7 Feed-Forward Network Normalization (W) | ( ~4K) 3840 | 3840 x 1 x 1 x 1 | F32 | | 172 | blk.7.attn_k_norm.weight | Block 7 Attn_K_Norm (W) | ( 256) 256 | 256 x 1 x 1 x 1 | F32 | | 173 | blk.7.attn_k.weight | Block 7 Attention Key (W) | ( ~8M) 7864320 | 3840 x 2048 x 1 x 1 | F16 | | 174 | blk.7.attn_output.weight | Block 7 Attention Output (W) | (~16M) 15728640 | 4096 x 3840 x 1 x 1 | F16 | | 175 | blk.7.attn_q_norm.weight | Block 7 Attn_Q_Norm (W) | ( 256) 256 | 256 x 1 x 1 x 1 | F32 | | 176 | blk.7.attn_q.weight | Block 7 Attention Query (W) | (~16M) 15728640 | 3840 x 4096 x 1 x 1 | F16 | | 177 | blk.7.attn_v.weight | Block 7 Attention Value (W) | ( ~8M) 7864320 | 3840 x 2048 x 1 x 1 | F16 | - Total elements in blk.7: (~224M) 224148992 - Percentage of total elements: 1.91% ### Block 8 Tensor Group : ~224M Elements | T_ID | Tensor Layer Name | Human Friendly Tensor Layer Name | Elements | Shape | Type | |-----:|:---------------------------------|:-----------------------------------------------|:----------------|:----------------------|:-----| | 178 | blk.8.attn_norm.weight | Block 8 Attention Normalization (W) | ( ~4K) 3840 | 3840 x 1 x 1 x 1 | F32 | | 179 | blk.8.ffn_down.weight | Block 8 Feed-Forward Network "Down" (W) | (~59M) 58982400 | 15360 x 3840 x 1 x 1 | F16 | | 180 | blk.8.ffn_gate.weight | Block 8 Feed-Forward Network "Gate" (W) | (~59M) 58982400 | 3840 x 15360 x 1 x 1 | F16 | | 181 | blk.8.ffn_up.weight | Block 8 Feed-Forward Network "Up" (W) | (~59M) 58982400 | 3840 x 15360 x 1 x 1 | F16 | | 182 | blk.8.post_attention_norm.weight | Block 8 Post_Attention_Norm (W) | ( ~4K) 3840 | 3840 x 1 x 1 x 1 | F32 | | 183 | blk.8.post_ffw_norm.weight | Block 8 Post_Ffw_Norm (W) | ( ~4K) 3840 | 3840 x 1 x 1 x 1 | F32 | | 184 | blk.8.ffn_norm.weight | Block 8 Feed-Forward Network Normalization (W) | ( ~4K) 3840 | 3840 x 1 x 1 x 1 | F32 | | 185 | blk.8.attn_k_norm.weight | Block 8 Attn_K_Norm (W) | ( 256) 256 | 256 x 1 x 1 x 1 | F32 | | 186 | blk.8.attn_k.weight | Block 8 Attention Key (W) | ( ~8M) 7864320 | 3840 x 2048 x 1 x 1 | F16 | | 187 | blk.8.attn_output.weight | Block 8 Attention Output (W) | (~16M) 15728640 | 4096 x 3840 x 1 x 1 | F16 | | 188 | blk.8.attn_q_norm.weight | Block 8 Attn_Q_Norm (W) | ( 256) 256 | 256 x 1 x 1 x 1 | F32 | | 189 | blk.8.attn_q.weight | Block 8 Attention Query (W) | (~16M) 15728640 | 3840 x 4096 x 1 x 1 | F16 | | 190 | blk.8.attn_v.weight | Block 8 Attention Value (W) | ( ~8M) 7864320 | 3840 x 2048 x 1 x 1 | F16 | - Total elements in blk.8: (~224M) 224148992 - Percentage of total elements: 1.91% ### Block 9 Tensor Group : ~224M Elements | T_ID | Tensor Layer Name | Human Friendly Tensor Layer Name | Elements | Shape | Type | |-----:|:---------------------------------|:-----------------------------------------------|:----------------|:----------------------|:-----| | 191 | blk.9.attn_norm.weight | Block 9 Attention Normalization (W) | ( ~4K) 3840 | 3840 x 1 x 1 x 1 | F32 | | 192 | blk.9.ffn_down.weight | Block 9 Feed-Forward Network "Down" (W) | (~59M) 58982400 | 15360 x 3840 x 1 x 1 | F16 | | 193 | blk.9.ffn_gate.weight | Block 9 Feed-Forward Network "Gate" (W) | (~59M) 58982400 | 3840 x 15360 x 1 x 1 | F16 | | 194 | blk.9.ffn_up.weight | Block 9 Feed-Forward Network "Up" (W) | (~59M) 58982400 | 3840 x 15360 x 1 x 1 | F16 | | 195 | blk.9.post_attention_norm.weight | Block 9 Post_Attention_Norm (W) | ( ~4K) 3840 | 3840 x 1 x 1 x 1 | F32 | | 196 | blk.9.post_ffw_norm.weight | Block 9 Post_Ffw_Norm (W) | ( ~4K) 3840 | 3840 x 1 x 1 x 1 | F32 | | 197 | blk.9.ffn_norm.weight | Block 9 Feed-Forward Network Normalization (W) | ( ~4K) 3840 | 3840 x 1 x 1 x 1 | F32 | | 198 | blk.9.attn_k_norm.weight | Block 9 Attn_K_Norm (W) | ( 256) 256 | 256 x 1 x 1 x 1 | F32 | | 199 | blk.9.attn_k.weight | Block 9 Attention Key (W) | ( ~8M) 7864320 | 3840 x 2048 x 1 x 1 | F16 | | 200 | blk.9.attn_output.weight | Block 9 Attention Output (W) | (~16M) 15728640 | 4096 x 3840 x 1 x 1 | F16 | | 201 | blk.9.attn_q_norm.weight | Block 9 Attn_Q_Norm (W) | ( 256) 256 | 256 x 1 x 1 x 1 | F32 | | 202 | blk.9.attn_q.weight | Block 9 Attention Query (W) | (~16M) 15728640 | 3840 x 4096 x 1 x 1 | F16 | | 203 | blk.9.attn_v.weight | Block 9 Attention Value (W) | ( ~8M) 7864320 | 3840 x 2048 x 1 x 1 | F16 | - Total elements in blk.9: (~224M) 224148992 - Percentage of total elements: 1.91% ### Block 16 Tensor Group : ~224M Elements | T_ID | Tensor Layer Name | Human Friendly Tensor Layer Name | Elements | Shape | Type | |-----:|:----------------------------------|:------------------------------------------------|:----------------|:----------------------|:-----| | 209 | blk.16.attn_norm.weight | Block 16 Attention Normalization (W) | ( ~4K) 3840 | 3840 x 1 x 1 x 1 | F32 | | 210 | blk.16.ffn_down.weight | Block 16 Feed-Forward Network "Down" (W) | (~59M) 58982400 | 15360 x 3840 x 1 x 1 | F16 | | 211 | blk.16.ffn_gate.weight | Block 16 Feed-Forward Network "Gate" (W) | (~59M) 58982400 | 3840 x 15360 x 1 x 1 | F16 | | 212 | blk.16.ffn_up.weight | Block 16 Feed-Forward Network "Up" (W) | (~59M) 58982400 | 3840 x 15360 x 1 x 1 | F16 | | 213 | blk.16.post_attention_norm.weight | Block 16 Post_Attention_Norm (W) | ( ~4K) 3840 | 3840 x 1 x 1 x 1 | F32 | | 214 | blk.16.post_ffw_norm.weight | Block 16 Post_Ffw_Norm (W) | ( ~4K) 3840 | 3840 x 1 x 1 x 1 | F32 | | 215 | blk.16.ffn_norm.weight | Block 16 Feed-Forward Network Normalization (W) | ( ~4K) 3840 | 3840 x 1 x 1 x 1 | F32 | | 216 | blk.16.attn_k_norm.weight | Block 16 Attn_K_Norm (W) | ( 256) 256 | 256 x 1 x 1 x 1 | F32 | | 217 | blk.16.attn_k.weight | Block 16 Attention Key (W) | ( ~8M) 7864320 | 3840 x 2048 x 1 x 1 | F16 | | 218 | blk.16.attn_output.weight | Block 16 Attention Output (W) | (~16M) 15728640 | 4096 x 3840 x 1 x 1 | F16 | | 219 | blk.16.attn_q_norm.weight | Block 16 Attn_Q_Norm (W) | ( 256) 256 | 256 x 1 x 1 x 1 | F32 | | 220 | blk.16.attn_q.weight | Block 16 Attention Query (W) | (~16M) 15728640 | 3840 x 4096 x 1 x 1 | F16 | | 221 | blk.16.attn_v.weight | Block 16 Attention Value (W) | ( ~8M) 7864320 | 3840 x 2048 x 1 x 1 | F16 | - Total elements in blk.16: (~224M) 224148992 - Percentage of total elements: 1.91% ### Block 17 Tensor Group : ~224M Elements | T_ID | Tensor Layer Name | Human Friendly Tensor Layer Name | Elements | Shape | Type | |-----:|:----------------------------------|:------------------------------------------------|:----------------|:----------------------|:-----| | 222 | blk.17.attn_norm.weight | Block 17 Attention Normalization (W) | ( ~4K) 3840 | 3840 x 1 x 1 x 1 | F32 | | 223 | blk.17.ffn_down.weight | Block 17 Feed-Forward Network "Down" (W) | (~59M) 58982400 | 15360 x 3840 x 1 x 1 | F16 | | 224 | blk.17.ffn_gate.weight | Block 17 Feed-Forward Network "Gate" (W) | (~59M) 58982400 | 3840 x 15360 x 1 x 1 | F16 | | 225 | blk.17.ffn_up.weight | Block 17 Feed-Forward Network "Up" (W) | (~59M) 58982400 | 3840 x 15360 x 1 x 1 | F16 | | 226 | blk.17.post_attention_norm.weight | Block 17 Post_Attention_Norm (W) | ( ~4K) 3840 | 3840 x 1 x 1 x 1 | F32 | | 227 | blk.17.post_ffw_norm.weight | Block 17 Post_Ffw_Norm (W) | ( ~4K) 3840 | 3840 x 1 x 1 x 1 | F32 | | 228 | blk.17.ffn_norm.weight | Block 17 Feed-Forward Network Normalization (W) | ( ~4K) 3840 | 3840 x 1 x 1 x 1 | F32 | | 229 | blk.17.attn_k_norm.weight | Block 17 Attn_K_Norm (W) | ( 256) 256 | 256 x 1 x 1 x 1 | F32 | | 230 | blk.17.attn_k.weight | Block 17 Attention Key (W) | ( ~8M) 7864320 | 3840 x 2048 x 1 x 1 | F16 | | 231 | blk.17.attn_output.weight | Block 17 Attention Output (W) | (~16M) 15728640 | 4096 x 3840 x 1 x 1 | F16 | | 232 | blk.17.attn_q_norm.weight | Block 17 Attn_Q_Norm (W) | ( 256) 256 | 256 x 1 x 1 x 1 | F32 | | 233 | blk.17.attn_q.weight | Block 17 Attention Query (W) | (~16M) 15728640 | 3840 x 4096 x 1 x 1 | F16 | | 234 | blk.17.attn_v.weight | Block 17 Attention Value (W) | ( ~8M) 7864320 | 3840 x 2048 x 1 x 1 | F16 | - Total elements in blk.17: (~224M) 224148992 - Percentage of total elements: 1.91% ### Block 18 Tensor Group : ~224M Elements | T_ID | Tensor Layer Name | Human Friendly Tensor Layer Name | Elements | Shape | Type | |-----:|:----------------------------------|:------------------------------------------------|:----------------|:----------------------|:-----| | 235 | blk.18.attn_norm.weight | Block 18 Attention Normalization (W) | ( ~4K) 3840 | 3840 x 1 x 1 x 1 | F32 | | 236 | blk.18.ffn_down.weight | Block 18 Feed-Forward Network "Down" (W) | (~59M) 58982400 | 15360 x 3840 x 1 x 1 | F16 | | 237 | blk.18.ffn_gate.weight | Block 18 Feed-Forward Network "Gate" (W) | (~59M) 58982400 | 3840 x 15360 x 1 x 1 | F16 | | 238 | blk.18.ffn_up.weight | Block 18 Feed-Forward Network "Up" (W) | (~59M) 58982400 | 3840 x 15360 x 1 x 1 | F16 | | 239 | blk.18.post_attention_norm.weight | Block 18 Post_Attention_Norm (W) | ( ~4K) 3840 | 3840 x 1 x 1 x 1 | F32 | | 240 | blk.18.post_ffw_norm.weight | Block 18 Post_Ffw_Norm (W) | ( ~4K) 3840 | 3840 x 1 x 1 x 1 | F32 | | 241 | blk.18.ffn_norm.weight | Block 18 Feed-Forward Network Normalization (W) | ( ~4K) 3840 | 3840 x 1 x 1 x 1 | F32 | | 242 | blk.18.attn_k_norm.weight | Block 18 Attn_K_Norm (W) | ( 256) 256 | 256 x 1 x 1 x 1 | F32 | | 243 | blk.18.attn_k.weight | Block 18 Attention Key (W) | ( ~8M) 7864320 | 3840 x 2048 x 1 x 1 | F16 | | 244 | blk.18.attn_output.weight | Block 18 Attention Output (W) | (~16M) 15728640 | 4096 x 3840 x 1 x 1 | F16 | | 245 | blk.18.attn_q_norm.weight | Block 18 Attn_Q_Norm (W) | ( 256) 256 | 256 x 1 x 1 x 1 | F32 | | 246 | blk.18.attn_q.weight | Block 18 Attention Query (W) | (~16M) 15728640 | 3840 x 4096 x 1 x 1 | F16 | | 247 | blk.18.attn_v.weight | Block 18 Attention Value (W) | ( ~8M) 7864320 | 3840 x 2048 x 1 x 1 | F16 | - Total elements in blk.18: (~224M) 224148992 - Percentage of total elements: 1.91% ### Block 19 Tensor Group : ~224M Elements | T_ID | Tensor Layer Name | Human Friendly Tensor Layer Name | Elements | Shape | Type | |-----:|:----------------------------------|:------------------------------------------------|:----------------|:----------------------|:-----| | 248 | blk.19.attn_norm.weight | Block 19 Attention Normalization (W) | ( ~4K) 3840 | 3840 x 1 x 1 x 1 | F32 | | 249 | blk.19.ffn_down.weight | Block 19 Feed-Forward Network "Down" (W) | (~59M) 58982400 | 15360 x 3840 x 1 x 1 | F16 | | 250 | blk.19.ffn_gate.weight | Block 19 Feed-Forward Network "Gate" (W) | (~59M) 58982400 | 3840 x 15360 x 1 x 1 | F16 | | 251 | blk.19.ffn_up.weight | Block 19 Feed-Forward Network "Up" (W) | (~59M) 58982400 | 3840 x 15360 x 1 x 1 | F16 | | 252 | blk.19.post_attention_norm.weight | Block 19 Post_Attention_Norm (W) | ( ~4K) 3840 | 3840 x 1 x 1 x 1 | F32 | | 253 | blk.19.post_ffw_norm.weight | Block 19 Post_Ffw_Norm (W) | ( ~4K) 3840 | 3840 x 1 x 1 x 1 | F32 | | 254 | blk.19.ffn_norm.weight | Block 19 Feed-Forward Network Normalization (W) | ( ~4K) 3840 | 3840 x 1 x 1 x 1 | F32 | | 255 | blk.19.attn_k_norm.weight | Block 19 Attn_K_Norm (W) | ( 256) 256 | 256 x 1 x 1 x 1 | F32 | | 256 | blk.19.attn_k.weight | Block 19 Attention Key (W) | ( ~8M) 7864320 | 3840 x 2048 x 1 x 1 | F16 | | 257 | blk.19.attn_output.weight | Block 19 Attention Output (W) | (~16M) 15728640 | 4096 x 3840 x 1 x 1 | F16 | | 258 | blk.19.attn_q_norm.weight | Block 19 Attn_Q_Norm (W) | ( 256) 256 | 256 x 1 x 1 x 1 | F32 | | 259 | blk.19.attn_q.weight | Block 19 Attention Query (W) | (~16M) 15728640 | 3840 x 4096 x 1 x 1 | F16 | | 260 | blk.19.attn_v.weight | Block 19 Attention Value (W) | ( ~8M) 7864320 | 3840 x 2048 x 1 x 1 | F16 | - Total elements in blk.19: (~224M) 224148992 - Percentage of total elements: 1.91% ### Block 20 Tensor Group : ~224M Elements | T_ID | Tensor Layer Name | Human Friendly Tensor Layer Name | Elements | Shape | Type | |-----:|:----------------------------------|:------------------------------------------------|:----------------|:----------------------|:-----| | 261 | blk.20.attn_norm.weight | Block 20 Attention Normalization (W) | ( ~4K) 3840 | 3840 x 1 x 1 x 1 | F32 | | 262 | blk.20.ffn_down.weight | Block 20 Feed-Forward Network "Down" (W) | (~59M) 58982400 | 15360 x 3840 x 1 x 1 | F16 | | 263 | blk.20.ffn_gate.weight | Block 20 Feed-Forward Network "Gate" (W) | (~59M) 58982400 | 3840 x 15360 x 1 x 1 | F16 | | 264 | blk.20.ffn_up.weight | Block 20 Feed-Forward Network "Up" (W) | (~59M) 58982400 | 3840 x 15360 x 1 x 1 | F16 | | 265 | blk.20.post_attention_norm.weight | Block 20 Post_Attention_Norm (W) | ( ~4K) 3840 | 3840 x 1 x 1 x 1 | F32 | | 266 | blk.20.post_ffw_norm.weight | Block 20 Post_Ffw_Norm (W) | ( ~4K) 3840 | 3840 x 1 x 1 x 1 | F32 | | 267 | blk.20.ffn_norm.weight | Block 20 Feed-Forward Network Normalization (W) | ( ~4K) 3840 | 3840 x 1 x 1 x 1 | F32 | | 268 | blk.20.attn_k_norm.weight | Block 20 Attn_K_Norm (W) | ( 256) 256 | 256 x 1 x 1 x 1 | F32 | | 269 | blk.20.attn_k.weight | Block 20 Attention Key (W) | ( ~8M) 7864320 | 3840 x 2048 x 1 x 1 | F16 | | 270 | blk.20.attn_output.weight | Block 20 Attention Output (W) | (~16M) 15728640 | 4096 x 3840 x 1 x 1 | F16 | | 271 | blk.20.attn_q_norm.weight | Block 20 Attn_Q_Norm (W) | ( 256) 256 | 256 x 1 x 1 x 1 | F32 | | 272 | blk.20.attn_q.weight | Block 20 Attention Query (W) | (~16M) 15728640 | 3840 x 4096 x 1 x 1 | F16 | | 273 | blk.20.attn_v.weight | Block 20 Attention Value (W) | ( ~8M) 7864320 | 3840 x 2048 x 1 x 1 | F16 | - Total elements in blk.20: (~224M) 224148992 - Percentage of total elements: 1.91% ### Block 21 Tensor Group : ~224M Elements | T_ID | Tensor Layer Name | Human Friendly Tensor Layer Name | Elements | Shape | Type | |-----:|:----------------------------------|:------------------------------------------------|:----------------|:----------------------|:-----| | 274 | blk.21.attn_norm.weight | Block 21 Attention Normalization (W) | ( ~4K) 3840 | 3840 x 1 x 1 x 1 | F32 | | 275 | blk.21.ffn_down.weight | Block 21 Feed-Forward Network "Down" (W) | (~59M) 58982400 | 15360 x 3840 x 1 x 1 | F16 | | 276 | blk.21.ffn_gate.weight | Block 21 Feed-Forward Network "Gate" (W) | (~59M) 58982400 | 3840 x 15360 x 1 x 1 | F16 | | 277 | blk.21.ffn_up.weight | Block 21 Feed-Forward Network "Up" (W) | (~59M) 58982400 | 3840 x 15360 x 1 x 1 | F16 | | 278 | blk.21.post_attention_norm.weight | Block 21 Post_Attention_Norm (W) | ( ~4K) 3840 | 3840 x 1 x 1 x 1 | F32 | | 279 | blk.21.post_ffw_norm.weight | Block 21 Post_Ffw_Norm (W) | ( ~4K) 3840 | 3840 x 1 x 1 x 1 | F32 | | 280 | blk.21.ffn_norm.weight | Block 21 Feed-Forward Network Normalization (W) | ( ~4K) 3840 | 3840 x 1 x 1 x 1 | F32 | | 281 | blk.21.attn_k_norm.weight | Block 21 Attn_K_Norm (W) | ( 256) 256 | 256 x 1 x 1 x 1 | F32 | | 282 | blk.21.attn_k.weight | Block 21 Attention Key (W) | ( ~8M) 7864320 | 3840 x 2048 x 1 x 1 | F16 | | 283 | blk.21.attn_output.weight | Block 21 Attention Output (W) | (~16M) 15728640 | 4096 x 3840 x 1 x 1 | F16 | | 284 | blk.21.attn_q_norm.weight | Block 21 Attn_Q_Norm (W) | ( 256) 256 | 256 x 1 x 1 x 1 | F32 | | 285 | blk.21.attn_q.weight | Block 21 Attention Query (W) | (~16M) 15728640 | 3840 x 4096 x 1 x 1 | F16 | | 286 | blk.21.attn_v.weight | Block 21 Attention Value (W) | ( ~8M) 7864320 | 3840 x 2048 x 1 x 1 | F16 | - Total elements in blk.21: (~224M) 224148992 - Percentage of total elements: 1.91% ### Block 22 Tensor Group : ~224M Elements | T_ID | Tensor Layer Name | Human Friendly Tensor Layer Name | Elements | Shape | Type | |-----:|:----------------------------------|:------------------------------------------------|:----------------|:----------------------|:-----| | 287 | blk.22.attn_norm.weight | Block 22 Attention Normalization (W) | ( ~4K) 3840 | 3840 x 1 x 1 x 1 | F32 | | 288 | blk.22.ffn_down.weight | Block 22 Feed-Forward Network "Down" (W) | (~59M) 58982400 | 15360 x 3840 x 1 x 1 | F16 | | 289 | blk.22.ffn_gate.weight | Block 22 Feed-Forward Network "Gate" (W) | (~59M) 58982400 | 3840 x 15360 x 1 x 1 | F16 | | 290 | blk.22.ffn_up.weight | Block 22 Feed-Forward Network "Up" (W) | (~59M) 58982400 | 3840 x 15360 x 1 x 1 | F16 | | 291 | blk.22.post_attention_norm.weight | Block 22 Post_Attention_Norm (W) | ( ~4K) 3840 | 3840 x 1 x 1 x 1 | F32 | | 292 | blk.22.post_ffw_norm.weight | Block 22 Post_Ffw_Norm (W) | ( ~4K) 3840 | 3840 x 1 x 1 x 1 | F32 | | 293 | blk.22.ffn_norm.weight | Block 22 Feed-Forward Network Normalization (W) | ( ~4K) 3840 | 3840 x 1 x 1 x 1 | F32 | | 294 | blk.22.attn_k_norm.weight | Block 22 Attn_K_Norm (W) | ( 256) 256 | 256 x 1 x 1 x 1 | F32 | | 295 | blk.22.attn_k.weight | Block 22 Attention Key (W) | ( ~8M) 7864320 | 3840 x 2048 x 1 x 1 | F16 | | 296 | blk.22.attn_output.weight | Block 22 Attention Output (W) | (~16M) 15728640 | 4096 x 3840 x 1 x 1 | F16 | | 297 | blk.22.attn_q_norm.weight | Block 22 Attn_Q_Norm (W) | ( 256) 256 | 256 x 1 x 1 x 1 | F32 | | 298 | blk.22.attn_q.weight | Block 22 Attention Query (W) | (~16M) 15728640 | 3840 x 4096 x 1 x 1 | F16 | | 299 | blk.22.attn_v.weight | Block 22 Attention Value (W) | ( ~8M) 7864320 | 3840 x 2048 x 1 x 1 | F16 | - Total elements in blk.22: (~224M) 224148992 - Percentage of total elements: 1.91% ### Block 23 Tensor Group : ~224M Elements | T_ID | Tensor Layer Name | Human Friendly Tensor Layer Name | Elements | Shape | Type | |-----:|:----------------------------------|:------------------------------------------------|:----------------|:----------------------|:-----| | 300 | blk.23.attn_norm.weight | Block 23 Attention Normalization (W) | ( ~4K) 3840 | 3840 x 1 x 1 x 1 | F32 | | 301 | blk.23.ffn_down.weight | Block 23 Feed-Forward Network "Down" (W) | (~59M) 58982400 | 15360 x 3840 x 1 x 1 | F16 | | 302 | blk.23.ffn_gate.weight | Block 23 Feed-Forward Network "Gate" (W) | (~59M) 58982400 | 3840 x 15360 x 1 x 1 | F16 | | 303 | blk.23.ffn_up.weight | Block 23 Feed-Forward Network "Up" (W) | (~59M) 58982400 | 3840 x 15360 x 1 x 1 | F16 | | 304 | blk.23.post_attention_norm.weight | Block 23 Post_Attention_Norm (W) | ( ~4K) 3840 | 3840 x 1 x 1 x 1 | F32 | | 305 | blk.23.post_ffw_norm.weight | Block 23 Post_Ffw_Norm (W) | ( ~4K) 3840 | 3840 x 1 x 1 x 1 | F32 | | 306 | blk.23.ffn_norm.weight | Block 23 Feed-Forward Network Normalization (W) | ( ~4K) 3840 | 3840 x 1 x 1 x 1 | F32 | | 307 | blk.23.attn_k_norm.weight | Block 23 Attn_K_Norm (W) | ( 256) 256 | 256 x 1 x 1 x 1 | F32 | | 308 | blk.23.attn_k.weight | Block 23 Attention Key (W) | ( ~8M) 7864320 | 3840 x 2048 x 1 x 1 | F16 | | 309 | blk.23.attn_output.weight | Block 23 Attention Output (W) | (~16M) 15728640 | 4096 x 3840 x 1 x 1 | F16 | | 310 | blk.23.attn_q_norm.weight | Block 23 Attn_Q_Norm (W) | ( 256) 256 | 256 x 1 x 1 x 1 | F32 | | 311 | blk.23.attn_q.weight | Block 23 Attention Query (W) | (~16M) 15728640 | 3840 x 4096 x 1 x 1 | F16 | | 312 | blk.23.attn_v.weight | Block 23 Attention Value (W) | ( ~8M) 7864320 | 3840 x 2048 x 1 x 1 | F16 | - Total elements in blk.23: (~224M) 224148992 - Percentage of total elements: 1.91% ### Block 24 Tensor Group : ~224M Elements | T_ID | Tensor Layer Name | Human Friendly Tensor Layer Name | Elements | Shape | Type | |-----:|:----------------------------------|:------------------------------------------------|:----------------|:----------------------|:-----| | 313 | blk.24.attn_norm.weight | Block 24 Attention Normalization (W) | ( ~4K) 3840 | 3840 x 1 x 1 x 1 | F32 | | 314 | blk.24.ffn_down.weight | Block 24 Feed-Forward Network "Down" (W) | (~59M) 58982400 | 15360 x 3840 x 1 x 1 | F16 | | 315 | blk.24.ffn_gate.weight | Block 24 Feed-Forward Network "Gate" (W) | (~59M) 58982400 | 3840 x 15360 x 1 x 1 | F16 | | 316 | blk.24.ffn_up.weight | Block 24 Feed-Forward Network "Up" (W) | (~59M) 58982400 | 3840 x 15360 x 1 x 1 | F16 | | 317 | blk.24.post_attention_norm.weight | Block 24 Post_Attention_Norm (W) | ( ~4K) 3840 | 3840 x 1 x 1 x 1 | F32 | | 318 | blk.24.post_ffw_norm.weight | Block 24 Post_Ffw_Norm (W) | ( ~4K) 3840 | 3840 x 1 x 1 x 1 | F32 | | 319 | blk.24.ffn_norm.weight | Block 24 Feed-Forward Network Normalization (W) | ( ~4K) 3840 | 3840 x 1 x 1 x 1 | F32 | | 320 | blk.24.attn_k_norm.weight | Block 24 Attn_K_Norm (W) | ( 256) 256 | 256 x 1 x 1 x 1 | F32 | | 321 | blk.24.attn_k.weight | Block 24 Attention Key (W) | ( ~8M) 7864320 | 3840 x 2048 x 1 x 1 | F16 | | 322 | blk.24.attn_output.weight | Block 24 Attention Output (W) | (~16M) 15728640 | 4096 x 3840 x 1 x 1 | F16 | | 323 | blk.24.attn_q_norm.weight | Block 24 Attn_Q_Norm (W) | ( 256) 256 | 256 x 1 x 1 x 1 | F32 | | 324 | blk.24.attn_q.weight | Block 24 Attention Query (W) | (~16M) 15728640 | 3840 x 4096 x 1 x 1 | F16 | | 325 | blk.24.attn_v.weight | Block 24 Attention Value (W) | ( ~8M) 7864320 | 3840 x 2048 x 1 x 1 | F16 | - Total elements in blk.24: (~224M) 224148992 - Percentage of total elements: 1.91% ### Block 25 Tensor Group : ~224M Elements | T_ID | Tensor Layer Name | Human Friendly Tensor Layer Name | Elements | Shape | Type | |-----:|:----------------------------------|:------------------------------------------------|:----------------|:----------------------|:-----| | 326 | blk.25.attn_norm.weight | Block 25 Attention Normalization (W) | ( ~4K) 3840 | 3840 x 1 x 1 x 1 | F32 | | 327 | blk.25.ffn_down.weight | Block 25 Feed-Forward Network "Down" (W) | (~59M) 58982400 | 15360 x 3840 x 1 x 1 | F16 | | 328 | blk.25.ffn_gate.weight | Block 25 Feed-Forward Network "Gate" (W) | (~59M) 58982400 | 3840 x 15360 x 1 x 1 | F16 | | 329 | blk.25.ffn_up.weight | Block 25 Feed-Forward Network "Up" (W) | (~59M) 58982400 | 3840 x 15360 x 1 x 1 | F16 | | 330 | blk.25.post_attention_norm.weight | Block 25 Post_Attention_Norm (W) | ( ~4K) 3840 | 3840 x 1 x 1 x 1 | F32 | | 331 | blk.25.post_ffw_norm.weight | Block 25 Post_Ffw_Norm (W) | ( ~4K) 3840 | 3840 x 1 x 1 x 1 | F32 | | 332 | blk.25.ffn_norm.weight | Block 25 Feed-Forward Network Normalization (W) | ( ~4K) 3840 | 3840 x 1 x 1 x 1 | F32 | | 333 | blk.25.attn_k_norm.weight | Block 25 Attn_K_Norm (W) | ( 256) 256 | 256 x 1 x 1 x 1 | F32 | | 334 | blk.25.attn_k.weight | Block 25 Attention Key (W) | ( ~8M) 7864320 | 3840 x 2048 x 1 x 1 | F16 | | 335 | blk.25.attn_output.weight | Block 25 Attention Output (W) | (~16M) 15728640 | 4096 x 3840 x 1 x 1 | F16 | | 336 | blk.25.attn_q_norm.weight | Block 25 Attn_Q_Norm (W) | ( 256) 256 | 256 x 1 x 1 x 1 | F32 | | 337 | blk.25.attn_q.weight | Block 25 Attention Query (W) | (~16M) 15728640 | 3840 x 4096 x 1 x 1 | F16 | | 338 | blk.25.attn_v.weight | Block 25 Attention Value (W) | ( ~8M) 7864320 | 3840 x 2048 x 1 x 1 | F16 | - Total elements in blk.25: (~224M) 224148992 - Percentage of total elements: 1.91% ### Block 26 Tensor Group : ~224M Elements | T_ID | Tensor Layer Name | Human Friendly Tensor Layer Name | Elements | Shape | Type | |-----:|:----------------------------------|:------------------------------------------------|:----------------|:----------------------|:-----| | 339 | blk.26.ffn_gate.weight | Block 26 Feed-Forward Network "Gate" (W) | (~59M) 58982400 | 3840 x 15360 x 1 x 1 | F16 | | 340 | blk.26.ffn_up.weight | Block 26 Feed-Forward Network "Up" (W) | (~59M) 58982400 | 3840 x 15360 x 1 x 1 | F16 | | 341 | blk.26.attn_k_norm.weight | Block 26 Attn_K_Norm (W) | ( 256) 256 | 256 x 1 x 1 x 1 | F32 | | 342 | blk.26.attn_k.weight | Block 26 Attention Key (W) | ( ~8M) 7864320 | 3840 x 2048 x 1 x 1 | F16 | | 343 | blk.26.attn_output.weight | Block 26 Attention Output (W) | (~16M) 15728640 | 4096 x 3840 x 1 x 1 | F16 | | 344 | blk.26.attn_q_norm.weight | Block 26 Attn_Q_Norm (W) | ( 256) 256 | 256 x 1 x 1 x 1 | F32 | | 345 | blk.26.attn_q.weight | Block 26 Attention Query (W) | (~16M) 15728640 | 3840 x 4096 x 1 x 1 | F16 | | 346 | blk.26.attn_v.weight | Block 26 Attention Value (W) | ( ~8M) 7864320 | 3840 x 2048 x 1 x 1 | F16 | | 347 | blk.26.attn_norm.weight | Block 26 Attention Normalization (W) | ( ~4K) 3840 | 3840 x 1 x 1 x 1 | F32 | | 348 | blk.26.ffn_down.weight | Block 26 Feed-Forward Network "Down" (W) | (~59M) 58982400 | 15360 x 3840 x 1 x 1 | F16 | | 349 | blk.26.post_attention_norm.weight | Block 26 Post_Attention_Norm (W) | ( ~4K) 3840 | 3840 x 1 x 1 x 1 | F32 | | 350 | blk.26.post_ffw_norm.weight | Block 26 Post_Ffw_Norm (W) | ( ~4K) 3840 | 3840 x 1 x 1 x 1 | F32 | | 351 | blk.26.ffn_norm.weight | Block 26 Feed-Forward Network Normalization (W) | ( ~4K) 3840 | 3840 x 1 x 1 x 1 | F32 | - Total elements in blk.26: (~224M) 224148992 - Percentage of total elements: 1.91% ### Block 27 Tensor Group : ~224M Elements | T_ID | Tensor Layer Name | Human Friendly Tensor Layer Name | Elements | Shape | Type | |-----:|:----------------------------------|:------------------------------------------------|:----------------|:----------------------|:-----| | 352 | blk.27.attn_norm.weight | Block 27 Attention Normalization (W) | ( ~4K) 3840 | 3840 x 1 x 1 x 1 | F32 | | 353 | blk.27.ffn_down.weight | Block 27 Feed-Forward Network "Down" (W) | (~59M) 58982400 | 15360 x 3840 x 1 x 1 | F16 | | 354 | blk.27.ffn_gate.weight | Block 27 Feed-Forward Network "Gate" (W) | (~59M) 58982400 | 3840 x 15360 x 1 x 1 | F16 | | 355 | blk.27.ffn_up.weight | Block 27 Feed-Forward Network "Up" (W) | (~59M) 58982400 | 3840 x 15360 x 1 x 1 | F16 | | 356 | blk.27.post_attention_norm.weight | Block 27 Post_Attention_Norm (W) | ( ~4K) 3840 | 3840 x 1 x 1 x 1 | F32 | | 357 | blk.27.post_ffw_norm.weight | Block 27 Post_Ffw_Norm (W) | ( ~4K) 3840 | 3840 x 1 x 1 x 1 | F32 | | 358 | blk.27.ffn_norm.weight | Block 27 Feed-Forward Network Normalization (W) | ( ~4K) 3840 | 3840 x 1 x 1 x 1 | F32 | | 359 | blk.27.attn_k_norm.weight | Block 27 Attn_K_Norm (W) | ( 256) 256 | 256 x 1 x 1 x 1 | F32 | | 360 | blk.27.attn_k.weight | Block 27 Attention Key (W) | ( ~8M) 7864320 | 3840 x 2048 x 1 x 1 | F16 | | 361 | blk.27.attn_output.weight | Block 27 Attention Output (W) | (~16M) 15728640 | 4096 x 3840 x 1 x 1 | F16 | | 362 | blk.27.attn_q_norm.weight | Block 27 Attn_Q_Norm (W) | ( 256) 256 | 256 x 1 x 1 x 1 | F32 | | 363 | blk.27.attn_q.weight | Block 27 Attention Query (W) | (~16M) 15728640 | 3840 x 4096 x 1 x 1 | F16 | | 364 | blk.27.attn_v.weight | Block 27 Attention Value (W) | ( ~8M) 7864320 | 3840 x 2048 x 1 x 1 | F16 | - Total elements in blk.27: (~224M) 224148992 - Percentage of total elements: 1.91% ### Block 28 Tensor Group : ~224M Elements | T_ID | Tensor Layer Name | Human Friendly Tensor Layer Name | Elements | Shape | Type | |-----:|:----------------------------------|:------------------------------------------------|:----------------|:----------------------|:-----| | 365 | blk.28.attn_norm.weight | Block 28 Attention Normalization (W) | ( ~4K) 3840 | 3840 x 1 x 1 x 1 | F32 | | 366 | blk.28.ffn_down.weight | Block 28 Feed-Forward Network "Down" (W) | (~59M) 58982400 | 15360 x 3840 x 1 x 1 | F16 | | 367 | blk.28.ffn_gate.weight | Block 28 Feed-Forward Network "Gate" (W) | (~59M) 58982400 | 3840 x 15360 x 1 x 1 | F16 | | 368 | blk.28.ffn_up.weight | Block 28 Feed-Forward Network "Up" (W) | (~59M) 58982400 | 3840 x 15360 x 1 x 1 | F16 | | 369 | blk.28.post_attention_norm.weight | Block 28 Post_Attention_Norm (W) | ( ~4K) 3840 | 3840 x 1 x 1 x 1 | F32 | | 370 | blk.28.post_ffw_norm.weight | Block 28 Post_Ffw_Norm (W) | ( ~4K) 3840 | 3840 x 1 x 1 x 1 | F32 | | 371 | blk.28.ffn_norm.weight | Block 28 Feed-Forward Network Normalization (W) | ( ~4K) 3840 | 3840 x 1 x 1 x 1 | F32 | | 372 | blk.28.attn_k_norm.weight | Block 28 Attn_K_Norm (W) | ( 256) 256 | 256 x 1 x 1 x 1 | F32 | | 373 | blk.28.attn_k.weight | Block 28 Attention Key (W) | ( ~8M) 7864320 | 3840 x 2048 x 1 x 1 | F16 | | 374 | blk.28.attn_output.weight | Block 28 Attention Output (W) | (~16M) 15728640 | 4096 x 3840 x 1 x 1 | F16 | | 375 | blk.28.attn_q_norm.weight | Block 28 Attn_Q_Norm (W) | ( 256) 256 | 256 x 1 x 1 x 1 | F32 | | 376 | blk.28.attn_q.weight | Block 28 Attention Query (W) | (~16M) 15728640 | 3840 x 4096 x 1 x 1 | F16 | | 377 | blk.28.attn_v.weight | Block 28 Attention Value (W) | ( ~8M) 7864320 | 3840 x 2048 x 1 x 1 | F16 | - Total elements in blk.28: (~224M) 224148992 - Percentage of total elements: 1.91% ### Block 29 Tensor Group : ~224M Elements | T_ID | Tensor Layer Name | Human Friendly Tensor Layer Name | Elements | Shape | Type | |-----:|:----------------------------------|:------------------------------------------------|:----------------|:----------------------|:-----| | 378 | blk.29.attn_norm.weight | Block 29 Attention Normalization (W) | ( ~4K) 3840 | 3840 x 1 x 1 x 1 | F32 | | 379 | blk.29.ffn_down.weight | Block 29 Feed-Forward Network "Down" (W) | (~59M) 58982400 | 15360 x 3840 x 1 x 1 | F16 | | 380 | blk.29.ffn_gate.weight | Block 29 Feed-Forward Network "Gate" (W) | (~59M) 58982400 | 3840 x 15360 x 1 x 1 | F16 | | 381 | blk.29.ffn_up.weight | Block 29 Feed-Forward Network "Up" (W) | (~59M) 58982400 | 3840 x 15360 x 1 x 1 | F16 | | 382 | blk.29.post_attention_norm.weight | Block 29 Post_Attention_Norm (W) | ( ~4K) 3840 | 3840 x 1 x 1 x 1 | F32 | | 383 | blk.29.post_ffw_norm.weight | Block 29 Post_Ffw_Norm (W) | ( ~4K) 3840 | 3840 x 1 x 1 x 1 | F32 | | 384 | blk.29.ffn_norm.weight | Block 29 Feed-Forward Network Normalization (W) | ( ~4K) 3840 | 3840 x 1 x 1 x 1 | F32 | | 385 | blk.29.attn_k_norm.weight | Block 29 Attn_K_Norm (W) | ( 256) 256 | 256 x 1 x 1 x 1 | F32 | | 386 | blk.29.attn_k.weight | Block 29 Attention Key (W) | ( ~8M) 7864320 | 3840 x 2048 x 1 x 1 | F16 | | 387 | blk.29.attn_output.weight | Block 29 Attention Output (W) | (~16M) 15728640 | 4096 x 3840 x 1 x 1 | F16 | | 388 | blk.29.attn_q_norm.weight | Block 29 Attn_Q_Norm (W) | ( 256) 256 | 256 x 1 x 1 x 1 | F32 | | 389 | blk.29.attn_q.weight | Block 29 Attention Query (W) | (~16M) 15728640 | 3840 x 4096 x 1 x 1 | F16 | | 390 | blk.29.attn_v.weight | Block 29 Attention Value (W) | ( ~8M) 7864320 | 3840 x 2048 x 1 x 1 | F16 | - Total elements in blk.29: (~224M) 224148992 - Percentage of total elements: 1.91% ### Block 30 Tensor Group : ~224M Elements | T_ID | Tensor Layer Name | Human Friendly Tensor Layer Name | Elements | Shape | Type | |-----:|:----------------------------------|:------------------------------------------------|:----------------|:----------------------|:-----| | 391 | blk.30.attn_norm.weight | Block 30 Attention Normalization (W) | ( ~4K) 3840 | 3840 x 1 x 1 x 1 | F32 | | 392 | blk.30.ffn_down.weight | Block 30 Feed-Forward Network "Down" (W) | (~59M) 58982400 | 15360 x 3840 x 1 x 1 | F16 | | 393 | blk.30.ffn_gate.weight | Block 30 Feed-Forward Network "Gate" (W) | (~59M) 58982400 | 3840 x 15360 x 1 x 1 | F16 | | 394 | blk.30.ffn_up.weight | Block 30 Feed-Forward Network "Up" (W) | (~59M) 58982400 | 3840 x 15360 x 1 x 1 | F16 | | 395 | blk.30.post_attention_norm.weight | Block 30 Post_Attention_Norm (W) | ( ~4K) 3840 | 3840 x 1 x 1 x 1 | F32 | | 396 | blk.30.post_ffw_norm.weight | Block 30 Post_Ffw_Norm (W) | ( ~4K) 3840 | 3840 x 1 x 1 x 1 | F32 | | 397 | blk.30.ffn_norm.weight | Block 30 Feed-Forward Network Normalization (W) | ( ~4K) 3840 | 3840 x 1 x 1 x 1 | F32 | | 398 | blk.30.attn_k_norm.weight | Block 30 Attn_K_Norm (W) | ( 256) 256 | 256 x 1 x 1 x 1 | F32 | | 399 | blk.30.attn_k.weight | Block 30 Attention Key (W) | ( ~8M) 7864320 | 3840 x 2048 x 1 x 1 | F16 | | 400 | blk.30.attn_output.weight | Block 30 Attention Output (W) | (~16M) 15728640 | 4096 x 3840 x 1 x 1 | F16 | | 401 | blk.30.attn_q_norm.weight | Block 30 Attn_Q_Norm (W) | ( 256) 256 | 256 x 1 x 1 x 1 | F32 | | 402 | blk.30.attn_q.weight | Block 30 Attention Query (W) | (~16M) 15728640 | 3840 x 4096 x 1 x 1 | F16 | | 403 | blk.30.attn_v.weight | Block 30 Attention Value (W) | ( ~8M) 7864320 | 3840 x 2048 x 1 x 1 | F16 | - Total elements in blk.30: (~224M) 224148992 - Percentage of total elements: 1.91% ### Block 31 Tensor Group : ~224M Elements | T_ID | Tensor Layer Name | Human Friendly Tensor Layer Name | Elements | Shape | Type | |-----:|:----------------------------------|:------------------------------------------------|:----------------|:----------------------|:-----| | 404 | blk.31.attn_norm.weight | Block 31 Attention Normalization (W) | ( ~4K) 3840 | 3840 x 1 x 1 x 1 | F32 | | 405 | blk.31.ffn_down.weight | Block 31 Feed-Forward Network "Down" (W) | (~59M) 58982400 | 15360 x 3840 x 1 x 1 | F16 | | 406 | blk.31.ffn_gate.weight | Block 31 Feed-Forward Network "Gate" (W) | (~59M) 58982400 | 3840 x 15360 x 1 x 1 | F16 | | 407 | blk.31.ffn_up.weight | Block 31 Feed-Forward Network "Up" (W) | (~59M) 58982400 | 3840 x 15360 x 1 x 1 | F16 | | 408 | blk.31.post_attention_norm.weight | Block 31 Post_Attention_Norm (W) | ( ~4K) 3840 | 3840 x 1 x 1 x 1 | F32 | | 409 | blk.31.post_ffw_norm.weight | Block 31 Post_Ffw_Norm (W) | ( ~4K) 3840 | 3840 x 1 x 1 x 1 | F32 | | 410 | blk.31.ffn_norm.weight | Block 31 Feed-Forward Network Normalization (W) | ( ~4K) 3840 | 3840 x 1 x 1 x 1 | F32 | | 411 | blk.31.attn_k_norm.weight | Block 31 Attn_K_Norm (W) | ( 256) 256 | 256 x 1 x 1 x 1 | F32 | | 412 | blk.31.attn_k.weight | Block 31 Attention Key (W) | ( ~8M) 7864320 | 3840 x 2048 x 1 x 1 | F16 | | 413 | blk.31.attn_output.weight | Block 31 Attention Output (W) | (~16M) 15728640 | 4096 x 3840 x 1 x 1 | F16 | | 414 | blk.31.attn_q_norm.weight | Block 31 Attn_Q_Norm (W) | ( 256) 256 | 256 x 1 x 1 x 1 | F32 | | 415 | blk.31.attn_q.weight | Block 31 Attention Query (W) | (~16M) 15728640 | 3840 x 4096 x 1 x 1 | F16 | | 416 | blk.31.attn_v.weight | Block 31 Attention Value (W) | ( ~8M) 7864320 | 3840 x 2048 x 1 x 1 | F16 | - Total elements in blk.31: (~224M) 224148992 - Percentage of total elements: 1.91% ### Block 32 Tensor Group : ~224M Elements | T_ID | Tensor Layer Name | Human Friendly Tensor Layer Name | Elements | Shape | Type | |-----:|:----------------------------------|:------------------------------------------------|:----------------|:----------------------|:-----| | 417 | blk.32.attn_norm.weight | Block 32 Attention Normalization (W) | ( ~4K) 3840 | 3840 x 1 x 1 x 1 | F32 | | 418 | blk.32.ffn_down.weight | Block 32 Feed-Forward Network "Down" (W) | (~59M) 58982400 | 15360 x 3840 x 1 x 1 | F16 | | 419 | blk.32.ffn_gate.weight | Block 32 Feed-Forward Network "Gate" (W) | (~59M) 58982400 | 3840 x 15360 x 1 x 1 | F16 | | 420 | blk.32.ffn_up.weight | Block 32 Feed-Forward Network "Up" (W) | (~59M) 58982400 | 3840 x 15360 x 1 x 1 | F16 | | 421 | blk.32.post_attention_norm.weight | Block 32 Post_Attention_Norm (W) | ( ~4K) 3840 | 3840 x 1 x 1 x 1 | F32 | | 422 | blk.32.post_ffw_norm.weight | Block 32 Post_Ffw_Norm (W) | ( ~4K) 3840 | 3840 x 1 x 1 x 1 | F32 | | 423 | blk.32.ffn_norm.weight | Block 32 Feed-Forward Network Normalization (W) | ( ~4K) 3840 | 3840 x 1 x 1 x 1 | F32 | | 424 | blk.32.attn_k_norm.weight | Block 32 Attn_K_Norm (W) | ( 256) 256 | 256 x 1 x 1 x 1 | F32 | | 425 | blk.32.attn_k.weight | Block 32 Attention Key (W) | ( ~8M) 7864320 | 3840 x 2048 x 1 x 1 | F16 | | 426 | blk.32.attn_output.weight | Block 32 Attention Output (W) | (~16M) 15728640 | 4096 x 3840 x 1 x 1 | F16 | | 427 | blk.32.attn_q_norm.weight | Block 32 Attn_Q_Norm (W) | ( 256) 256 | 256 x 1 x 1 x 1 | F32 | | 428 | blk.32.attn_q.weight | Block 32 Attention Query (W) | (~16M) 15728640 | 3840 x 4096 x 1 x 1 | F16 | | 429 | blk.32.attn_v.weight | Block 32 Attention Value (W) | ( ~8M) 7864320 | 3840 x 2048 x 1 x 1 | F16 | - Total elements in blk.32: (~224M) 224148992 - Percentage of total elements: 1.91% ### Block 33 Tensor Group : ~224M Elements | T_ID | Tensor Layer Name | Human Friendly Tensor Layer Name | Elements | Shape | Type | |-----:|:----------------------------------|:------------------------------------------------|:----------------|:----------------------|:-----| | 430 | blk.33.attn_norm.weight | Block 33 Attention Normalization (W) | ( ~4K) 3840 | 3840 x 1 x 1 x 1 | F32 | | 431 | blk.33.ffn_down.weight | Block 33 Feed-Forward Network "Down" (W) | (~59M) 58982400 | 15360 x 3840 x 1 x 1 | F16 | | 432 | blk.33.ffn_gate.weight | Block 33 Feed-Forward Network "Gate" (W) | (~59M) 58982400 | 3840 x 15360 x 1 x 1 | F16 | | 433 | blk.33.ffn_up.weight | Block 33 Feed-Forward Network "Up" (W) | (~59M) 58982400 | 3840 x 15360 x 1 x 1 | F16 | | 434 | blk.33.post_attention_norm.weight | Block 33 Post_Attention_Norm (W) | ( ~4K) 3840 | 3840 x 1 x 1 x 1 | F32 | | 435 | blk.33.post_ffw_norm.weight | Block 33 Post_Ffw_Norm (W) | ( ~4K) 3840 | 3840 x 1 x 1 x 1 | F32 | | 436 | blk.33.ffn_norm.weight | Block 33 Feed-Forward Network Normalization (W) | ( ~4K) 3840 | 3840 x 1 x 1 x 1 | F32 | | 437 | blk.33.attn_k_norm.weight | Block 33 Attn_K_Norm (W) | ( 256) 256 | 256 x 1 x 1 x 1 | F32 | | 438 | blk.33.attn_k.weight | Block 33 Attention Key (W) | ( ~8M) 7864320 | 3840 x 2048 x 1 x 1 | F16 | | 439 | blk.33.attn_output.weight | Block 33 Attention Output (W) | (~16M) 15728640 | 4096 x 3840 x 1 x 1 | F16 | | 440 | blk.33.attn_q_norm.weight | Block 33 Attn_Q_Norm (W) | ( 256) 256 | 256 x 1 x 1 x 1 | F32 | | 441 | blk.33.attn_q.weight | Block 33 Attention Query (W) | (~16M) 15728640 | 3840 x 4096 x 1 x 1 | F16 | | 442 | blk.33.attn_v.weight | Block 33 Attention Value (W) | ( ~8M) 7864320 | 3840 x 2048 x 1 x 1 | F16 | - Total elements in blk.33: (~224M) 224148992 - Percentage of total elements: 1.91% ### Block 34 Tensor Group : ~224M Elements | T_ID | Tensor Layer Name | Human Friendly Tensor Layer Name | Elements | Shape | Type | |-----:|:----------------------------------|:------------------------------------------------|:----------------|:----------------------|:-----| | 443 | blk.34.attn_norm.weight | Block 34 Attention Normalization (W) | ( ~4K) 3840 | 3840 x 1 x 1 x 1 | F32 | | 444 | blk.34.ffn_down.weight | Block 34 Feed-Forward Network "Down" (W) | (~59M) 58982400 | 15360 x 3840 x 1 x 1 | F16 | | 445 | blk.34.ffn_gate.weight | Block 34 Feed-Forward Network "Gate" (W) | (~59M) 58982400 | 3840 x 15360 x 1 x 1 | F16 | | 446 | blk.34.ffn_up.weight | Block 34 Feed-Forward Network "Up" (W) | (~59M) 58982400 | 3840 x 15360 x 1 x 1 | F16 | | 447 | blk.34.post_attention_norm.weight | Block 34 Post_Attention_Norm (W) | ( ~4K) 3840 | 3840 x 1 x 1 x 1 | F32 | | 448 | blk.34.post_ffw_norm.weight | Block 34 Post_Ffw_Norm (W) | ( ~4K) 3840 | 3840 x 1 x 1 x 1 | F32 | | 449 | blk.34.ffn_norm.weight | Block 34 Feed-Forward Network Normalization (W) | ( ~4K) 3840 | 3840 x 1 x 1 x 1 | F32 | | 450 | blk.34.attn_k_norm.weight | Block 34 Attn_K_Norm (W) | ( 256) 256 | 256 x 1 x 1 x 1 | F32 | | 451 | blk.34.attn_k.weight | Block 34 Attention Key (W) | ( ~8M) 7864320 | 3840 x 2048 x 1 x 1 | F16 | | 452 | blk.34.attn_output.weight | Block 34 Attention Output (W) | (~16M) 15728640 | 4096 x 3840 x 1 x 1 | F16 | | 453 | blk.34.attn_q_norm.weight | Block 34 Attn_Q_Norm (W) | ( 256) 256 | 256 x 1 x 1 x 1 | F32 | | 454 | blk.34.attn_q.weight | Block 34 Attention Query (W) | (~16M) 15728640 | 3840 x 4096 x 1 x 1 | F16 | | 455 | blk.34.attn_v.weight | Block 34 Attention Value (W) | ( ~8M) 7864320 | 3840 x 2048 x 1 x 1 | F16 | - Total elements in blk.34: (~224M) 224148992 - Percentage of total elements: 1.91% ### Block 35 Tensor Group : ~224M Elements | T_ID | Tensor Layer Name | Human Friendly Tensor Layer Name | Elements | Shape | Type | |-----:|:----------------------------------|:------------------------------------------------|:----------------|:----------------------|:-----| | 456 | blk.35.attn_norm.weight | Block 35 Attention Normalization (W) | ( ~4K) 3840 | 3840 x 1 x 1 x 1 | F32 | | 457 | blk.35.ffn_down.weight | Block 35 Feed-Forward Network "Down" (W) | (~59M) 58982400 | 15360 x 3840 x 1 x 1 | F16 | | 458 | blk.35.ffn_gate.weight | Block 35 Feed-Forward Network "Gate" (W) | (~59M) 58982400 | 3840 x 15360 x 1 x 1 | F16 | | 459 | blk.35.ffn_up.weight | Block 35 Feed-Forward Network "Up" (W) | (~59M) 58982400 | 3840 x 15360 x 1 x 1 | F16 | | 460 | blk.35.post_attention_norm.weight | Block 35 Post_Attention_Norm (W) | ( ~4K) 3840 | 3840 x 1 x 1 x 1 | F32 | | 461 | blk.35.post_ffw_norm.weight | Block 35 Post_Ffw_Norm (W) | ( ~4K) 3840 | 3840 x 1 x 1 x 1 | F32 | | 462 | blk.35.ffn_norm.weight | Block 35 Feed-Forward Network Normalization (W) | ( ~4K) 3840 | 3840 x 1 x 1 x 1 | F32 | | 463 | blk.35.attn_k_norm.weight | Block 35 Attn_K_Norm (W) | ( 256) 256 | 256 x 1 x 1 x 1 | F32 | | 464 | blk.35.attn_k.weight | Block 35 Attention Key (W) | ( ~8M) 7864320 | 3840 x 2048 x 1 x 1 | F16 | | 465 | blk.35.attn_output.weight | Block 35 Attention Output (W) | (~16M) 15728640 | 4096 x 3840 x 1 x 1 | F16 | | 466 | blk.35.attn_q_norm.weight | Block 35 Attn_Q_Norm (W) | ( 256) 256 | 256 x 1 x 1 x 1 | F32 | | 467 | blk.35.attn_q.weight | Block 35 Attention Query (W) | (~16M) 15728640 | 3840 x 4096 x 1 x 1 | F16 | | 468 | blk.35.attn_v.weight | Block 35 Attention Value (W) | ( ~8M) 7864320 | 3840 x 2048 x 1 x 1 | F16 | - Total elements in blk.35: (~224M) 224148992 - Percentage of total elements: 1.91% ### Block 36 Tensor Group : ~224M Elements | T_ID | Tensor Layer Name | Human Friendly Tensor Layer Name | Elements | Shape | Type | |-----:|:----------------------------------|:------------------------------------------------|:----------------|:----------------------|:-----| | 469 | blk.36.attn_norm.weight | Block 36 Attention Normalization (W) | ( ~4K) 3840 | 3840 x 1 x 1 x 1 | F32 | | 470 | blk.36.ffn_down.weight | Block 36 Feed-Forward Network "Down" (W) | (~59M) 58982400 | 15360 x 3840 x 1 x 1 | F16 | | 471 | blk.36.ffn_gate.weight | Block 36 Feed-Forward Network "Gate" (W) | (~59M) 58982400 | 3840 x 15360 x 1 x 1 | F16 | | 472 | blk.36.ffn_up.weight | Block 36 Feed-Forward Network "Up" (W) | (~59M) 58982400 | 3840 x 15360 x 1 x 1 | F16 | | 473 | blk.36.post_attention_norm.weight | Block 36 Post_Attention_Norm (W) | ( ~4K) 3840 | 3840 x 1 x 1 x 1 | F32 | | 474 | blk.36.post_ffw_norm.weight | Block 36 Post_Ffw_Norm (W) | ( ~4K) 3840 | 3840 x 1 x 1 x 1 | F32 | | 475 | blk.36.ffn_norm.weight | Block 36 Feed-Forward Network Normalization (W) | ( ~4K) 3840 | 3840 x 1 x 1 x 1 | F32 | | 476 | blk.36.attn_k_norm.weight | Block 36 Attn_K_Norm (W) | ( 256) 256 | 256 x 1 x 1 x 1 | F32 | | 477 | blk.36.attn_k.weight | Block 36 Attention Key (W) | ( ~8M) 7864320 | 3840 x 2048 x 1 x 1 | F16 | | 478 | blk.36.attn_output.weight | Block 36 Attention Output (W) | (~16M) 15728640 | 4096 x 3840 x 1 x 1 | F16 | | 479 | blk.36.attn_q_norm.weight | Block 36 Attn_Q_Norm (W) | ( 256) 256 | 256 x 1 x 1 x 1 | F32 | | 480 | blk.36.attn_q.weight | Block 36 Attention Query (W) | (~16M) 15728640 | 3840 x 4096 x 1 x 1 | F16 | | 481 | blk.36.attn_v.weight | Block 36 Attention Value (W) | ( ~8M) 7864320 | 3840 x 2048 x 1 x 1 | F16 | - Total elements in blk.36: (~224M) 224148992 - Percentage of total elements: 1.91% ### Block 37 Tensor Group : ~224M Elements | T_ID | Tensor Layer Name | Human Friendly Tensor Layer Name | Elements | Shape | Type | |-----:|:----------------------------------|:------------------------------------------------|:----------------|:----------------------|:-----| | 482 | blk.37.ffn_gate.weight | Block 37 Feed-Forward Network "Gate" (W) | (~59M) 58982400 | 3840 x 15360 x 1 x 1 | F16 | | 483 | blk.37.ffn_up.weight | Block 37 Feed-Forward Network "Up" (W) | (~59M) 58982400 | 3840 x 15360 x 1 x 1 | F16 | | 484 | blk.37.attn_k_norm.weight | Block 37 Attn_K_Norm (W) | ( 256) 256 | 256 x 1 x 1 x 1 | F32 | | 485 | blk.37.attn_k.weight | Block 37 Attention Key (W) | ( ~8M) 7864320 | 3840 x 2048 x 1 x 1 | F16 | | 486 | blk.37.attn_output.weight | Block 37 Attention Output (W) | (~16M) 15728640 | 4096 x 3840 x 1 x 1 | F16 | | 487 | blk.37.attn_q_norm.weight | Block 37 Attn_Q_Norm (W) | ( 256) 256 | 256 x 1 x 1 x 1 | F32 | | 488 | blk.37.attn_q.weight | Block 37 Attention Query (W) | (~16M) 15728640 | 3840 x 4096 x 1 x 1 | F16 | | 489 | blk.37.attn_v.weight | Block 37 Attention Value (W) | ( ~8M) 7864320 | 3840 x 2048 x 1 x 1 | F16 | | 490 | blk.37.attn_norm.weight | Block 37 Attention Normalization (W) | ( ~4K) 3840 | 3840 x 1 x 1 x 1 | F32 | | 491 | blk.37.ffn_down.weight | Block 37 Feed-Forward Network "Down" (W) | (~59M) 58982400 | 15360 x 3840 x 1 x 1 | F16 | | 492 | blk.37.post_attention_norm.weight | Block 37 Post_Attention_Norm (W) | ( ~4K) 3840 | 3840 x 1 x 1 x 1 | F32 | | 493 | blk.37.post_ffw_norm.weight | Block 37 Post_Ffw_Norm (W) | ( ~4K) 3840 | 3840 x 1 x 1 x 1 | F32 | | 494 | blk.37.ffn_norm.weight | Block 37 Feed-Forward Network Normalization (W) | ( ~4K) 3840 | 3840 x 1 x 1 x 1 | F32 | - Total elements in blk.37: (~224M) 224148992 - Percentage of total elements: 1.91% ### Block 38 Tensor Group : ~224M Elements | T_ID | Tensor Layer Name | Human Friendly Tensor Layer Name | Elements | Shape | Type | |-----:|:----------------------------------|:------------------------------------------------|:----------------|:----------------------|:-----| | 495 | blk.38.attn_norm.weight | Block 38 Attention Normalization (W) | ( ~4K) 3840 | 3840 x 1 x 1 x 1 | F32 | | 496 | blk.38.ffn_down.weight | Block 38 Feed-Forward Network "Down" (W) | (~59M) 58982400 | 15360 x 3840 x 1 x 1 | F16 | | 497 | blk.38.ffn_gate.weight | Block 38 Feed-Forward Network "Gate" (W) | (~59M) 58982400 | 3840 x 15360 x 1 x 1 | F16 | | 498 | blk.38.ffn_up.weight | Block 38 Feed-Forward Network "Up" (W) | (~59M) 58982400 | 3840 x 15360 x 1 x 1 | F16 | | 499 | blk.38.post_attention_norm.weight | Block 38 Post_Attention_Norm (W) | ( ~4K) 3840 | 3840 x 1 x 1 x 1 | F32 | | 500 | blk.38.post_ffw_norm.weight | Block 38 Post_Ffw_Norm (W) | ( ~4K) 3840 | 3840 x 1 x 1 x 1 | F32 | | 501 | blk.38.ffn_norm.weight | Block 38 Feed-Forward Network Normalization (W) | ( ~4K) 3840 | 3840 x 1 x 1 x 1 | F32 | | 502 | blk.38.attn_k_norm.weight | Block 38 Attn_K_Norm (W) | ( 256) 256 | 256 x 1 x 1 x 1 | F32 | | 503 | blk.38.attn_k.weight | Block 38 Attention Key (W) | ( ~8M) 7864320 | 3840 x 2048 x 1 x 1 | F16 | | 504 | blk.38.attn_output.weight | Block 38 Attention Output (W) | (~16M) 15728640 | 4096 x 3840 x 1 x 1 | F16 | | 505 | blk.38.attn_q_norm.weight | Block 38 Attn_Q_Norm (W) | ( 256) 256 | 256 x 1 x 1 x 1 | F32 | | 506 | blk.38.attn_q.weight | Block 38 Attention Query (W) | (~16M) 15728640 | 3840 x 4096 x 1 x 1 | F16 | | 507 | blk.38.attn_v.weight | Block 38 Attention Value (W) | ( ~8M) 7864320 | 3840 x 2048 x 1 x 1 | F16 | - Total elements in blk.38: (~224M) 224148992 - Percentage of total elements: 1.91% ### Block 39 Tensor Group : ~224M Elements | T_ID | Tensor Layer Name | Human Friendly Tensor Layer Name | Elements | Shape | Type | |-----:|:----------------------------------|:------------------------------------------------|:----------------|:----------------------|:-----| | 508 | blk.39.attn_norm.weight | Block 39 Attention Normalization (W) | ( ~4K) 3840 | 3840 x 1 x 1 x 1 | F32 | | 509 | blk.39.ffn_down.weight | Block 39 Feed-Forward Network "Down" (W) | (~59M) 58982400 | 15360 x 3840 x 1 x 1 | F16 | | 510 | blk.39.ffn_gate.weight | Block 39 Feed-Forward Network "Gate" (W) | (~59M) 58982400 | 3840 x 15360 x 1 x 1 | F16 | | 511 | blk.39.ffn_up.weight | Block 39 Feed-Forward Network "Up" (W) | (~59M) 58982400 | 3840 x 15360 x 1 x 1 | F16 | | 512 | blk.39.post_attention_norm.weight | Block 39 Post_Attention_Norm (W) | ( ~4K) 3840 | 3840 x 1 x 1 x 1 | F32 | | 513 | blk.39.post_ffw_norm.weight | Block 39 Post_Ffw_Norm (W) | ( ~4K) 3840 | 3840 x 1 x 1 x 1 | F32 | | 514 | blk.39.ffn_norm.weight | Block 39 Feed-Forward Network Normalization (W) | ( ~4K) 3840 | 3840 x 1 x 1 x 1 | F32 | | 515 | blk.39.attn_k_norm.weight | Block 39 Attn_K_Norm (W) | ( 256) 256 | 256 x 1 x 1 x 1 | F32 | | 516 | blk.39.attn_k.weight | Block 39 Attention Key (W) | ( ~8M) 7864320 | 3840 x 2048 x 1 x 1 | F16 | | 517 | blk.39.attn_output.weight | Block 39 Attention Output (W) | (~16M) 15728640 | 4096 x 3840 x 1 x 1 | F16 | | 518 | blk.39.attn_q_norm.weight | Block 39 Attn_Q_Norm (W) | ( 256) 256 | 256 x 1 x 1 x 1 | F32 | | 519 | blk.39.attn_q.weight | Block 39 Attention Query (W) | (~16M) 15728640 | 3840 x 4096 x 1 x 1 | F16 | | 520 | blk.39.attn_v.weight | Block 39 Attention Value (W) | ( ~8M) 7864320 | 3840 x 2048 x 1 x 1 | F16 | - Total elements in blk.39: (~224M) 224148992 - Percentage of total elements: 1.91% ### Block 40 Tensor Group : ~224M Elements | T_ID | Tensor Layer Name | Human Friendly Tensor Layer Name | Elements | Shape | Type | |-----:|:----------------------------------|:------------------------------------------------|:----------------|:----------------------|:-----| | 521 | blk.40.attn_norm.weight | Block 40 Attention Normalization (W) | ( ~4K) 3840 | 3840 x 1 x 1 x 1 | F32 | | 522 | blk.40.ffn_down.weight | Block 40 Feed-Forward Network "Down" (W) | (~59M) 58982400 | 15360 x 3840 x 1 x 1 | F16 | | 523 | blk.40.ffn_gate.weight | Block 40 Feed-Forward Network "Gate" (W) | (~59M) 58982400 | 3840 x 15360 x 1 x 1 | F16 | | 524 | blk.40.ffn_up.weight | Block 40 Feed-Forward Network "Up" (W) | (~59M) 58982400 | 3840 x 15360 x 1 x 1 | F16 | | 525 | blk.40.post_attention_norm.weight | Block 40 Post_Attention_Norm (W) | ( ~4K) 3840 | 3840 x 1 x 1 x 1 | F32 | | 526 | blk.40.post_ffw_norm.weight | Block 40 Post_Ffw_Norm (W) | ( ~4K) 3840 | 3840 x 1 x 1 x 1 | F32 | | 527 | blk.40.ffn_norm.weight | Block 40 Feed-Forward Network Normalization (W) | ( ~4K) 3840 | 3840 x 1 x 1 x 1 | F32 | | 528 | blk.40.attn_k_norm.weight | Block 40 Attn_K_Norm (W) | ( 256) 256 | 256 x 1 x 1 x 1 | F32 | | 529 | blk.40.attn_k.weight | Block 40 Attention Key (W) | ( ~8M) 7864320 | 3840 x 2048 x 1 x 1 | F16 | | 530 | blk.40.attn_output.weight | Block 40 Attention Output (W) | (~16M) 15728640 | 4096 x 3840 x 1 x 1 | F16 | | 531 | blk.40.attn_q_norm.weight | Block 40 Attn_Q_Norm (W) | ( 256) 256 | 256 x 1 x 1 x 1 | F32 | | 532 | blk.40.attn_q.weight | Block 40 Attention Query (W) | (~16M) 15728640 | 3840 x 4096 x 1 x 1 | F16 | | 533 | blk.40.attn_v.weight | Block 40 Attention Value (W) | ( ~8M) 7864320 | 3840 x 2048 x 1 x 1 | F16 | - Total elements in blk.40: (~224M) 224148992 - Percentage of total elements: 1.91% ### Block 41 Tensor Group : ~224M Elements | T_ID | Tensor Layer Name | Human Friendly Tensor Layer Name | Elements | Shape | Type | |-----:|:----------------------------------|:------------------------------------------------|:----------------|:----------------------|:-----| | 534 | blk.41.attn_norm.weight | Block 41 Attention Normalization (W) | ( ~4K) 3840 | 3840 x 1 x 1 x 1 | F32 | | 535 | blk.41.ffn_down.weight | Block 41 Feed-Forward Network "Down" (W) | (~59M) 58982400 | 15360 x 3840 x 1 x 1 | F16 | | 536 | blk.41.ffn_gate.weight | Block 41 Feed-Forward Network "Gate" (W) | (~59M) 58982400 | 3840 x 15360 x 1 x 1 | F16 | | 537 | blk.41.ffn_up.weight | Block 41 Feed-Forward Network "Up" (W) | (~59M) 58982400 | 3840 x 15360 x 1 x 1 | F16 | | 538 | blk.41.post_attention_norm.weight | Block 41 Post_Attention_Norm (W) | ( ~4K) 3840 | 3840 x 1 x 1 x 1 | F32 | | 539 | blk.41.post_ffw_norm.weight | Block 41 Post_Ffw_Norm (W) | ( ~4K) 3840 | 3840 x 1 x 1 x 1 | F32 | | 540 | blk.41.ffn_norm.weight | Block 41 Feed-Forward Network Normalization (W) | ( ~4K) 3840 | 3840 x 1 x 1 x 1 | F32 | | 541 | blk.41.attn_k_norm.weight | Block 41 Attn_K_Norm (W) | ( 256) 256 | 256 x 1 x 1 x 1 | F32 | | 542 | blk.41.attn_k.weight | Block 41 Attention Key (W) | ( ~8M) 7864320 | 3840 x 2048 x 1 x 1 | F16 | | 543 | blk.41.attn_output.weight | Block 41 Attention Output (W) | (~16M) 15728640 | 4096 x 3840 x 1 x 1 | F16 | | 544 | blk.41.attn_q_norm.weight | Block 41 Attn_Q_Norm (W) | ( 256) 256 | 256 x 1 x 1 x 1 | F32 | | 545 | blk.41.attn_q.weight | Block 41 Attention Query (W) | (~16M) 15728640 | 3840 x 4096 x 1 x 1 | F16 | | 546 | blk.41.attn_v.weight | Block 41 Attention Value (W) | ( ~8M) 7864320 | 3840 x 2048 x 1 x 1 | F16 | - Total elements in blk.41: (~224M) 224148992 - Percentage of total elements: 1.91% ### Block 42 Tensor Group : ~224M Elements | T_ID | Tensor Layer Name | Human Friendly Tensor Layer Name | Elements | Shape | Type | |-----:|:----------------------------------|:------------------------------------------------|:----------------|:----------------------|:-----| | 547 | blk.42.attn_norm.weight | Block 42 Attention Normalization (W) | ( ~4K) 3840 | 3840 x 1 x 1 x 1 | F32 | | 548 | blk.42.ffn_down.weight | Block 42 Feed-Forward Network "Down" (W) | (~59M) 58982400 | 15360 x 3840 x 1 x 1 | F16 | | 549 | blk.42.ffn_gate.weight | Block 42 Feed-Forward Network "Gate" (W) | (~59M) 58982400 | 3840 x 15360 x 1 x 1 | F16 | | 550 | blk.42.ffn_up.weight | Block 42 Feed-Forward Network "Up" (W) | (~59M) 58982400 | 3840 x 15360 x 1 x 1 | F16 | | 551 | blk.42.post_attention_norm.weight | Block 42 Post_Attention_Norm (W) | ( ~4K) 3840 | 3840 x 1 x 1 x 1 | F32 | | 552 | blk.42.post_ffw_norm.weight | Block 42 Post_Ffw_Norm (W) | ( ~4K) 3840 | 3840 x 1 x 1 x 1 | F32 | | 553 | blk.42.ffn_norm.weight | Block 42 Feed-Forward Network Normalization (W) | ( ~4K) 3840 | 3840 x 1 x 1 x 1 | F32 | | 554 | blk.42.attn_k_norm.weight | Block 42 Attn_K_Norm (W) | ( 256) 256 | 256 x 1 x 1 x 1 | F32 | | 555 | blk.42.attn_k.weight | Block 42 Attention Key (W) | ( ~8M) 7864320 | 3840 x 2048 x 1 x 1 | F16 | | 556 | blk.42.attn_output.weight | Block 42 Attention Output (W) | (~16M) 15728640 | 4096 x 3840 x 1 x 1 | F16 | | 557 | blk.42.attn_q_norm.weight | Block 42 Attn_Q_Norm (W) | ( 256) 256 | 256 x 1 x 1 x 1 | F32 | | 558 | blk.42.attn_q.weight | Block 42 Attention Query (W) | (~16M) 15728640 | 3840 x 4096 x 1 x 1 | F16 | | 559 | blk.42.attn_v.weight | Block 42 Attention Value (W) | ( ~8M) 7864320 | 3840 x 2048 x 1 x 1 | F16 | - Total elements in blk.42: (~224M) 224148992 - Percentage of total elements: 1.91% ### Block 43 Tensor Group : ~224M Elements | T_ID | Tensor Layer Name | Human Friendly Tensor Layer Name | Elements | Shape | Type | |-----:|:----------------------------------|:------------------------------------------------|:----------------|:----------------------|:-----| | 560 | blk.43.attn_norm.weight | Block 43 Attention Normalization (W) | ( ~4K) 3840 | 3840 x 1 x 1 x 1 | F32 | | 561 | blk.43.ffn_down.weight | Block 43 Feed-Forward Network "Down" (W) | (~59M) 58982400 | 15360 x 3840 x 1 x 1 | F16 | | 562 | blk.43.ffn_gate.weight | Block 43 Feed-Forward Network "Gate" (W) | (~59M) 58982400 | 3840 x 15360 x 1 x 1 | F16 | | 563 | blk.43.ffn_up.weight | Block 43 Feed-Forward Network "Up" (W) | (~59M) 58982400 | 3840 x 15360 x 1 x 1 | F16 | | 564 | blk.43.post_attention_norm.weight | Block 43 Post_Attention_Norm (W) | ( ~4K) 3840 | 3840 x 1 x 1 x 1 | F32 | | 565 | blk.43.post_ffw_norm.weight | Block 43 Post_Ffw_Norm (W) | ( ~4K) 3840 | 3840 x 1 x 1 x 1 | F32 | | 566 | blk.43.ffn_norm.weight | Block 43 Feed-Forward Network Normalization (W) | ( ~4K) 3840 | 3840 x 1 x 1 x 1 | F32 | | 567 | blk.43.attn_k_norm.weight | Block 43 Attn_K_Norm (W) | ( 256) 256 | 256 x 1 x 1 x 1 | F32 | | 568 | blk.43.attn_k.weight | Block 43 Attention Key (W) | ( ~8M) 7864320 | 3840 x 2048 x 1 x 1 | F16 | | 569 | blk.43.attn_output.weight | Block 43 Attention Output (W) | (~16M) 15728640 | 4096 x 3840 x 1 x 1 | F16 | | 570 | blk.43.attn_q_norm.weight | Block 43 Attn_Q_Norm (W) | ( 256) 256 | 256 x 1 x 1 x 1 | F32 | | 571 | blk.43.attn_q.weight | Block 43 Attention Query (W) | (~16M) 15728640 | 3840 x 4096 x 1 x 1 | F16 | | 572 | blk.43.attn_v.weight | Block 43 Attention Value (W) | ( ~8M) 7864320 | 3840 x 2048 x 1 x 1 | F16 | - Total elements in blk.43: (~224M) 224148992 - Percentage of total elements: 1.91% ### Block 44 Tensor Group : ~224M Elements | T_ID | Tensor Layer Name | Human Friendly Tensor Layer Name | Elements | Shape | Type | |-----:|:----------------------------------|:------------------------------------------------|:----------------|:----------------------|:-----| | 573 | blk.44.attn_norm.weight | Block 44 Attention Normalization (W) | ( ~4K) 3840 | 3840 x 1 x 1 x 1 | F32 | | 574 | blk.44.ffn_down.weight | Block 44 Feed-Forward Network "Down" (W) | (~59M) 58982400 | 15360 x 3840 x 1 x 1 | F16 | | 575 | blk.44.ffn_gate.weight | Block 44 Feed-Forward Network "Gate" (W) | (~59M) 58982400 | 3840 x 15360 x 1 x 1 | F16 | | 576 | blk.44.ffn_up.weight | Block 44 Feed-Forward Network "Up" (W) | (~59M) 58982400 | 3840 x 15360 x 1 x 1 | F16 | | 577 | blk.44.post_attention_norm.weight | Block 44 Post_Attention_Norm (W) | ( ~4K) 3840 | 3840 x 1 x 1 x 1 | F32 | | 578 | blk.44.post_ffw_norm.weight | Block 44 Post_Ffw_Norm (W) | ( ~4K) 3840 | 3840 x 1 x 1 x 1 | F32 | | 579 | blk.44.ffn_norm.weight | Block 44 Feed-Forward Network Normalization (W) | ( ~4K) 3840 | 3840 x 1 x 1 x 1 | F32 | | 580 | blk.44.attn_k_norm.weight | Block 44 Attn_K_Norm (W) | ( 256) 256 | 256 x 1 x 1 x 1 | F32 | | 581 | blk.44.attn_k.weight | Block 44 Attention Key (W) | ( ~8M) 7864320 | 3840 x 2048 x 1 x 1 | F16 | | 582 | blk.44.attn_output.weight | Block 44 Attention Output (W) | (~16M) 15728640 | 4096 x 3840 x 1 x 1 | F16 | | 583 | blk.44.attn_q_norm.weight | Block 44 Attn_Q_Norm (W) | ( 256) 256 | 256 x 1 x 1 x 1 | F32 | | 584 | blk.44.attn_q.weight | Block 44 Attention Query (W) | (~16M) 15728640 | 3840 x 4096 x 1 x 1 | F16 | | 585 | blk.44.attn_v.weight | Block 44 Attention Value (W) | ( ~8M) 7864320 | 3840 x 2048 x 1 x 1 | F16 | - Total elements in blk.44: (~224M) 224148992 - Percentage of total elements: 1.91% ### Block 45 Tensor Group : ~224M Elements | T_ID | Tensor Layer Name | Human Friendly Tensor Layer Name | Elements | Shape | Type | |-----:|:----------------------------------|:------------------------------------------------|:----------------|:----------------------|:-----| | 586 | blk.45.attn_norm.weight | Block 45 Attention Normalization (W) | ( ~4K) 3840 | 3840 x 1 x 1 x 1 | F32 | | 587 | blk.45.ffn_down.weight | Block 45 Feed-Forward Network "Down" (W) | (~59M) 58982400 | 15360 x 3840 x 1 x 1 | F16 | | 588 | blk.45.ffn_gate.weight | Block 45 Feed-Forward Network "Gate" (W) | (~59M) 58982400 | 3840 x 15360 x 1 x 1 | F16 | | 589 | blk.45.ffn_up.weight | Block 45 Feed-Forward Network "Up" (W) | (~59M) 58982400 | 3840 x 15360 x 1 x 1 | F16 | | 590 | blk.45.post_attention_norm.weight | Block 45 Post_Attention_Norm (W) | ( ~4K) 3840 | 3840 x 1 x 1 x 1 | F32 | | 591 | blk.45.post_ffw_norm.weight | Block 45 Post_Ffw_Norm (W) | ( ~4K) 3840 | 3840 x 1 x 1 x 1 | F32 | | 592 | blk.45.ffn_norm.weight | Block 45 Feed-Forward Network Normalization (W) | ( ~4K) 3840 | 3840 x 1 x 1 x 1 | F32 | | 593 | blk.45.attn_k_norm.weight | Block 45 Attn_K_Norm (W) | ( 256) 256 | 256 x 1 x 1 x 1 | F32 | | 594 | blk.45.attn_k.weight | Block 45 Attention Key (W) | ( ~8M) 7864320 | 3840 x 2048 x 1 x 1 | F16 | | 595 | blk.45.attn_output.weight | Block 45 Attention Output (W) | (~16M) 15728640 | 4096 x 3840 x 1 x 1 | F16 | | 596 | blk.45.attn_q_norm.weight | Block 45 Attn_Q_Norm (W) | ( 256) 256 | 256 x 1 x 1 x 1 | F32 | | 597 | blk.45.attn_q.weight | Block 45 Attention Query (W) | (~16M) 15728640 | 3840 x 4096 x 1 x 1 | F16 | | 598 | blk.45.attn_v.weight | Block 45 Attention Value (W) | ( ~8M) 7864320 | 3840 x 2048 x 1 x 1 | F16 | - Total elements in blk.45: (~224M) 224148992 - Percentage of total elements: 1.91% ### Block 46 Tensor Group : ~224M Elements | T_ID | Tensor Layer Name | Human Friendly Tensor Layer Name | Elements | Shape | Type | |-----:|:----------------------------------|:------------------------------------------------|:----------------|:----------------------|:-----| | 599 | blk.46.attn_norm.weight | Block 46 Attention Normalization (W) | ( ~4K) 3840 | 3840 x 1 x 1 x 1 | F32 | | 600 | blk.46.ffn_down.weight | Block 46 Feed-Forward Network "Down" (W) | (~59M) 58982400 | 15360 x 3840 x 1 x 1 | F16 | | 601 | blk.46.ffn_gate.weight | Block 46 Feed-Forward Network "Gate" (W) | (~59M) 58982400 | 3840 x 15360 x 1 x 1 | F16 | | 602 | blk.46.ffn_up.weight | Block 46 Feed-Forward Network "Up" (W) | (~59M) 58982400 | 3840 x 15360 x 1 x 1 | F16 | | 603 | blk.46.post_attention_norm.weight | Block 46 Post_Attention_Norm (W) | ( ~4K) 3840 | 3840 x 1 x 1 x 1 | F32 | | 604 | blk.46.post_ffw_norm.weight | Block 46 Post_Ffw_Norm (W) | ( ~4K) 3840 | 3840 x 1 x 1 x 1 | F32 | | 605 | blk.46.ffn_norm.weight | Block 46 Feed-Forward Network Normalization (W) | ( ~4K) 3840 | 3840 x 1 x 1 x 1 | F32 | | 606 | blk.46.attn_k_norm.weight | Block 46 Attn_K_Norm (W) | ( 256) 256 | 256 x 1 x 1 x 1 | F32 | | 607 | blk.46.attn_k.weight | Block 46 Attention Key (W) | ( ~8M) 7864320 | 3840 x 2048 x 1 x 1 | F16 | | 608 | blk.46.attn_output.weight | Block 46 Attention Output (W) | (~16M) 15728640 | 4096 x 3840 x 1 x 1 | F16 | | 609 | blk.46.attn_q_norm.weight | Block 46 Attn_Q_Norm (W) | ( 256) 256 | 256 x 1 x 1 x 1 | F32 | | 610 | blk.46.attn_q.weight | Block 46 Attention Query (W) | (~16M) 15728640 | 3840 x 4096 x 1 x 1 | F16 | | 611 | blk.46.attn_v.weight | Block 46 Attention Value (W) | ( ~8M) 7864320 | 3840 x 2048 x 1 x 1 | F16 | - Total elements in blk.46: (~224M) 224148992 - Percentage of total elements: 1.91% ### Block 47 Tensor Group : ~224M Elements | T_ID | Tensor Layer Name | Human Friendly Tensor Layer Name | Elements | Shape | Type | |-----:|:----------------------------------|:------------------------------------------------|:----------------|:----------------------|:-----| | 612 | blk.47.attn_norm.weight | Block 47 Attention Normalization (W) | ( ~4K) 3840 | 3840 x 1 x 1 x 1 | F32 | | 613 | blk.47.ffn_down.weight | Block 47 Feed-Forward Network "Down" (W) | (~59M) 58982400 | 15360 x 3840 x 1 x 1 | F16 | | 614 | blk.47.ffn_gate.weight | Block 47 Feed-Forward Network "Gate" (W) | (~59M) 58982400 | 3840 x 15360 x 1 x 1 | F16 | | 615 | blk.47.ffn_up.weight | Block 47 Feed-Forward Network "Up" (W) | (~59M) 58982400 | 3840 x 15360 x 1 x 1 | F16 | | 616 | blk.47.post_attention_norm.weight | Block 47 Post_Attention_Norm (W) | ( ~4K) 3840 | 3840 x 1 x 1 x 1 | F32 | | 617 | blk.47.post_ffw_norm.weight | Block 47 Post_Ffw_Norm (W) | ( ~4K) 3840 | 3840 x 1 x 1 x 1 | F32 | | 618 | blk.47.ffn_norm.weight | Block 47 Feed-Forward Network Normalization (W) | ( ~4K) 3840 | 3840 x 1 x 1 x 1 | F32 | | 619 | blk.47.attn_k_norm.weight | Block 47 Attn_K_Norm (W) | ( 256) 256 | 256 x 1 x 1 x 1 | F32 | | 620 | blk.47.attn_k.weight | Block 47 Attention Key (W) | ( ~8M) 7864320 | 3840 x 2048 x 1 x 1 | F16 | | 621 | blk.47.attn_output.weight | Block 47 Attention Output (W) | (~16M) 15728640 | 4096 x 3840 x 1 x 1 | F16 | | 622 | blk.47.attn_q_norm.weight | Block 47 Attn_Q_Norm (W) | ( 256) 256 | 256 x 1 x 1 x 1 | F32 | | 623 | blk.47.attn_q.weight | Block 47 Attention Query (W) | (~16M) 15728640 | 3840 x 4096 x 1 x 1 | F16 | | 624 | blk.47.attn_v.weight | Block 47 Attention Value (W) | ( ~8M) 7864320 | 3840 x 2048 x 1 x 1 | F16 | - Total elements in blk.47: (~224M) 224148992 - Percentage of total elements: 1.91%