# gemma-4-26B-A4B-it-F16.gguf - GGUF Internal File Dump - Endian: LITTLE endian ## Key Value Metadata Store There are 53 key-value pairs in this file | POS | TYPE | Count | Key | Value | | ---: | :-------- | -----: | :-------------------------------------- | :--------------------------------------------------------------------------------------------------------------- | | 1 | UINT32 | 1 | GGUF.version | 3 | | 2 | UINT64 | 1 | GGUF.tensor_count | 658 | | 3 | UINT64 | 1 | GGUF.kv_count | 50 | | 4 | STRING | 1 | general.architecture | `gemma4` | | 5 | STRING | 1 | general.type | `model` | | 6 | INT32 | 1 | general.sampling.top_k | 64 | | 7 | FLOAT32 | 1 | general.sampling.top_p | 0.95 | | 8 | FLOAT32 | 1 | general.sampling.temp | 1.0 | | 9 | STRING | 1 | general.name | `Gemma 4 26B A4B It` | | 10 | STRING | 1 | general.finetune | `it` | | 11 | STRING | 1 | general.basename | `gemma-4` | | 12 | STRING | 1 | general.size_label | `26B-A4B` | | 13 | STRING | 1 | general.license | `apache-2.0` | | 14 | STRING | 1 | general.license.link | `https://ai.google.dev/gemma/docs/gemma_4_license` | | 15 | [STRING] | 1 | general.tags | [ `image-text-to-text` ] | | 16 | UINT32 | 1 | gemma4.block_count | 30 | | 17 | UINT32 | 1 | gemma4.context_length | 262144 | | 18 | UINT32 | 1 | gemma4.embedding_length | 2816 | | 19 | UINT32 | 1 | gemma4.feed_forward_length | 2112 | | 20 | UINT32 | 1 | gemma4.attention.head_count | 16 | | 21 | [INT32] | 30 | gemma4.attention.head_count_kv | [ 8, 8, 8, 8, 8, 2, 8, ... ] | | 22 | FLOAT32 | 1 | gemma4.rope.freq_base | 1e+06 | | 23 | FLOAT32 | 1 | gemma4.rope.freq_base_swa | 10000.0 | | 24 | FLOAT32 | 1 | gemma4.attention.layer_norm_rms_epsilon | 1e-06 | | 25 | UINT32 | 1 | gemma4.expert_count | 128 | | 26 | UINT32 | 1 | gemma4.expert_used_count | 8 | | 27 | UINT32 | 1 | gemma4.attention.key_length | 512 | | 28 | UINT32 | 1 | gemma4.attention.value_length | 512 | | 29 | UINT32 | 1 | general.file_type | 1 | | 30 | FLOAT32 | 1 | gemma4.final_logit_softcapping | 30.0 | | 31 | UINT32 | 1 | gemma4.attention.sliding_window | 1024 | | 32 | UINT32 | 1 | gemma4.attention.shared_kv_layers | 0 | | 33 | UINT32 | 1 | gemma4.embedding_length_per_layer_input | 0 | | 34 | [BOOL] | 30 | gemma4.attention.sliding_window_pattern | [ True, True, True, True, True, False, True, ... ] | | 35 | UINT32 | 1 | gemma4.attention.key_length_swa | 256 | | 36 | UINT32 | 1 | gemma4.attention.value_length_swa | 256 | | 37 | UINT32 | 1 | gemma4.expert_feed_forward_length | 704 | | 38 | UINT32 | 1 | gemma4.rope.dimension_count | 512 | | 39 | UINT32 | 1 | gemma4.rope.dimension_count_swa | 256 | | 40 | UINT32 | 1 | general.quantization_version | 2 | | 41 | STRING | 1 | tokenizer.ggml.model | `gemma4` | | 42 | [STRING] | 262144 | tokenizer.ggml.tokens | [ ``, ``, ``, ``, ``, ... ] | | 43 | [FLOAT32] | 262144 | tokenizer.ggml.scores | [ -1000.0, -1000.0, -1000.0, -1000.0, -1000.0, -1000.0, -1000.0, ... ] | | 44 | [INT32] | 262144 | tokenizer.ggml.token_type | [ 3, 3, 3, 3, 3, 1, 1, ... ] | | 45 | [STRING] | 514906 | tokenizer.ggml.merges | [ ``...``, `▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁`...`▁▁▁▁▁▁▁▁▁▁▁▁▁ ▁`, ``...``, ``...``, `▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁`...`▁▁▁▁▁▁▁▁▁▁▁▁ ▁▁`, ... ] | | 46 | UINT32 | 1 | tokenizer.ggml.bos_token_id | 2 | | 47 | UINT32 | 1 | tokenizer.ggml.eos_token_id | 1 | | 48 | UINT32 | 1 | tokenizer.ggml.unknown_token_id | 3 | | 49 | UINT32 | 1 | tokenizer.ggml.padding_token_id | 0 | | 50 | UINT32 | 1 | tokenizer.ggml.mask_token_id | 4 | | 51 | STRING | 1 | tokenizer.chat_template | `{%- macro format_parameters(pr`...` {%- endif -%}{%- endif -%}` | | 52 | BOOL | 1 | tokenizer.ggml.add_space_prefix | False | | 53 | BOOL | 1 | tokenizer.ggml.add_bos_token | True | ## Tensors Overview ~25B Elements Total number of elements in all tensors: 25233142046 Elements - [/Users/ed/Development/AI/hf/gemma-4-26B-A4B-it-WIP/gemma-4-26B-A4B-it-F16.gguf - GGUF Internal File Dump](#userseddevelopmentaihfgemma-4-26b-a4b-it-wipgemma-4-26b-a4b-it-f16gguf---gguf-internal-file-dump) - [Key Value Metadata Store](#key-value-metadata-store) - [Tensors Overview ~25B Elements](#tensors-overview-25b-elements) - [Tensor Data Offset](#tensor-data-offset) - [Base Tensor Group : ~738M Elements](#base-tensor-group--738m-elements) - [Block 0 Tensor Group : ~814M Elements](#block-0-tensor-group--814m-elements) - [Block 1 Tensor Group : ~814M Elements](#block-1-tensor-group--814m-elements) - [Block 10 Tensor Group : ~814M Elements](#block-10-tensor-group--814m-elements) - [Block 11 Tensor Group : ~829M Elements](#block-11-tensor-group--829m-elements) - [Block 12 Tensor Group : ~814M Elements](#block-12-tensor-group--814m-elements) - [Block 13 Tensor Group : ~814M Elements](#block-13-tensor-group--814m-elements) - [Block 14 Tensor Group : ~814M Elements](#block-14-tensor-group--814m-elements) - [Block 15 Tensor Group : ~814M Elements](#block-15-tensor-group--814m-elements) - [Block 16 Tensor Group : ~814M Elements](#block-16-tensor-group--814m-elements) - [Block 17 Tensor Group : ~829M Elements](#block-17-tensor-group--829m-elements) - [Block 18 Tensor Group : ~814M Elements](#block-18-tensor-group--814m-elements) - [Block 19 Tensor Group : ~814M Elements](#block-19-tensor-group--814m-elements) - [Block 2 Tensor Group : ~814M Elements](#block-2-tensor-group--814m-elements) - [Block 20 Tensor Group : ~814M Elements](#block-20-tensor-group--814m-elements) - [Block 21 Tensor Group : ~814M Elements](#block-21-tensor-group--814m-elements) - [Block 22 Tensor Group : ~814M Elements](#block-22-tensor-group--814m-elements) - [Block 23 Tensor Group : ~829M Elements](#block-23-tensor-group--829m-elements) - [Block 24 Tensor Group : ~814M Elements](#block-24-tensor-group--814m-elements) - [Block 25 Tensor Group : ~814M Elements](#block-25-tensor-group--814m-elements) - [Block 26 Tensor Group : ~814M Elements](#block-26-tensor-group--814m-elements) - [Block 27 Tensor Group : ~814M Elements](#block-27-tensor-group--814m-elements) - [Block 28 Tensor Group : ~814M Elements](#block-28-tensor-group--814m-elements) - [Block 29 Tensor Group : ~829M Elements](#block-29-tensor-group--829m-elements) - [Block 3 Tensor Group : ~814M Elements](#block-3-tensor-group--814m-elements) - [Block 4 Tensor Group : ~814M Elements](#block-4-tensor-group--814m-elements) - [Block 5 Tensor Group : ~829M Elements](#block-5-tensor-group--829m-elements) - [Block 6 Tensor Group : ~814M Elements](#block-6-tensor-group--814m-elements) - [Block 7 Tensor Group : ~814M Elements](#block-7-tensor-group--814m-elements) - [Block 8 Tensor Group : ~814M Elements](#block-8-tensor-group--814m-elements) - [Block 9 Tensor Group : ~814M Elements](#block-9-tensor-group--814m-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 | rope_freqs.weight | 0xf16ae0 | 0x400 | | 1 | token_embd.weight | 0xf16ee0 | 0x58000000 | | 2 | blk.0.ffn_down_exps.weight | 0x58f16ee0 | 0x1e400000 | | 3 | blk.0.ffn_gate_up_exps.weight | 0x77316ee0 | 0x3c800000 | | 4 | blk.0.attn_norm.weight | 0xb3b16ee0 | 0x2c00 | | 5 | blk.0.layer_output_scale.weight | 0xb3b19ae0 | 0x4 | | 6 | blk.0.ffn_down.weight | 0xb3b19b00 | 0xb58000 | | 7 | blk.0.ffn_gate.weight | 0xb4671b00 | 0xb58000 | | 8 | blk.0.ffn_up.weight | 0xb51c9b00 | 0xb58000 | | 9 | blk.0.post_attention_norm.weight | 0xb5d21b00 | 0x2c00 | | 10 | blk.0.post_ffw_norm.weight | 0xb5d24700 | 0x2c00 | | 11 | blk.0.post_ffw_norm_1.weight | 0xb5d27300 | 0x2c00 | | 12 | blk.0.post_ffw_norm_2.weight | 0xb5d29f00 | 0x2c00 | | 13 | blk.0.ffn_norm.weight | 0xb5d2cb00 | 0x2c00 | | 14 | blk.0.pre_ffw_norm_2.weight | 0xb5d2f700 | 0x2c00 | | 15 | blk.0.ffn_down_exps.scale | 0xb5d32300 | 0x200 | | 16 | blk.0.ffn_gate_inp.weight | 0xb5d32500 | 0x160000 | | 17 | blk.0.ffn_gate_inp.scale | 0xb5e92500 | 0x2c00 | | 18 | blk.0.attn_k_norm.weight | 0xb5e95100 | 0x400 | | 19 | blk.0.attn_k.weight | 0xb5e95500 | 0xb00000 | | 20 | blk.0.attn_output.weight | 0xb6995500 | 0x1600000 | | 21 | blk.0.attn_q_norm.weight | 0xb7f95500 | 0x400 | | 22 | blk.0.attn_q.weight | 0xb7f95900 | 0x1600000 | | 23 | blk.0.attn_v.weight | 0xb9595900 | 0xb00000 | | 24 | blk.1.ffn_down_exps.weight | 0xba095900 | 0x1e400000 | | 25 | blk.1.ffn_gate_up_exps.weight | 0xd8495900 | 0x3c800000 | | 26 | blk.1.attn_norm.weight | 0x114c95900 | 0x2c00 | | 27 | blk.1.layer_output_scale.weight | 0x114c98500 | 0x4 | | 28 | blk.1.ffn_down.weight | 0x114c98520 | 0xb58000 | | 29 | blk.1.ffn_gate.weight | 0x1157f0520 | 0xb58000 | | 30 | blk.1.ffn_up.weight | 0x116348520 | 0xb58000 | | 31 | blk.1.post_attention_norm.weight | 0x116ea0520 | 0x2c00 | | 32 | blk.1.post_ffw_norm.weight | 0x116ea3120 | 0x2c00 | | 33 | blk.1.post_ffw_norm_1.weight | 0x116ea5d20 | 0x2c00 | | 34 | blk.1.post_ffw_norm_2.weight | 0x116ea8920 | 0x2c00 | | 35 | blk.1.ffn_norm.weight | 0x116eab520 | 0x2c00 | | 36 | blk.1.pre_ffw_norm_2.weight | 0x116eae120 | 0x2c00 | | 37 | blk.1.ffn_down_exps.scale | 0x116eb0d20 | 0x200 | | 38 | blk.1.ffn_gate_inp.weight | 0x116eb0f20 | 0x160000 | | 39 | blk.1.ffn_gate_inp.scale | 0x117010f20 | 0x2c00 | | 40 | blk.1.attn_k_norm.weight | 0x117013b20 | 0x400 | | 41 | blk.1.attn_k.weight | 0x117013f20 | 0xb00000 | | 42 | blk.1.attn_output.weight | 0x117b13f20 | 0x1600000 | | 43 | blk.1.attn_q_norm.weight | 0x119113f20 | 0x400 | | 44 | blk.1.attn_q.weight | 0x119114320 | 0x1600000 | | 45 | blk.1.attn_v.weight | 0x11a714320 | 0xb00000 | | 46 | blk.10.ffn_down_exps.weight | 0x11b214320 | 0x1e400000 | | 47 | blk.10.ffn_gate_up_exps.weight | 0x139614320 | 0x3c800000 | | 48 | blk.10.attn_norm.weight | 0x175e14320 | 0x2c00 | | 49 | blk.10.layer_output_scale.weight | 0x175e16f20 | 0x4 | | 50 | blk.10.ffn_down.weight | 0x175e16f40 | 0xb58000 | | 51 | blk.10.ffn_gate.weight | 0x17696ef40 | 0xb58000 | | 52 | blk.10.ffn_up.weight | 0x1774c6f40 | 0xb58000 | | 53 | blk.10.post_attention_norm.weight | 0x17801ef40 | 0x2c00 | | 54 | blk.10.post_ffw_norm.weight | 0x178021b40 | 0x2c00 | | 55 | blk.10.post_ffw_norm_1.weight | 0x178024740 | 0x2c00 | | 56 | blk.10.post_ffw_norm_2.weight | 0x178027340 | 0x2c00 | | 57 | blk.10.ffn_norm.weight | 0x178029f40 | 0x2c00 | | 58 | blk.10.pre_ffw_norm_2.weight | 0x17802cb40 | 0x2c00 | | 59 | blk.10.ffn_down_exps.scale | 0x17802f740 | 0x200 | | 60 | blk.10.ffn_gate_inp.weight | 0x17802f940 | 0x160000 | | 61 | blk.10.ffn_gate_inp.scale | 0x17818f940 | 0x2c00 | | 62 | blk.10.attn_k_norm.weight | 0x178192540 | 0x400 | | 63 | blk.10.attn_k.weight | 0x178192940 | 0xb00000 | | 64 | blk.10.attn_output.weight | 0x178c92940 | 0x1600000 | | 65 | blk.10.attn_q_norm.weight | 0x17a292940 | 0x400 | | 66 | blk.10.attn_q.weight | 0x17a292d40 | 0x1600000 | | 67 | blk.10.attn_v.weight | 0x17b892d40 | 0xb00000 | | 68 | blk.11.ffn_down_exps.weight | 0x17c392d40 | 0x1e400000 | | 69 | blk.11.ffn_gate_up_exps.weight | 0x19a792d40 | 0x3c800000 | | 70 | blk.11.layer_output_scale.weight | 0x1d6f92d40 | 0x4 | | 71 | blk.11.ffn_down_exps.scale | 0x1d6f92d60 | 0x200 | | 72 | blk.11.ffn_gate_inp.scale | 0x1d6f92f60 | 0x2c00 | | 73 | blk.11.attn_k_norm.weight | 0x1d6f95b60 | 0x800 | | 74 | blk.11.attn_k.weight | 0x1d6f96360 | 0x580000 | | 75 | blk.11.attn_output.weight | 0x1d7516360 | 0x2c00000 | | 76 | blk.11.attn_q_norm.weight | 0x1da116360 | 0x800 | | 77 | blk.11.attn_q.weight | 0x1da116b60 | 0x2c00000 | | 78 | blk.12.ffn_down_exps.weight | 0x1dcd16b60 | 0x1e400000 | | 79 | blk.12.ffn_gate_up_exps.weight | 0x1fb116b60 | 0x3c800000 | | 80 | blk.12.attn_norm.weight | 0x237916b60 | 0x2c00 | | 81 | blk.12.layer_output_scale.weight | 0x237919760 | 0x4 | | 82 | blk.12.ffn_down.weight | 0x237919780 | 0xb58000 | | 83 | blk.12.ffn_gate.weight | 0x238471780 | 0xb58000 | | 84 | blk.12.ffn_up.weight | 0x238fc9780 | 0xb58000 | | 85 | blk.12.post_attention_norm.weight | 0x239b21780 | 0x2c00 | | 86 | blk.12.post_ffw_norm.weight | 0x239b24380 | 0x2c00 | | 87 | blk.12.post_ffw_norm_1.weight | 0x239b26f80 | 0x2c00 | | 88 | blk.12.post_ffw_norm_2.weight | 0x239b29b80 | 0x2c00 | | 89 | blk.12.ffn_norm.weight | 0x239b2c780 | 0x2c00 | | 90 | blk.12.pre_ffw_norm_2.weight | 0x239b2f380 | 0x2c00 | | 91 | blk.12.ffn_down_exps.scale | 0x239b31f80 | 0x200 | | 92 | blk.12.ffn_gate_inp.weight | 0x239b32180 | 0x160000 | | 93 | blk.12.ffn_gate_inp.scale | 0x239c92180 | 0x2c00 | | 94 | blk.12.attn_k_norm.weight | 0x239c94d80 | 0x400 | | 95 | blk.12.attn_k.weight | 0x239c95180 | 0xb00000 | | 96 | blk.12.attn_output.weight | 0x23a795180 | 0x1600000 | | 97 | blk.12.attn_q_norm.weight | 0x23bd95180 | 0x400 | | 98 | blk.12.attn_q.weight | 0x23bd95580 | 0x1600000 | | 99 | blk.12.attn_v.weight | 0x23d395580 | 0xb00000 | | 100 | blk.13.ffn_down_exps.weight | 0x23de95580 | 0x1e400000 | | 101 | blk.13.ffn_gate_up_exps.weight | 0x25c295580 | 0x3c800000 | | 102 | blk.13.attn_norm.weight | 0x298a95580 | 0x2c00 | | 103 | blk.13.layer_output_scale.weight | 0x298a98180 | 0x4 | | 104 | blk.13.ffn_down.weight | 0x298a981a0 | 0xb58000 | | 105 | blk.13.ffn_gate.weight | 0x2995f01a0 | 0xb58000 | | 106 | blk.13.ffn_up.weight | 0x29a1481a0 | 0xb58000 | | 107 | blk.13.post_attention_norm.weight | 0x29aca01a0 | 0x2c00 | | 108 | blk.13.post_ffw_norm.weight | 0x29aca2da0 | 0x2c00 | | 109 | blk.13.post_ffw_norm_1.weight | 0x29aca59a0 | 0x2c00 | | 110 | blk.13.post_ffw_norm_2.weight | 0x29aca85a0 | 0x2c00 | | 111 | blk.13.ffn_norm.weight | 0x29acab1a0 | 0x2c00 | | 112 | blk.13.pre_ffw_norm_2.weight | 0x29acadda0 | 0x2c00 | | 113 | blk.13.ffn_down_exps.scale | 0x29acb09a0 | 0x200 | | 114 | blk.13.ffn_gate_inp.weight | 0x29acb0ba0 | 0x160000 | | 115 | blk.13.ffn_gate_inp.scale | 0x29ae10ba0 | 0x2c00 | | 116 | blk.13.attn_k_norm.weight | 0x29ae137a0 | 0x400 | | 117 | blk.13.attn_k.weight | 0x29ae13ba0 | 0xb00000 | | 118 | blk.13.attn_output.weight | 0x29b913ba0 | 0x1600000 | | 119 | blk.13.attn_q_norm.weight | 0x29cf13ba0 | 0x400 | | 120 | blk.13.attn_q.weight | 0x29cf13fa0 | 0x1600000 | | 121 | blk.13.attn_v.weight | 0x29e513fa0 | 0xb00000 | | 122 | blk.14.ffn_down_exps.weight | 0x29f013fa0 | 0x1e400000 | | 123 | blk.14.ffn_gate_up_exps.weight | 0x2bd413fa0 | 0x3c800000 | | 124 | blk.14.attn_norm.weight | 0x2f9c13fa0 | 0x2c00 | | 125 | blk.14.layer_output_scale.weight | 0x2f9c16ba0 | 0x4 | | 126 | blk.14.ffn_down.weight | 0x2f9c16bc0 | 0xb58000 | | 127 | blk.14.ffn_gate.weight | 0x2fa76ebc0 | 0xb58000 | | 128 | blk.14.ffn_up.weight | 0x2fb2c6bc0 | 0xb58000 | | 129 | blk.14.post_attention_norm.weight | 0x2fbe1ebc0 | 0x2c00 | | 130 | blk.14.post_ffw_norm.weight | 0x2fbe217c0 | 0x2c00 | | 131 | blk.14.post_ffw_norm_1.weight | 0x2fbe243c0 | 0x2c00 | | 132 | blk.14.post_ffw_norm_2.weight | 0x2fbe26fc0 | 0x2c00 | | 133 | blk.14.ffn_norm.weight | 0x2fbe29bc0 | 0x2c00 | | 134 | blk.14.pre_ffw_norm_2.weight | 0x2fbe2c7c0 | 0x2c00 | | 135 | blk.14.ffn_down_exps.scale | 0x2fbe2f3c0 | 0x200 | | 136 | blk.14.ffn_gate_inp.weight | 0x2fbe2f5c0 | 0x160000 | | 137 | blk.14.ffn_gate_inp.scale | 0x2fbf8f5c0 | 0x2c00 | | 138 | blk.14.attn_k_norm.weight | 0x2fbf921c0 | 0x400 | | 139 | blk.14.attn_k.weight | 0x2fbf925c0 | 0xb00000 | | 140 | blk.14.attn_output.weight | 0x2fca925c0 | 0x1600000 | | 141 | blk.14.attn_q_norm.weight | 0x2fe0925c0 | 0x400 | | 142 | blk.14.attn_q.weight | 0x2fe0929c0 | 0x1600000 | | 143 | blk.14.attn_v.weight | 0x2ff6929c0 | 0xb00000 | | 144 | blk.15.ffn_down_exps.weight | 0x3001929c0 | 0x1e400000 | | 145 | blk.15.ffn_gate_up_exps.weight | 0x31e5929c0 | 0x3c800000 | | 146 | blk.15.attn_norm.weight | 0x35ad929c0 | 0x2c00 | | 147 | blk.15.layer_output_scale.weight | 0x35ad955c0 | 0x4 | | 148 | blk.15.ffn_down.weight | 0x35ad955e0 | 0xb58000 | | 149 | blk.15.ffn_gate.weight | 0x35b8ed5e0 | 0xb58000 | | 150 | blk.15.ffn_up.weight | 0x35c4455e0 | 0xb58000 | | 151 | blk.15.post_attention_norm.weight | 0x35cf9d5e0 | 0x2c00 | | 152 | blk.15.post_ffw_norm.weight | 0x35cfa01e0 | 0x2c00 | | 153 | blk.15.post_ffw_norm_1.weight | 0x35cfa2de0 | 0x2c00 | | 154 | blk.15.post_ffw_norm_2.weight | 0x35cfa59e0 | 0x2c00 | | 155 | blk.15.ffn_norm.weight | 0x35cfa85e0 | 0x2c00 | | 156 | blk.15.pre_ffw_norm_2.weight | 0x35cfab1e0 | 0x2c00 | | 157 | blk.15.ffn_down_exps.scale | 0x35cfadde0 | 0x200 | | 158 | blk.15.ffn_gate_inp.weight | 0x35cfadfe0 | 0x160000 | | 159 | blk.15.ffn_gate_inp.scale | 0x35d10dfe0 | 0x2c00 | | 160 | blk.15.attn_k_norm.weight | 0x35d110be0 | 0x400 | | 161 | blk.15.attn_k.weight | 0x35d110fe0 | 0xb00000 | | 162 | blk.15.attn_output.weight | 0x35dc10fe0 | 0x1600000 | | 163 | blk.15.attn_q_norm.weight | 0x35f210fe0 | 0x400 | | 164 | blk.15.attn_q.weight | 0x35f2113e0 | 0x1600000 | | 165 | blk.15.attn_v.weight | 0x3608113e0 | 0xb00000 | | 166 | blk.16.ffn_down_exps.weight | 0x3613113e0 | 0x1e400000 | | 167 | blk.16.ffn_gate_up_exps.weight | 0x37f7113e0 | 0x3c800000 | | 168 | blk.16.attn_norm.weight | 0x3bbf113e0 | 0x2c00 | | 169 | blk.16.layer_output_scale.weight | 0x3bbf13fe0 | 0x4 | | 170 | blk.16.ffn_down.weight | 0x3bbf14000 | 0xb58000 | | 171 | blk.16.ffn_gate.weight | 0x3bca6c000 | 0xb58000 | | 172 | blk.16.ffn_up.weight | 0x3bd5c4000 | 0xb58000 | | 173 | blk.16.post_attention_norm.weight | 0x3be11c000 | 0x2c00 | | 174 | blk.16.post_ffw_norm.weight | 0x3be11ec00 | 0x2c00 | | 175 | blk.16.post_ffw_norm_1.weight | 0x3be121800 | 0x2c00 | | 176 | blk.16.post_ffw_norm_2.weight | 0x3be124400 | 0x2c00 | | 177 | blk.16.ffn_norm.weight | 0x3be127000 | 0x2c00 | | 178 | blk.16.pre_ffw_norm_2.weight | 0x3be129c00 | 0x2c00 | | 179 | blk.16.ffn_down_exps.scale | 0x3be12c800 | 0x200 | | 180 | blk.16.ffn_gate_inp.weight | 0x3be12ca00 | 0x160000 | | 181 | blk.16.ffn_gate_inp.scale | 0x3be28ca00 | 0x2c00 | | 182 | blk.16.attn_k_norm.weight | 0x3be28f600 | 0x400 | | 183 | blk.16.attn_k.weight | 0x3be28fa00 | 0xb00000 | | 184 | blk.16.attn_output.weight | 0x3bed8fa00 | 0x1600000 | | 185 | blk.16.attn_q_norm.weight | 0x3c038fa00 | 0x400 | | 186 | blk.16.attn_q.weight | 0x3c038fe00 | 0x1600000 | | 187 | blk.16.attn_v.weight | 0x3c198fe00 | 0xb00000 | | 188 | blk.17.ffn_gate_up_exps.weight | 0x3c248fe00 | 0x3c800000 | | 189 | blk.17.layer_output_scale.weight | 0x3fec8fe00 | 0x4 | | 190 | blk.17.ffn_down_exps.scale | 0x3fec8fe20 | 0x200 | | 191 | blk.17.ffn_gate_inp.scale | 0x3fec90020 | 0x2c00 | | 192 | blk.17.attn_k_norm.weight | 0x3fec92c20 | 0x800 | | 193 | blk.17.attn_k.weight | 0x3fec93420 | 0x580000 | | 194 | blk.17.attn_output.weight | 0x3ff213420 | 0x2c00000 | | 195 | blk.17.attn_q_norm.weight | 0x401e13420 | 0x800 | | 196 | blk.17.attn_q.weight | 0x401e13c20 | 0x2c00000 | | 197 | blk.18.ffn_down_exps.weight | 0x404a13c20 | 0x1e400000 | | 198 | blk.18.ffn_gate_up_exps.weight | 0x422e13c20 | 0x3c800000 | | 199 | blk.18.attn_norm.weight | 0x45f613c20 | 0x2c00 | | 200 | blk.18.layer_output_scale.weight | 0x45f616820 | 0x4 | | 201 | blk.18.ffn_down.weight | 0x45f616840 | 0xb58000 | | 202 | blk.18.ffn_gate.weight | 0x46016e840 | 0xb58000 | | 203 | blk.18.ffn_up.weight | 0x460cc6840 | 0xb58000 | | 204 | blk.18.post_attention_norm.weight | 0x46181e840 | 0x2c00 | | 205 | blk.18.post_ffw_norm.weight | 0x461821440 | 0x2c00 | | 206 | blk.18.post_ffw_norm_1.weight | 0x461824040 | 0x2c00 | | 207 | blk.18.post_ffw_norm_2.weight | 0x461826c40 | 0x2c00 | | 208 | blk.18.ffn_norm.weight | 0x461829840 | 0x2c00 | | 209 | blk.18.pre_ffw_norm_2.weight | 0x46182c440 | 0x2c00 | | 210 | blk.18.ffn_down_exps.scale | 0x46182f040 | 0x200 | | 211 | blk.18.ffn_gate_inp.weight | 0x46182f240 | 0x160000 | | 212 | blk.18.ffn_gate_inp.scale | 0x46198f240 | 0x2c00 | | 213 | blk.18.attn_k_norm.weight | 0x461991e40 | 0x400 | | 214 | blk.18.attn_k.weight | 0x461992240 | 0xb00000 | | 215 | blk.18.attn_output.weight | 0x462492240 | 0x1600000 | | 216 | blk.18.attn_q_norm.weight | 0x463a92240 | 0x400 | | 217 | blk.18.attn_q.weight | 0x463a92640 | 0x1600000 | | 218 | blk.18.attn_v.weight | 0x465092640 | 0xb00000 | | 219 | blk.19.ffn_down_exps.weight | 0x465b92640 | 0x1e400000 | | 220 | blk.19.ffn_gate_up_exps.weight | 0x483f92640 | 0x3c800000 | | 221 | blk.19.attn_norm.weight | 0x4c0792640 | 0x2c00 | | 222 | blk.19.layer_output_scale.weight | 0x4c0795240 | 0x4 | | 223 | blk.19.ffn_down.weight | 0x4c0795260 | 0xb58000 | | 224 | blk.19.ffn_gate.weight | 0x4c12ed260 | 0xb58000 | | 225 | blk.19.ffn_up.weight | 0x4c1e45260 | 0xb58000 | | 226 | blk.19.post_attention_norm.weight | 0x4c299d260 | 0x2c00 | | 227 | blk.19.post_ffw_norm.weight | 0x4c299fe60 | 0x2c00 | | 228 | blk.19.post_ffw_norm_1.weight | 0x4c29a2a60 | 0x2c00 | | 229 | blk.19.post_ffw_norm_2.weight | 0x4c29a5660 | 0x2c00 | | 230 | blk.19.ffn_norm.weight | 0x4c29a8260 | 0x2c00 | | 231 | blk.19.pre_ffw_norm_2.weight | 0x4c29aae60 | 0x2c00 | | 232 | blk.19.ffn_down_exps.scale | 0x4c29ada60 | 0x200 | | 233 | blk.19.ffn_gate_inp.weight | 0x4c29adc60 | 0x160000 | | 234 | blk.19.ffn_gate_inp.scale | 0x4c2b0dc60 | 0x2c00 | | 235 | blk.19.attn_k_norm.weight | 0x4c2b10860 | 0x400 | | 236 | blk.19.attn_k.weight | 0x4c2b10c60 | 0xb00000 | | 237 | blk.19.attn_output.weight | 0x4c3610c60 | 0x1600000 | | 238 | blk.19.attn_q_norm.weight | 0x4c4c10c60 | 0x400 | | 239 | blk.19.attn_q.weight | 0x4c4c11060 | 0x1600000 | | 240 | blk.19.attn_v.weight | 0x4c6211060 | 0xb00000 | | 241 | blk.2.ffn_down_exps.weight | 0x4c6d11060 | 0x1e400000 | | 242 | blk.2.ffn_gate_up_exps.weight | 0x4e5111060 | 0x3c800000 | | 243 | blk.2.attn_norm.weight | 0x521911060 | 0x2c00 | | 244 | blk.2.layer_output_scale.weight | 0x521913c60 | 0x4 | | 245 | blk.2.ffn_down.weight | 0x521913c80 | 0xb58000 | | 246 | blk.2.ffn_gate.weight | 0x52246bc80 | 0xb58000 | | 247 | blk.2.ffn_up.weight | 0x522fc3c80 | 0xb58000 | | 248 | blk.2.post_attention_norm.weight | 0x523b1bc80 | 0x2c00 | | 249 | blk.2.post_ffw_norm.weight | 0x523b1e880 | 0x2c00 | | 250 | blk.2.post_ffw_norm_1.weight | 0x523b21480 | 0x2c00 | | 251 | blk.2.post_ffw_norm_2.weight | 0x523b24080 | 0x2c00 | | 252 | blk.2.ffn_norm.weight | 0x523b26c80 | 0x2c00 | | 253 | blk.2.pre_ffw_norm_2.weight | 0x523b29880 | 0x2c00 | | 254 | blk.2.ffn_down_exps.scale | 0x523b2c480 | 0x200 | | 255 | blk.2.ffn_gate_inp.weight | 0x523b2c680 | 0x160000 | | 256 | blk.2.ffn_gate_inp.scale | 0x523c8c680 | 0x2c00 | | 257 | blk.2.attn_k_norm.weight | 0x523c8f280 | 0x400 | | 258 | blk.2.attn_k.weight | 0x523c8f680 | 0xb00000 | | 259 | blk.2.attn_output.weight | 0x52478f680 | 0x1600000 | | 260 | blk.2.attn_q_norm.weight | 0x525d8f680 | 0x400 | | 261 | blk.2.attn_q.weight | 0x525d8fa80 | 0x1600000 | | 262 | blk.2.attn_v.weight | 0x52738fa80 | 0xb00000 | | 263 | blk.20.ffn_down_exps.weight | 0x527e8fa80 | 0x1e400000 | | 264 | blk.20.ffn_gate_up_exps.weight | 0x54628fa80 | 0x3c800000 | | 265 | blk.20.attn_norm.weight | 0x582a8fa80 | 0x2c00 | | 266 | blk.20.layer_output_scale.weight | 0x582a92680 | 0x4 | | 267 | blk.20.ffn_down.weight | 0x582a926a0 | 0xb58000 | | 268 | blk.20.ffn_gate.weight | 0x5835ea6a0 | 0xb58000 | | 269 | blk.20.ffn_up.weight | 0x5841426a0 | 0xb58000 | | 270 | blk.20.post_attention_norm.weight | 0x584c9a6a0 | 0x2c00 | | 271 | blk.20.post_ffw_norm.weight | 0x584c9d2a0 | 0x2c00 | | 272 | blk.20.post_ffw_norm_1.weight | 0x584c9fea0 | 0x2c00 | | 273 | blk.20.post_ffw_norm_2.weight | 0x584ca2aa0 | 0x2c00 | | 274 | blk.20.ffn_norm.weight | 0x584ca56a0 | 0x2c00 | | 275 | blk.20.pre_ffw_norm_2.weight | 0x584ca82a0 | 0x2c00 | | 276 | blk.20.ffn_down_exps.scale | 0x584caaea0 | 0x200 | | 277 | blk.20.ffn_gate_inp.weight | 0x584cab0a0 | 0x160000 | | 278 | blk.20.ffn_gate_inp.scale | 0x584e0b0a0 | 0x2c00 | | 279 | blk.20.attn_k_norm.weight | 0x584e0dca0 | 0x400 | | 280 | blk.20.attn_k.weight | 0x584e0e0a0 | 0xb00000 | | 281 | blk.20.attn_output.weight | 0x58590e0a0 | 0x1600000 | | 282 | blk.20.attn_q_norm.weight | 0x586f0e0a0 | 0x400 | | 283 | blk.20.attn_q.weight | 0x586f0e4a0 | 0x1600000 | | 284 | blk.20.attn_v.weight | 0x58850e4a0 | 0xb00000 | | 285 | blk.21.ffn_down_exps.weight | 0x58900e4a0 | 0x1e400000 | | 286 | blk.21.ffn_gate_up_exps.weight | 0x5a740e4a0 | 0x3c800000 | | 287 | blk.21.attn_norm.weight | 0x5e3c0e4a0 | 0x2c00 | | 288 | blk.21.layer_output_scale.weight | 0x5e3c110a0 | 0x4 | | 289 | blk.21.ffn_down.weight | 0x5e3c110c0 | 0xb58000 | | 290 | blk.21.ffn_gate.weight | 0x5e47690c0 | 0xb58000 | | 291 | blk.21.ffn_up.weight | 0x5e52c10c0 | 0xb58000 | | 292 | blk.21.post_attention_norm.weight | 0x5e5e190c0 | 0x2c00 | | 293 | blk.21.post_ffw_norm.weight | 0x5e5e1bcc0 | 0x2c00 | | 294 | blk.21.post_ffw_norm_1.weight | 0x5e5e1e8c0 | 0x2c00 | | 295 | blk.21.post_ffw_norm_2.weight | 0x5e5e214c0 | 0x2c00 | | 296 | blk.21.ffn_norm.weight | 0x5e5e240c0 | 0x2c00 | | 297 | blk.21.pre_ffw_norm_2.weight | 0x5e5e26cc0 | 0x2c00 | | 298 | blk.21.ffn_down_exps.scale | 0x5e5e298c0 | 0x200 | | 299 | blk.21.ffn_gate_inp.weight | 0x5e5e29ac0 | 0x160000 | | 300 | blk.21.ffn_gate_inp.scale | 0x5e5f89ac0 | 0x2c00 | | 301 | blk.21.attn_k_norm.weight | 0x5e5f8c6c0 | 0x400 | | 302 | blk.21.attn_k.weight | 0x5e5f8cac0 | 0xb00000 | | 303 | blk.21.attn_output.weight | 0x5e6a8cac0 | 0x1600000 | | 304 | blk.21.attn_q_norm.weight | 0x5e808cac0 | 0x400 | | 305 | blk.21.attn_q.weight | 0x5e808cec0 | 0x1600000 | | 306 | blk.21.attn_v.weight | 0x5e968cec0 | 0xb00000 | | 307 | blk.22.ffn_down_exps.weight | 0x5ea18cec0 | 0x1e400000 | | 308 | blk.22.ffn_gate_up_exps.weight | 0x60858cec0 | 0x3c800000 | | 309 | blk.22.attn_norm.weight | 0x644d8cec0 | 0x2c00 | | 310 | blk.22.layer_output_scale.weight | 0x644d8fac0 | 0x4 | | 311 | blk.22.ffn_down.weight | 0x644d8fae0 | 0xb58000 | | 312 | blk.22.ffn_gate.weight | 0x6458e7ae0 | 0xb58000 | | 313 | blk.22.ffn_up.weight | 0x64643fae0 | 0xb58000 | | 314 | blk.22.post_attention_norm.weight | 0x646f97ae0 | 0x2c00 | | 315 | blk.22.post_ffw_norm.weight | 0x646f9a6e0 | 0x2c00 | | 316 | blk.22.post_ffw_norm_1.weight | 0x646f9d2e0 | 0x2c00 | | 317 | blk.22.post_ffw_norm_2.weight | 0x646f9fee0 | 0x2c00 | | 318 | blk.22.ffn_norm.weight | 0x646fa2ae0 | 0x2c00 | | 319 | blk.22.pre_ffw_norm_2.weight | 0x646fa56e0 | 0x2c00 | | 320 | blk.22.ffn_down_exps.scale | 0x646fa82e0 | 0x200 | | 321 | blk.22.ffn_gate_inp.weight | 0x646fa84e0 | 0x160000 | | 322 | blk.22.ffn_gate_inp.scale | 0x6471084e0 | 0x2c00 | | 323 | blk.22.attn_k_norm.weight | 0x64710b0e0 | 0x400 | | 324 | blk.22.attn_k.weight | 0x64710b4e0 | 0xb00000 | | 325 | blk.22.attn_output.weight | 0x647c0b4e0 | 0x1600000 | | 326 | blk.22.attn_q_norm.weight | 0x64920b4e0 | 0x400 | | 327 | blk.22.attn_q.weight | 0x64920b8e0 | 0x1600000 | | 328 | blk.22.attn_v.weight | 0x64a80b8e0 | 0xb00000 | | 329 | blk.23.ffn_gate_up_exps.weight | 0x64b30b8e0 | 0x3c800000 | | 330 | blk.23.layer_output_scale.weight | 0x687b0b8e0 | 0x4 | | 331 | blk.23.ffn_down_exps.scale | 0x687b0b900 | 0x200 | | 332 | blk.23.ffn_gate_inp.scale | 0x687b0bb00 | 0x2c00 | | 333 | blk.23.attn_k_norm.weight | 0x687b0e700 | 0x800 | | 334 | blk.23.attn_k.weight | 0x687b0ef00 | 0x580000 | | 335 | blk.23.attn_output.weight | 0x68808ef00 | 0x2c00000 | | 336 | blk.23.attn_q_norm.weight | 0x68ac8ef00 | 0x800 | | 337 | blk.23.attn_q.weight | 0x68ac8f700 | 0x2c00000 | | 338 | blk.24.ffn_down_exps.weight | 0x68d88f700 | 0x1e400000 | | 339 | blk.24.ffn_gate_up_exps.weight | 0x6abc8f700 | 0x3c800000 | | 340 | blk.24.attn_norm.weight | 0x6e848f700 | 0x2c00 | | 341 | blk.24.layer_output_scale.weight | 0x6e8492300 | 0x4 | | 342 | blk.24.ffn_down.weight | 0x6e8492320 | 0xb58000 | | 343 | blk.24.ffn_gate.weight | 0x6e8fea320 | 0xb58000 | | 344 | blk.24.ffn_up.weight | 0x6e9b42320 | 0xb58000 | | 345 | blk.24.post_attention_norm.weight | 0x6ea69a320 | 0x2c00 | | 346 | blk.24.post_ffw_norm.weight | 0x6ea69cf20 | 0x2c00 | | 347 | blk.24.post_ffw_norm_1.weight | 0x6ea69fb20 | 0x2c00 | | 348 | blk.24.post_ffw_norm_2.weight | 0x6ea6a2720 | 0x2c00 | | 349 | blk.24.ffn_norm.weight | 0x6ea6a5320 | 0x2c00 | | 350 | blk.24.pre_ffw_norm_2.weight | 0x6ea6a7f20 | 0x2c00 | | 351 | blk.24.ffn_down_exps.scale | 0x6ea6aab20 | 0x200 | | 352 | blk.24.ffn_gate_inp.weight | 0x6ea6aad20 | 0x160000 | | 353 | blk.24.ffn_gate_inp.scale | 0x6ea80ad20 | 0x2c00 | | 354 | blk.24.attn_k_norm.weight | 0x6ea80d920 | 0x400 | | 355 | blk.24.attn_k.weight | 0x6ea80dd20 | 0xb00000 | | 356 | blk.24.attn_output.weight | 0x6eb30dd20 | 0x1600000 | | 357 | blk.24.attn_q_norm.weight | 0x6ec90dd20 | 0x400 | | 358 | blk.24.attn_q.weight | 0x6ec90e120 | 0x1600000 | | 359 | blk.24.attn_v.weight | 0x6edf0e120 | 0xb00000 | | 360 | blk.25.ffn_down_exps.weight | 0x6eea0e120 | 0x1e400000 | | 361 | blk.25.ffn_gate_up_exps.weight | 0x70ce0e120 | 0x3c800000 | | 362 | blk.25.attn_norm.weight | 0x74960e120 | 0x2c00 | | 363 | blk.25.layer_output_scale.weight | 0x749610d20 | 0x4 | | 364 | blk.25.ffn_down.weight | 0x749610d40 | 0xb58000 | | 365 | blk.25.ffn_gate.weight | 0x74a168d40 | 0xb58000 | | 366 | blk.25.ffn_up.weight | 0x74acc0d40 | 0xb58000 | | 367 | blk.25.post_attention_norm.weight | 0x74b818d40 | 0x2c00 | | 368 | blk.25.post_ffw_norm.weight | 0x74b81b940 | 0x2c00 | | 369 | blk.25.post_ffw_norm_1.weight | 0x74b81e540 | 0x2c00 | | 370 | blk.25.post_ffw_norm_2.weight | 0x74b821140 | 0x2c00 | | 371 | blk.25.ffn_norm.weight | 0x74b823d40 | 0x2c00 | | 372 | blk.25.pre_ffw_norm_2.weight | 0x74b826940 | 0x2c00 | | 373 | blk.25.ffn_down_exps.scale | 0x74b829540 | 0x200 | | 374 | blk.25.ffn_gate_inp.weight | 0x74b829740 | 0x160000 | | 375 | blk.25.ffn_gate_inp.scale | 0x74b989740 | 0x2c00 | | 376 | blk.25.attn_k_norm.weight | 0x74b98c340 | 0x400 | | 377 | blk.25.attn_k.weight | 0x74b98c740 | 0xb00000 | | 378 | blk.25.attn_output.weight | 0x74c48c740 | 0x1600000 | | 379 | blk.25.attn_q_norm.weight | 0x74da8c740 | 0x400 | | 380 | blk.25.attn_q.weight | 0x74da8cb40 | 0x1600000 | | 381 | blk.25.attn_v.weight | 0x74f08cb40 | 0xb00000 | | 382 | blk.26.ffn_down_exps.weight | 0x74fb8cb40 | 0x1e400000 | | 383 | blk.26.ffn_gate_up_exps.weight | 0x76df8cb40 | 0x3c800000 | | 384 | blk.26.attn_norm.weight | 0x7aa78cb40 | 0x2c00 | | 385 | blk.26.layer_output_scale.weight | 0x7aa78f740 | 0x4 | | 386 | blk.26.ffn_down.weight | 0x7aa78f760 | 0xb58000 | | 387 | blk.26.ffn_gate.weight | 0x7ab2e7760 | 0xb58000 | | 388 | blk.26.ffn_up.weight | 0x7abe3f760 | 0xb58000 | | 389 | blk.26.post_attention_norm.weight | 0x7ac997760 | 0x2c00 | | 390 | blk.26.post_ffw_norm.weight | 0x7ac99a360 | 0x2c00 | | 391 | blk.26.post_ffw_norm_1.weight | 0x7ac99cf60 | 0x2c00 | | 392 | blk.26.post_ffw_norm_2.weight | 0x7ac99fb60 | 0x2c00 | | 393 | blk.26.ffn_norm.weight | 0x7ac9a2760 | 0x2c00 | | 394 | blk.26.pre_ffw_norm_2.weight | 0x7ac9a5360 | 0x2c00 | | 395 | blk.26.ffn_down_exps.scale | 0x7ac9a7f60 | 0x200 | | 396 | blk.26.ffn_gate_inp.weight | 0x7ac9a8160 | 0x160000 | | 397 | blk.26.ffn_gate_inp.scale | 0x7acb08160 | 0x2c00 | | 398 | blk.26.attn_k_norm.weight | 0x7acb0ad60 | 0x400 | | 399 | blk.26.attn_k.weight | 0x7acb0b160 | 0xb00000 | | 400 | blk.26.attn_output.weight | 0x7ad60b160 | 0x1600000 | | 401 | blk.26.attn_q_norm.weight | 0x7aec0b160 | 0x400 | | 402 | blk.26.attn_q.weight | 0x7aec0b560 | 0x1600000 | | 403 | blk.26.attn_v.weight | 0x7b020b560 | 0xb00000 | | 404 | blk.27.ffn_down_exps.weight | 0x7b0d0b560 | 0x1e400000 | | 405 | blk.27.ffn_gate_up_exps.weight | 0x7cf10b560 | 0x3c800000 | | 406 | blk.27.attn_norm.weight | 0x80b90b560 | 0x2c00 | | 407 | blk.27.layer_output_scale.weight | 0x80b90e160 | 0x4 | | 408 | blk.27.ffn_down.weight | 0x80b90e180 | 0xb58000 | | 409 | blk.27.ffn_gate.weight | 0x80c466180 | 0xb58000 | | 410 | blk.27.ffn_up.weight | 0x80cfbe180 | 0xb58000 | | 411 | blk.27.post_attention_norm.weight | 0x80db16180 | 0x2c00 | | 412 | blk.27.post_ffw_norm.weight | 0x80db18d80 | 0x2c00 | | 413 | blk.27.post_ffw_norm_1.weight | 0x80db1b980 | 0x2c00 | | 414 | blk.27.post_ffw_norm_2.weight | 0x80db1e580 | 0x2c00 | | 415 | blk.27.ffn_norm.weight | 0x80db21180 | 0x2c00 | | 416 | blk.27.pre_ffw_norm_2.weight | 0x80db23d80 | 0x2c00 | | 417 | blk.27.ffn_down_exps.scale | 0x80db26980 | 0x200 | | 418 | blk.27.ffn_gate_inp.weight | 0x80db26b80 | 0x160000 | | 419 | blk.27.ffn_gate_inp.scale | 0x80dc86b80 | 0x2c00 | | 420 | blk.27.attn_k_norm.weight | 0x80dc89780 | 0x400 | | 421 | blk.27.attn_k.weight | 0x80dc89b80 | 0xb00000 | | 422 | blk.27.attn_output.weight | 0x80e789b80 | 0x1600000 | | 423 | blk.27.attn_q_norm.weight | 0x80fd89b80 | 0x400 | | 424 | blk.27.attn_q.weight | 0x80fd89f80 | 0x1600000 | | 425 | blk.27.attn_v.weight | 0x811389f80 | 0xb00000 | | 426 | blk.28.ffn_down_exps.weight | 0x811e89f80 | 0x1e400000 | | 427 | blk.28.ffn_gate_up_exps.weight | 0x830289f80 | 0x3c800000 | | 428 | blk.28.attn_norm.weight | 0x86ca89f80 | 0x2c00 | | 429 | blk.28.layer_output_scale.weight | 0x86ca8cb80 | 0x4 | | 430 | blk.28.ffn_down.weight | 0x86ca8cba0 | 0xb58000 | | 431 | blk.28.ffn_gate.weight | 0x86d5e4ba0 | 0xb58000 | | 432 | blk.28.ffn_up.weight | 0x86e13cba0 | 0xb58000 | | 433 | blk.28.post_attention_norm.weight | 0x86ec94ba0 | 0x2c00 | | 434 | blk.28.post_ffw_norm.weight | 0x86ec977a0 | 0x2c00 | | 435 | blk.28.post_ffw_norm_1.weight | 0x86ec9a3a0 | 0x2c00 | | 436 | blk.28.post_ffw_norm_2.weight | 0x86ec9cfa0 | 0x2c00 | | 437 | blk.28.ffn_norm.weight | 0x86ec9fba0 | 0x2c00 | | 438 | blk.28.pre_ffw_norm_2.weight | 0x86eca27a0 | 0x2c00 | | 439 | blk.28.ffn_down_exps.scale | 0x86eca53a0 | 0x200 | | 440 | blk.28.ffn_gate_inp.weight | 0x86eca55a0 | 0x160000 | | 441 | blk.28.ffn_gate_inp.scale | 0x86ee055a0 | 0x2c00 | | 442 | blk.28.attn_k_norm.weight | 0x86ee081a0 | 0x400 | | 443 | blk.28.attn_k.weight | 0x86ee085a0 | 0xb00000 | | 444 | blk.28.attn_output.weight | 0x86f9085a0 | 0x1600000 | | 445 | blk.28.attn_q_norm.weight | 0x870f085a0 | 0x400 | | 446 | blk.28.attn_q.weight | 0x870f089a0 | 0x1600000 | | 447 | blk.28.attn_v.weight | 0x8725089a0 | 0xb00000 | | 448 | blk.29.ffn_gate_up_exps.weight | 0x8730089a0 | 0x3c800000 | | 449 | blk.29.layer_output_scale.weight | 0x8af8089a0 | 0x4 | | 450 | blk.29.ffn_down_exps.scale | 0x8af8089c0 | 0x200 | | 451 | blk.29.ffn_gate_inp.scale | 0x8af808bc0 | 0x2c00 | | 452 | blk.29.attn_k_norm.weight | 0x8af80b7c0 | 0x800 | | 453 | blk.29.attn_k.weight | 0x8af80bfc0 | 0x580000 | | 454 | blk.29.attn_output.weight | 0x8afd8bfc0 | 0x2c00000 | | 455 | blk.29.attn_q_norm.weight | 0x8b298bfc0 | 0x800 | | 456 | blk.29.attn_q.weight | 0x8b298c7c0 | 0x2c00000 | | 457 | blk.3.ffn_down_exps.weight | 0x8b558c7c0 | 0x1e400000 | | 458 | blk.3.ffn_gate_up_exps.weight | 0x8d398c7c0 | 0x3c800000 | | 459 | blk.3.attn_norm.weight | 0x91018c7c0 | 0x2c00 | | 460 | blk.3.layer_output_scale.weight | 0x91018f3c0 | 0x4 | | 461 | blk.3.ffn_down.weight | 0x91018f3e0 | 0xb58000 | | 462 | blk.3.ffn_gate.weight | 0x910ce73e0 | 0xb58000 | | 463 | blk.3.ffn_up.weight | 0x91183f3e0 | 0xb58000 | | 464 | blk.3.post_attention_norm.weight | 0x9123973e0 | 0x2c00 | | 465 | blk.3.post_ffw_norm.weight | 0x912399fe0 | 0x2c00 | | 466 | blk.3.post_ffw_norm_1.weight | 0x91239cbe0 | 0x2c00 | | 467 | blk.3.post_ffw_norm_2.weight | 0x91239f7e0 | 0x2c00 | | 468 | blk.3.ffn_norm.weight | 0x9123a23e0 | 0x2c00 | | 469 | blk.3.pre_ffw_norm_2.weight | 0x9123a4fe0 | 0x2c00 | | 470 | blk.3.ffn_down_exps.scale | 0x9123a7be0 | 0x200 | | 471 | blk.3.ffn_gate_inp.weight | 0x9123a7de0 | 0x160000 | | 472 | blk.3.ffn_gate_inp.scale | 0x912507de0 | 0x2c00 | | 473 | blk.3.attn_k_norm.weight | 0x91250a9e0 | 0x400 | | 474 | blk.3.attn_k.weight | 0x91250ade0 | 0xb00000 | | 475 | blk.3.attn_output.weight | 0x91300ade0 | 0x1600000 | | 476 | blk.3.attn_q_norm.weight | 0x91460ade0 | 0x400 | | 477 | blk.3.attn_q.weight | 0x91460b1e0 | 0x1600000 | | 478 | blk.3.attn_v.weight | 0x915c0b1e0 | 0xb00000 | | 479 | blk.4.ffn_down_exps.weight | 0x91670b1e0 | 0x1e400000 | | 480 | blk.4.ffn_gate_up_exps.weight | 0x934b0b1e0 | 0x3c800000 | | 481 | blk.4.attn_norm.weight | 0x97130b1e0 | 0x2c00 | | 482 | blk.4.layer_output_scale.weight | 0x97130dde0 | 0x4 | | 483 | blk.4.ffn_down.weight | 0x97130de00 | 0xb58000 | | 484 | blk.4.ffn_gate.weight | 0x971e65e00 | 0xb58000 | | 485 | blk.4.ffn_up.weight | 0x9729bde00 | 0xb58000 | | 486 | blk.4.post_attention_norm.weight | 0x973515e00 | 0x2c00 | | 487 | blk.4.post_ffw_norm.weight | 0x973518a00 | 0x2c00 | | 488 | blk.4.post_ffw_norm_1.weight | 0x97351b600 | 0x2c00 | | 489 | blk.4.post_ffw_norm_2.weight | 0x97351e200 | 0x2c00 | | 490 | blk.4.ffn_norm.weight | 0x973520e00 | 0x2c00 | | 491 | blk.4.pre_ffw_norm_2.weight | 0x973523a00 | 0x2c00 | | 492 | blk.4.ffn_down_exps.scale | 0x973526600 | 0x200 | | 493 | blk.4.ffn_gate_inp.weight | 0x973526800 | 0x160000 | | 494 | blk.4.ffn_gate_inp.scale | 0x973686800 | 0x2c00 | | 495 | blk.4.attn_k_norm.weight | 0x973689400 | 0x400 | | 496 | blk.4.attn_k.weight | 0x973689800 | 0xb00000 | | 497 | blk.4.attn_output.weight | 0x974189800 | 0x1600000 | | 498 | blk.4.attn_q_norm.weight | 0x975789800 | 0x400 | | 499 | blk.4.attn_q.weight | 0x975789c00 | 0x1600000 | | 500 | blk.4.attn_v.weight | 0x976d89c00 | 0xb00000 | | 501 | blk.5.ffn_down_exps.weight | 0x977889c00 | 0x1e400000 | | 502 | blk.5.ffn_gate_up_exps.weight | 0x995c89c00 | 0x3c800000 | | 503 | blk.5.layer_output_scale.weight | 0x9d2489c00 | 0x4 | | 504 | blk.5.ffn_down_exps.scale | 0x9d2489c20 | 0x200 | | 505 | blk.5.ffn_gate_inp.scale | 0x9d2489e20 | 0x2c00 | | 506 | blk.5.attn_k_norm.weight | 0x9d248ca20 | 0x800 | | 507 | blk.5.attn_k.weight | 0x9d248d220 | 0x580000 | | 508 | blk.5.attn_output.weight | 0x9d2a0d220 | 0x2c00000 | | 509 | blk.5.attn_q_norm.weight | 0x9d560d220 | 0x800 | | 510 | blk.5.attn_q.weight | 0x9d560da20 | 0x2c00000 | | 511 | blk.6.ffn_down_exps.weight | 0x9d820da20 | 0x1e400000 | | 512 | blk.6.ffn_gate_up_exps.weight | 0x9f660da20 | 0x3c800000 | | 513 | blk.6.attn_norm.weight | 0xa32e0da20 | 0x2c00 | | 514 | blk.6.layer_output_scale.weight | 0xa32e10620 | 0x4 | | 515 | blk.6.ffn_down.weight | 0xa32e10640 | 0xb58000 | | 516 | blk.6.ffn_gate.weight | 0xa33968640 | 0xb58000 | | 517 | blk.6.ffn_up.weight | 0xa344c0640 | 0xb58000 | | 518 | blk.6.post_attention_norm.weight | 0xa35018640 | 0x2c00 | | 519 | blk.6.post_ffw_norm.weight | 0xa3501b240 | 0x2c00 | | 520 | blk.6.post_ffw_norm_1.weight | 0xa3501de40 | 0x2c00 | | 521 | blk.6.post_ffw_norm_2.weight | 0xa35020a40 | 0x2c00 | | 522 | blk.6.ffn_norm.weight | 0xa35023640 | 0x2c00 | | 523 | blk.6.pre_ffw_norm_2.weight | 0xa35026240 | 0x2c00 | | 524 | blk.6.ffn_down_exps.scale | 0xa35028e40 | 0x200 | | 525 | blk.6.ffn_gate_inp.weight | 0xa35029040 | 0x160000 | | 526 | blk.6.ffn_gate_inp.scale | 0xa35189040 | 0x2c00 | | 527 | blk.6.attn_k_norm.weight | 0xa3518bc40 | 0x400 | | 528 | blk.6.attn_k.weight | 0xa3518c040 | 0xb00000 | | 529 | blk.6.attn_output.weight | 0xa35c8c040 | 0x1600000 | | 530 | blk.6.attn_q_norm.weight | 0xa3728c040 | 0x400 | | 531 | blk.6.attn_q.weight | 0xa3728c440 | 0x1600000 | | 532 | blk.6.attn_v.weight | 0xa3888c440 | 0xb00000 | | 533 | blk.7.ffn_down_exps.weight | 0xa3938c440 | 0x1e400000 | | 534 | blk.7.ffn_gate_up_exps.weight | 0xa5778c440 | 0x3c800000 | | 535 | blk.7.attn_norm.weight | 0xa93f8c440 | 0x2c00 | | 536 | blk.7.layer_output_scale.weight | 0xa93f8f040 | 0x4 | | 537 | blk.7.ffn_down.weight | 0xa93f8f060 | 0xb58000 | | 538 | blk.7.ffn_gate.weight | 0xa94ae7060 | 0xb58000 | | 539 | blk.7.ffn_up.weight | 0xa9563f060 | 0xb58000 | | 540 | blk.7.post_attention_norm.weight | 0xa96197060 | 0x2c00 | | 541 | blk.7.post_ffw_norm.weight | 0xa96199c60 | 0x2c00 | | 542 | blk.7.post_ffw_norm_1.weight | 0xa9619c860 | 0x2c00 | | 543 | blk.7.post_ffw_norm_2.weight | 0xa9619f460 | 0x2c00 | | 544 | blk.7.ffn_norm.weight | 0xa961a2060 | 0x2c00 | | 545 | blk.7.pre_ffw_norm_2.weight | 0xa961a4c60 | 0x2c00 | | 546 | blk.7.ffn_down_exps.scale | 0xa961a7860 | 0x200 | | 547 | blk.7.ffn_gate_inp.weight | 0xa961a7a60 | 0x160000 | | 548 | blk.7.ffn_gate_inp.scale | 0xa96307a60 | 0x2c00 | | 549 | blk.7.attn_k_norm.weight | 0xa9630a660 | 0x400 | | 550 | blk.7.attn_k.weight | 0xa9630aa60 | 0xb00000 | | 551 | blk.7.attn_output.weight | 0xa96e0aa60 | 0x1600000 | | 552 | blk.7.attn_q_norm.weight | 0xa9840aa60 | 0x400 | | 553 | blk.7.attn_q.weight | 0xa9840ae60 | 0x1600000 | | 554 | blk.7.attn_v.weight | 0xa99a0ae60 | 0xb00000 | | 555 | blk.8.ffn_down_exps.weight | 0xa9a50ae60 | 0x1e400000 | | 556 | blk.8.ffn_gate_up_exps.weight | 0xab890ae60 | 0x3c800000 | | 557 | blk.8.attn_norm.weight | 0xaf510ae60 | 0x2c00 | | 558 | blk.8.layer_output_scale.weight | 0xaf510da60 | 0x4 | | 559 | blk.8.ffn_down.weight | 0xaf510da80 | 0xb58000 | | 560 | blk.8.ffn_gate.weight | 0xaf5c65a80 | 0xb58000 | | 561 | blk.8.ffn_up.weight | 0xaf67bda80 | 0xb58000 | | 562 | blk.8.post_attention_norm.weight | 0xaf7315a80 | 0x2c00 | | 563 | blk.8.post_ffw_norm.weight | 0xaf7318680 | 0x2c00 | | 564 | blk.8.post_ffw_norm_1.weight | 0xaf731b280 | 0x2c00 | | 565 | blk.8.post_ffw_norm_2.weight | 0xaf731de80 | 0x2c00 | | 566 | blk.8.ffn_norm.weight | 0xaf7320a80 | 0x2c00 | | 567 | blk.8.pre_ffw_norm_2.weight | 0xaf7323680 | 0x2c00 | | 568 | blk.8.ffn_down_exps.scale | 0xaf7326280 | 0x200 | | 569 | blk.8.ffn_gate_inp.weight | 0xaf7326480 | 0x160000 | | 570 | blk.8.ffn_gate_inp.scale | 0xaf7486480 | 0x2c00 | | 571 | blk.8.attn_k_norm.weight | 0xaf7489080 | 0x400 | | 572 | blk.8.attn_k.weight | 0xaf7489480 | 0xb00000 | | 573 | blk.8.attn_output.weight | 0xaf7f89480 | 0x1600000 | | 574 | blk.8.attn_q_norm.weight | 0xaf9589480 | 0x400 | | 575 | blk.8.attn_q.weight | 0xaf9589880 | 0x1600000 | | 576 | blk.8.attn_v.weight | 0xafab89880 | 0xb00000 | | 577 | blk.9.ffn_down_exps.weight | 0xafb689880 | 0x1e400000 | | 578 | blk.9.ffn_gate_up_exps.weight | 0xb19a89880 | 0x3c800000 | | 579 | blk.9.attn_norm.weight | 0xb56289880 | 0x2c00 | | 580 | blk.9.layer_output_scale.weight | 0xb5628c480 | 0x4 | | 581 | blk.9.ffn_down.weight | 0xb5628c4a0 | 0xb58000 | | 582 | blk.9.ffn_gate.weight | 0xb56de44a0 | 0xb58000 | | 583 | blk.9.ffn_up.weight | 0xb5793c4a0 | 0xb58000 | | 584 | blk.9.post_attention_norm.weight | 0xb584944a0 | 0x2c00 | | 585 | blk.9.post_ffw_norm.weight | 0xb584970a0 | 0x2c00 | | 586 | blk.9.post_ffw_norm_1.weight | 0xb58499ca0 | 0x2c00 | | 587 | blk.9.post_ffw_norm_2.weight | 0xb5849c8a0 | 0x2c00 | | 588 | blk.9.ffn_norm.weight | 0xb5849f4a0 | 0x2c00 | | 589 | blk.9.pre_ffw_norm_2.weight | 0xb584a20a0 | 0x2c00 | | 590 | blk.9.ffn_down_exps.scale | 0xb584a4ca0 | 0x200 | | 591 | blk.9.ffn_gate_inp.weight | 0xb584a4ea0 | 0x160000 | | 592 | blk.9.ffn_gate_inp.scale | 0xb58604ea0 | 0x2c00 | | 593 | blk.9.attn_k_norm.weight | 0xb58607aa0 | 0x400 | | 594 | blk.9.attn_k.weight | 0xb58607ea0 | 0xb00000 | | 595 | blk.9.attn_output.weight | 0xb59107ea0 | 0x1600000 | | 596 | blk.9.attn_q_norm.weight | 0xb5a707ea0 | 0x400 | | 597 | blk.9.attn_q.weight | 0xb5a7082a0 | 0x1600000 | | 598 | blk.9.attn_v.weight | 0xb5bd082a0 | 0xb00000 | | 599 | output_norm.weight | 0xb5c8082a0 | 0x2c00 | | 600 | blk.11.attn_norm.weight | 0xb5c80aea0 | 0x2c00 | | 601 | blk.11.ffn_down.weight | 0xb5c80daa0 | 0xb58000 | | 602 | blk.11.ffn_gate.weight | 0xb5d365aa0 | 0xb58000 | | 603 | blk.11.ffn_up.weight | 0xb5debdaa0 | 0xb58000 | | 604 | blk.11.post_attention_norm.weight | 0xb5ea15aa0 | 0x2c00 | | 605 | blk.11.post_ffw_norm.weight | 0xb5ea186a0 | 0x2c00 | | 606 | blk.11.post_ffw_norm_1.weight | 0xb5ea1b2a0 | 0x2c00 | | 607 | blk.11.post_ffw_norm_2.weight | 0xb5ea1dea0 | 0x2c00 | | 608 | blk.11.ffn_norm.weight | 0xb5ea20aa0 | 0x2c00 | | 609 | blk.11.pre_ffw_norm_2.weight | 0xb5ea236a0 | 0x2c00 | | 610 | blk.11.ffn_gate_inp.weight | 0xb5ea262a0 | 0x160000 | | 611 | blk.17.ffn_down_exps.weight | 0xb5eb862a0 | 0x1e400000 | | 612 | blk.17.attn_norm.weight | 0xb7cf862a0 | 0x2c00 | | 613 | blk.17.ffn_down.weight | 0xb7cf88ea0 | 0xb58000 | | 614 | blk.17.ffn_gate.weight | 0xb7dae0ea0 | 0xb58000 | | 615 | blk.17.ffn_up.weight | 0xb7e638ea0 | 0xb58000 | | 616 | blk.17.post_attention_norm.weight | 0xb7f190ea0 | 0x2c00 | | 617 | blk.17.post_ffw_norm.weight | 0xb7f193aa0 | 0x2c00 | | 618 | blk.17.post_ffw_norm_1.weight | 0xb7f1966a0 | 0x2c00 | | 619 | blk.17.post_ffw_norm_2.weight | 0xb7f1992a0 | 0x2c00 | | 620 | blk.17.ffn_norm.weight | 0xb7f19bea0 | 0x2c00 | | 621 | blk.17.pre_ffw_norm_2.weight | 0xb7f19eaa0 | 0x2c00 | | 622 | blk.17.ffn_gate_inp.weight | 0xb7f1a16a0 | 0x160000 | | 623 | blk.23.ffn_down_exps.weight | 0xb7f3016a0 | 0x1e400000 | | 624 | blk.23.attn_norm.weight | 0xb9d7016a0 | 0x2c00 | | 625 | blk.23.ffn_down.weight | 0xb9d7042a0 | 0xb58000 | | 626 | blk.23.ffn_gate.weight | 0xb9e25c2a0 | 0xb58000 | | 627 | blk.23.ffn_up.weight | 0xb9edb42a0 | 0xb58000 | | 628 | blk.23.post_attention_norm.weight | 0xb9f90c2a0 | 0x2c00 | | 629 | blk.23.post_ffw_norm.weight | 0xb9f90eea0 | 0x2c00 | | 630 | blk.23.post_ffw_norm_1.weight | 0xb9f911aa0 | 0x2c00 | | 631 | blk.23.post_ffw_norm_2.weight | 0xb9f9146a0 | 0x2c00 | | 632 | blk.23.ffn_norm.weight | 0xb9f9172a0 | 0x2c00 | | 633 | blk.23.pre_ffw_norm_2.weight | 0xb9f919ea0 | 0x2c00 | | 634 | blk.23.ffn_gate_inp.weight | 0xb9f91caa0 | 0x160000 | | 635 | blk.29.ffn_down_exps.weight | 0xb9fa7caa0 | 0x1e400000 | | 636 | blk.29.attn_norm.weight | 0xbbde7caa0 | 0x2c00 | | 637 | blk.29.ffn_down.weight | 0xbbde7f6a0 | 0xb58000 | | 638 | blk.29.ffn_gate.weight | 0xbbe9d76a0 | 0xb58000 | | 639 | blk.29.ffn_up.weight | 0xbbf52f6a0 | 0xb58000 | | 640 | blk.29.post_attention_norm.weight | 0xbc00876a0 | 0x2c00 | | 641 | blk.29.post_ffw_norm.weight | 0xbc008a2a0 | 0x2c00 | | 642 | blk.29.post_ffw_norm_1.weight | 0xbc008cea0 | 0x2c00 | | 643 | blk.29.post_ffw_norm_2.weight | 0xbc008faa0 | 0x2c00 | | 644 | blk.29.ffn_norm.weight | 0xbc00926a0 | 0x2c00 | | 645 | blk.29.pre_ffw_norm_2.weight | 0xbc00952a0 | 0x2c00 | | 646 | blk.29.ffn_gate_inp.weight | 0xbc0097ea0 | 0x160000 | | 647 | blk.5.attn_norm.weight | 0xbc01f7ea0 | 0x2c00 | | 648 | blk.5.ffn_down.weight | 0xbc01faaa0 | 0xb58000 | | 649 | blk.5.ffn_gate.weight | 0xbc0d52aa0 | 0xb58000 | | 650 | blk.5.ffn_up.weight | 0xbc18aaaa0 | 0xb58000 | | 651 | blk.5.post_attention_norm.weight | 0xbc2402aa0 | 0x2c00 | | 652 | blk.5.post_ffw_norm.weight | 0xbc24056a0 | 0x2c00 | | 653 | blk.5.post_ffw_norm_1.weight | 0xbc24082a0 | 0x2c00 | | 654 | blk.5.post_ffw_norm_2.weight | 0xbc240aea0 | 0x2c00 | | 655 | blk.5.ffn_norm.weight | 0xbc240daa0 | 0x2c00 | | 656 | blk.5.pre_ffw_norm_2.weight | 0xbc24106a0 | 0x2c00 | | 657 | blk.5.ffn_gate_inp.weight | 0xbc24132a0 | 0x160000 | ### Base Tensor Group : ~738M Elements | T_ID | Tensor Layer Name | Human Friendly Tensor Layer Name | Elements | Shape | Type | BPW | | ---: | :----------------- | :------------------------------- | :---------------- | :-------------------- | :--- | ------: | | 0 | rope_freqs.weight | Rope_Freqs (W) | ( 256) 256 | 256 x 1 x 1 x 1 | F32 | 32.0000 | | 1 | token_embd.weight | Token Embedding (W) | (~738M) 738197504 | 2816 x 262144 x 1 x 1 | F16 | 16.0000 | | 599 | output_norm.weight | Output Normalization (W) | ( ~3K) 2816 | 2816 x 1 x 1 x 1 | F32 | 32.0000 | - Total elements in base: (~738M) 738200576 - Percentage of total elements: 2.93% - Bits per Weight (BPW) for base: 16.0001 bits ### Block 0 Tensor Group : ~814M Elements | T_ID | Tensor Layer Name | Human Friendly Tensor Layer Name | Elements | Shape | Type | BPW | | ---: | :------------------------------- | :------------------------------------------------------------------------------------------ | :---------------- | :-------------------- | :--- | ------: | | 2 | blk.0.ffn_down_exps.weight | Block 0 Ffn_Down_Exps (W) | (~254M) 253755392 | 704 x 2816 x 128 x 1 | F16 | 16.0000 | | 3 | blk.0.ffn_gate_up_exps.weight | Block 0 Ffn_Gate_Up_Exps (W) | (~508M) 507510784 | 2816 x 1408 x 128 x 1 | F16 | 16.0000 | | 4 | blk.0.attn_norm.weight | Block 0 Attention Normalization (W) | ( ~3K) 2816 | 2816 x 1 x 1 x 1 | F32 | 32.0000 | | 5 | blk.0.layer_output_scale.weight | Block 0 Layer_Output_Scale (W) | ( 1) 1 | 1 x 1 x 1 x 1 | F32 | 32.0000 | | 6 | blk.0.ffn_down.weight | Block 0 Feed-Forward Network "Down" (W) | ( ~6M) 5947392 | 2112 x 2816 x 1 x 1 | F16 | 16.0000 | | 7 | blk.0.ffn_gate.weight | Block 0 Feed-Forward Network "Gate" (W) | ( ~6M) 5947392 | 2816 x 2112 x 1 x 1 | F16 | 16.0000 | | 8 | blk.0.ffn_up.weight | Block 0 Feed-Forward Network "Up" (W) | ( ~6M) 5947392 | 2816 x 2112 x 1 x 1 | F16 | 16.0000 | | 9 | blk.0.post_attention_norm.weight | Block 0 Post_Attention_Norm (W) | ( ~3K) 2816 | 2816 x 1 x 1 x 1 | F32 | 32.0000 | | 10 | blk.0.post_ffw_norm.weight | Block 0 Post_Ffw_Norm (W) | ( ~3K) 2816 | 2816 x 1 x 1 x 1 | F32 | 32.0000 | | 11 | blk.0.post_ffw_norm_1.weight | Block 0 Post_Ffw_Norm_1 (W) | ( ~3K) 2816 | 2816 x 1 x 1 x 1 | F32 | 32.0000 | | 12 | blk.0.post_ffw_norm_2.weight | Block 0 Post_Ffw_Norm_2 (W) | ( ~3K) 2816 | 2816 x 1 x 1 x 1 | F32 | 32.0000 | | 13 | blk.0.ffn_norm.weight | Block 0 Feed-Forward Network Normalization (W) | ( ~3K) 2816 | 2816 x 1 x 1 x 1 | F32 | 32.0000 | | 14 | blk.0.pre_ffw_norm_2.weight | Block 0 Pre_Ffw_Norm_2 (W) | ( ~3K) 2816 | 2816 x 1 x 1 x 1 | F32 | 32.0000 | | 15 | blk.0.ffn_down_exps.scale | Block 0 Ffn_Down_Exps Scale | ( 128) 128 | 128 x 1 x 1 x 1 | F32 | 32.0000 | | 16 | blk.0.ffn_gate_inp.weight | Block 0 Expert-Routing Layer For The Feed-Forward Network In Mixture Of Expert Models (W) | (~360K) 360448 | 2816 x 128 x 1 x 1 | F32 | 32.0000 | | 17 | blk.0.ffn_gate_inp.scale | Block 0 Expert-Routing Layer For The Feed-Forward Network In Mixture Of Expert Models Scale | ( ~3K) 2816 | 2816 x 1 x 1 x 1 | F32 | 32.0000 | | 18 | blk.0.attn_k_norm.weight | Block 0 Attn_K_Norm (W) | ( 256) 256 | 256 x 1 x 1 x 1 | F32 | 32.0000 | | 19 | blk.0.attn_k.weight | Block 0 Attention Key (W) | ( ~6M) 5767168 | 2816 x 2048 x 1 x 1 | F16 | 16.0000 | | 20 | blk.0.attn_output.weight | Block 0 Attention Output (W) | ( ~12M) 11534336 | 4096 x 2816 x 1 x 1 | F16 | 16.0000 | | 21 | blk.0.attn_q_norm.weight | Block 0 Attn_Q_Norm (W) | ( 256) 256 | 256 x 1 x 1 x 1 | F32 | 32.0000 | | 22 | blk.0.attn_q.weight | Block 0 Attention Query (W) | ( ~12M) 11534336 | 2816 x 4096 x 1 x 1 | F16 | 16.0000 | | 23 | blk.0.attn_v.weight | Block 0 Attention Value (W) | ( ~6M) 5767168 | 2816 x 2048 x 1 x 1 | F16 | 16.0000 | - Total elements in blk.0: (~814M) 814094977 - Percentage of total elements: 3.23% - Bits per Weight (BPW) for blk.0: 16.0075 bits ### Block 1 Tensor Group : ~814M Elements | T_ID | Tensor Layer Name | Human Friendly Tensor Layer Name | Elements | Shape | Type | BPW | | ---: | :------------------------------- | :------------------------------------------------------------------------------------------ | :---------------- | :-------------------- | :--- | ------: | | 24 | blk.1.ffn_down_exps.weight | Block 1 Ffn_Down_Exps (W) | (~254M) 253755392 | 704 x 2816 x 128 x 1 | F16 | 16.0000 | | 25 | blk.1.ffn_gate_up_exps.weight | Block 1 Ffn_Gate_Up_Exps (W) | (~508M) 507510784 | 2816 x 1408 x 128 x 1 | F16 | 16.0000 | | 26 | blk.1.attn_norm.weight | Block 1 Attention Normalization (W) | ( ~3K) 2816 | 2816 x 1 x 1 x 1 | F32 | 32.0000 | | 27 | blk.1.layer_output_scale.weight | Block 1 Layer_Output_Scale (W) | ( 1) 1 | 1 x 1 x 1 x 1 | F32 | 32.0000 | | 28 | blk.1.ffn_down.weight | Block 1 Feed-Forward Network "Down" (W) | ( ~6M) 5947392 | 2112 x 2816 x 1 x 1 | F16 | 16.0000 | | 29 | blk.1.ffn_gate.weight | Block 1 Feed-Forward Network "Gate" (W) | ( ~6M) 5947392 | 2816 x 2112 x 1 x 1 | F16 | 16.0000 | | 30 | blk.1.ffn_up.weight | Block 1 Feed-Forward Network "Up" (W) | ( ~6M) 5947392 | 2816 x 2112 x 1 x 1 | F16 | 16.0000 | | 31 | blk.1.post_attention_norm.weight | Block 1 Post_Attention_Norm (W) | ( ~3K) 2816 | 2816 x 1 x 1 x 1 | F32 | 32.0000 | | 32 | blk.1.post_ffw_norm.weight | Block 1 Post_Ffw_Norm (W) | ( ~3K) 2816 | 2816 x 1 x 1 x 1 | F32 | 32.0000 | | 33 | blk.1.post_ffw_norm_1.weight | Block 1 Post_Ffw_Norm_1 (W) | ( ~3K) 2816 | 2816 x 1 x 1 x 1 | F32 | 32.0000 | | 34 | blk.1.post_ffw_norm_2.weight | Block 1 Post_Ffw_Norm_2 (W) | ( ~3K) 2816 | 2816 x 1 x 1 x 1 | F32 | 32.0000 | | 35 | blk.1.ffn_norm.weight | Block 1 Feed-Forward Network Normalization (W) | ( ~3K) 2816 | 2816 x 1 x 1 x 1 | F32 | 32.0000 | | 36 | blk.1.pre_ffw_norm_2.weight | Block 1 Pre_Ffw_Norm_2 (W) | ( ~3K) 2816 | 2816 x 1 x 1 x 1 | F32 | 32.0000 | | 37 | blk.1.ffn_down_exps.scale | Block 1 Ffn_Down_Exps Scale | ( 128) 128 | 128 x 1 x 1 x 1 | F32 | 32.0000 | | 38 | blk.1.ffn_gate_inp.weight | Block 1 Expert-Routing Layer For The Feed-Forward Network In Mixture Of Expert Models (W) | (~360K) 360448 | 2816 x 128 x 1 x 1 | F32 | 32.0000 | | 39 | blk.1.ffn_gate_inp.scale | Block 1 Expert-Routing Layer For The Feed-Forward Network In Mixture Of Expert Models Scale | ( ~3K) 2816 | 2816 x 1 x 1 x 1 | F32 | 32.0000 | | 40 | blk.1.attn_k_norm.weight | Block 1 Attn_K_Norm (W) | ( 256) 256 | 256 x 1 x 1 x 1 | F32 | 32.0000 | | 41 | blk.1.attn_k.weight | Block 1 Attention Key (W) | ( ~6M) 5767168 | 2816 x 2048 x 1 x 1 | F16 | 16.0000 | | 42 | blk.1.attn_output.weight | Block 1 Attention Output (W) | ( ~12M) 11534336 | 4096 x 2816 x 1 x 1 | F16 | 16.0000 | | 43 | blk.1.attn_q_norm.weight | Block 1 Attn_Q_Norm (W) | ( 256) 256 | 256 x 1 x 1 x 1 | F32 | 32.0000 | | 44 | blk.1.attn_q.weight | Block 1 Attention Query (W) | ( ~12M) 11534336 | 2816 x 4096 x 1 x 1 | F16 | 16.0000 | | 45 | blk.1.attn_v.weight | Block 1 Attention Value (W) | ( ~6M) 5767168 | 2816 x 2048 x 1 x 1 | F16 | 16.0000 | - Total elements in blk.1: (~814M) 814094977 - Percentage of total elements: 3.23% - Bits per Weight (BPW) for blk.1: 16.0075 bits ### Block 10 Tensor Group : ~814M Elements | T_ID | Tensor Layer Name | Human Friendly Tensor Layer Name | Elements | Shape | Type | BPW | | ---: | :-------------------------------- | :------------------------------------------------------------------------------------------- | :---------------- | :-------------------- | :--- | ------: | | 46 | blk.10.ffn_down_exps.weight | Block 10 Ffn_Down_Exps (W) | (~254M) 253755392 | 704 x 2816 x 128 x 1 | F16 | 16.0000 | | 47 | blk.10.ffn_gate_up_exps.weight | Block 10 Ffn_Gate_Up_Exps (W) | (~508M) 507510784 | 2816 x 1408 x 128 x 1 | F16 | 16.0000 | | 48 | blk.10.attn_norm.weight | Block 10 Attention Normalization (W) | ( ~3K) 2816 | 2816 x 1 x 1 x 1 | F32 | 32.0000 | | 49 | blk.10.layer_output_scale.weight | Block 10 Layer_Output_Scale (W) | ( 1) 1 | 1 x 1 x 1 x 1 | F32 | 32.0000 | | 50 | blk.10.ffn_down.weight | Block 10 Feed-Forward Network "Down" (W) | ( ~6M) 5947392 | 2112 x 2816 x 1 x 1 | F16 | 16.0000 | | 51 | blk.10.ffn_gate.weight | Block 10 Feed-Forward Network "Gate" (W) | ( ~6M) 5947392 | 2816 x 2112 x 1 x 1 | F16 | 16.0000 | | 52 | blk.10.ffn_up.weight | Block 10 Feed-Forward Network "Up" (W) | ( ~6M) 5947392 | 2816 x 2112 x 1 x 1 | F16 | 16.0000 | | 53 | blk.10.post_attention_norm.weight | Block 10 Post_Attention_Norm (W) | ( ~3K) 2816 | 2816 x 1 x 1 x 1 | F32 | 32.0000 | | 54 | blk.10.post_ffw_norm.weight | Block 10 Post_Ffw_Norm (W) | ( ~3K) 2816 | 2816 x 1 x 1 x 1 | F32 | 32.0000 | | 55 | blk.10.post_ffw_norm_1.weight | Block 10 Post_Ffw_Norm_1 (W) | ( ~3K) 2816 | 2816 x 1 x 1 x 1 | F32 | 32.0000 | | 56 | blk.10.post_ffw_norm_2.weight | Block 10 Post_Ffw_Norm_2 (W) | ( ~3K) 2816 | 2816 x 1 x 1 x 1 | F32 | 32.0000 | | 57 | blk.10.ffn_norm.weight | Block 10 Feed-Forward Network Normalization (W) | ( ~3K) 2816 | 2816 x 1 x 1 x 1 | F32 | 32.0000 | | 58 | blk.10.pre_ffw_norm_2.weight | Block 10 Pre_Ffw_Norm_2 (W) | ( ~3K) 2816 | 2816 x 1 x 1 x 1 | F32 | 32.0000 | | 59 | blk.10.ffn_down_exps.scale | Block 10 Ffn_Down_Exps Scale | ( 128) 128 | 128 x 1 x 1 x 1 | F32 | 32.0000 | | 60 | blk.10.ffn_gate_inp.weight | Block 10 Expert-Routing Layer For The Feed-Forward Network In Mixture Of Expert Models (W) | (~360K) 360448 | 2816 x 128 x 1 x 1 | F32 | 32.0000 | | 61 | blk.10.ffn_gate_inp.scale | Block 10 Expert-Routing Layer For The Feed-Forward Network In Mixture Of Expert Models Scale | ( ~3K) 2816 | 2816 x 1 x 1 x 1 | F32 | 32.0000 | | 62 | blk.10.attn_k_norm.weight | Block 10 Attn_K_Norm (W) | ( 256) 256 | 256 x 1 x 1 x 1 | F32 | 32.0000 | | 63 | blk.10.attn_k.weight | Block 10 Attention Key (W) | ( ~6M) 5767168 | 2816 x 2048 x 1 x 1 | F16 | 16.0000 | | 64 | blk.10.attn_output.weight | Block 10 Attention Output (W) | ( ~12M) 11534336 | 4096 x 2816 x 1 x 1 | F16 | 16.0000 | | 65 | blk.10.attn_q_norm.weight | Block 10 Attn_Q_Norm (W) | ( 256) 256 | 256 x 1 x 1 x 1 | F32 | 32.0000 | | 66 | blk.10.attn_q.weight | Block 10 Attention Query (W) | ( ~12M) 11534336 | 2816 x 4096 x 1 x 1 | F16 | 16.0000 | | 67 | blk.10.attn_v.weight | Block 10 Attention Value (W) | ( ~6M) 5767168 | 2816 x 2048 x 1 x 1 | F16 | 16.0000 | - Total elements in blk.10: (~814M) 814094977 - Percentage of total elements: 3.23% - Bits per Weight (BPW) for blk.10: 16.0075 bits ### Block 11 Tensor Group : ~829M Elements | T_ID | Tensor Layer Name | Human Friendly Tensor Layer Name | Elements | Shape | Type | BPW | | ---: | :-------------------------------- | :------------------------------------------------------------------------------------------- | :---------------- | :-------------------- | :--- | ------: | | 68 | blk.11.ffn_down_exps.weight | Block 11 Ffn_Down_Exps (W) | (~254M) 253755392 | 704 x 2816 x 128 x 1 | F16 | 16.0000 | | 69 | blk.11.ffn_gate_up_exps.weight | Block 11 Ffn_Gate_Up_Exps (W) | (~508M) 507510784 | 2816 x 1408 x 128 x 1 | F16 | 16.0000 | | 70 | blk.11.layer_output_scale.weight | Block 11 Layer_Output_Scale (W) | ( 1) 1 | 1 x 1 x 1 x 1 | F32 | 32.0000 | | 71 | blk.11.ffn_down_exps.scale | Block 11 Ffn_Down_Exps Scale | ( 128) 128 | 128 x 1 x 1 x 1 | F32 | 32.0000 | | 72 | blk.11.ffn_gate_inp.scale | Block 11 Expert-Routing Layer For The Feed-Forward Network In Mixture Of Expert Models Scale | ( ~3K) 2816 | 2816 x 1 x 1 x 1 | F32 | 32.0000 | | 73 | blk.11.attn_k_norm.weight | Block 11 Attn_K_Norm (W) | ( 512) 512 | 512 x 1 x 1 x 1 | F32 | 32.0000 | | 74 | blk.11.attn_k.weight | Block 11 Attention Key (W) | ( ~3M) 2883584 | 2816 x 1024 x 1 x 1 | F16 | 16.0000 | | 75 | blk.11.attn_output.weight | Block 11 Attention Output (W) | ( ~23M) 23068672 | 8192 x 2816 x 1 x 1 | F16 | 16.0000 | | 76 | blk.11.attn_q_norm.weight | Block 11 Attn_Q_Norm (W) | ( 512) 512 | 512 x 1 x 1 x 1 | F32 | 32.0000 | | 77 | blk.11.attn_q.weight | Block 11 Attention Query (W) | ( ~23M) 23068672 | 2816 x 8192 x 1 x 1 | F16 | 16.0000 | | 600 | blk.11.attn_norm.weight | Block 11 Attention Normalization (W) | ( ~3K) 2816 | 2816 x 1 x 1 x 1 | F32 | 32.0000 | | 601 | blk.11.ffn_down.weight | Block 11 Feed-Forward Network "Down" (W) | ( ~6M) 5947392 | 2112 x 2816 x 1 x 1 | F16 | 16.0000 | | 602 | blk.11.ffn_gate.weight | Block 11 Feed-Forward Network "Gate" (W) | ( ~6M) 5947392 | 2816 x 2112 x 1 x 1 | F16 | 16.0000 | | 603 | blk.11.ffn_up.weight | Block 11 Feed-Forward Network "Up" (W) | ( ~6M) 5947392 | 2816 x 2112 x 1 x 1 | F16 | 16.0000 | | 604 | blk.11.post_attention_norm.weight | Block 11 Post_Attention_Norm (W) | ( ~3K) 2816 | 2816 x 1 x 1 x 1 | F32 | 32.0000 | | 605 | blk.11.post_ffw_norm.weight | Block 11 Post_Ffw_Norm (W) | ( ~3K) 2816 | 2816 x 1 x 1 x 1 | F32 | 32.0000 | | 606 | blk.11.post_ffw_norm_1.weight | Block 11 Post_Ffw_Norm_1 (W) | ( ~3K) 2816 | 2816 x 1 x 1 x 1 | F32 | 32.0000 | | 607 | blk.11.post_ffw_norm_2.weight | Block 11 Post_Ffw_Norm_2 (W) | ( ~3K) 2816 | 2816 x 1 x 1 x 1 | F32 | 32.0000 | | 608 | blk.11.ffn_norm.weight | Block 11 Feed-Forward Network Normalization (W) | ( ~3K) 2816 | 2816 x 1 x 1 x 1 | F32 | 32.0000 | | 609 | blk.11.pre_ffw_norm_2.weight | Block 11 Pre_Ffw_Norm_2 (W) | ( ~3K) 2816 | 2816 x 1 x 1 x 1 | F32 | 32.0000 | | 610 | blk.11.ffn_gate_inp.weight | Block 11 Expert-Routing Layer For The Feed-Forward Network In Mixture Of Expert Models (W) | (~360K) 360448 | 2816 x 128 x 1 x 1 | F32 | 32.0000 | - Total elements in blk.11: (~829M) 828513409 - Percentage of total elements: 3.28% - Bits per Weight (BPW) for blk.11: 16.0074 bits ### Block 12 Tensor Group : ~814M Elements | T_ID | Tensor Layer Name | Human Friendly Tensor Layer Name | Elements | Shape | Type | BPW | | ---: | :-------------------------------- | :------------------------------------------------------------------------------------------- | :---------------- | :-------------------- | :--- | ------: | | 78 | blk.12.ffn_down_exps.weight | Block 12 Ffn_Down_Exps (W) | (~254M) 253755392 | 704 x 2816 x 128 x 1 | F16 | 16.0000 | | 79 | blk.12.ffn_gate_up_exps.weight | Block 12 Ffn_Gate_Up_Exps (W) | (~508M) 507510784 | 2816 x 1408 x 128 x 1 | F16 | 16.0000 | | 80 | blk.12.attn_norm.weight | Block 12 Attention Normalization (W) | ( ~3K) 2816 | 2816 x 1 x 1 x 1 | F32 | 32.0000 | | 81 | blk.12.layer_output_scale.weight | Block 12 Layer_Output_Scale (W) | ( 1) 1 | 1 x 1 x 1 x 1 | F32 | 32.0000 | | 82 | blk.12.ffn_down.weight | Block 12 Feed-Forward Network "Down" (W) | ( ~6M) 5947392 | 2112 x 2816 x 1 x 1 | F16 | 16.0000 | | 83 | blk.12.ffn_gate.weight | Block 12 Feed-Forward Network "Gate" (W) | ( ~6M) 5947392 | 2816 x 2112 x 1 x 1 | F16 | 16.0000 | | 84 | blk.12.ffn_up.weight | Block 12 Feed-Forward Network "Up" (W) | ( ~6M) 5947392 | 2816 x 2112 x 1 x 1 | F16 | 16.0000 | | 85 | blk.12.post_attention_norm.weight | Block 12 Post_Attention_Norm (W) | ( ~3K) 2816 | 2816 x 1 x 1 x 1 | F32 | 32.0000 | | 86 | blk.12.post_ffw_norm.weight | Block 12 Post_Ffw_Norm (W) | ( ~3K) 2816 | 2816 x 1 x 1 x 1 | F32 | 32.0000 | | 87 | blk.12.post_ffw_norm_1.weight | Block 12 Post_Ffw_Norm_1 (W) | ( ~3K) 2816 | 2816 x 1 x 1 x 1 | F32 | 32.0000 | | 88 | blk.12.post_ffw_norm_2.weight | Block 12 Post_Ffw_Norm_2 (W) | ( ~3K) 2816 | 2816 x 1 x 1 x 1 | F32 | 32.0000 | | 89 | blk.12.ffn_norm.weight | Block 12 Feed-Forward Network Normalization (W) | ( ~3K) 2816 | 2816 x 1 x 1 x 1 | F32 | 32.0000 | | 90 | blk.12.pre_ffw_norm_2.weight | Block 12 Pre_Ffw_Norm_2 (W) | ( ~3K) 2816 | 2816 x 1 x 1 x 1 | F32 | 32.0000 | | 91 | blk.12.ffn_down_exps.scale | Block 12 Ffn_Down_Exps Scale | ( 128) 128 | 128 x 1 x 1 x 1 | F32 | 32.0000 | | 92 | blk.12.ffn_gate_inp.weight | Block 12 Expert-Routing Layer For The Feed-Forward Network In Mixture Of Expert Models (W) | (~360K) 360448 | 2816 x 128 x 1 x 1 | F32 | 32.0000 | | 93 | blk.12.ffn_gate_inp.scale | Block 12 Expert-Routing Layer For The Feed-Forward Network In Mixture Of Expert Models Scale | ( ~3K) 2816 | 2816 x 1 x 1 x 1 | F32 | 32.0000 | | 94 | blk.12.attn_k_norm.weight | Block 12 Attn_K_Norm (W) | ( 256) 256 | 256 x 1 x 1 x 1 | F32 | 32.0000 | | 95 | blk.12.attn_k.weight | Block 12 Attention Key (W) | ( ~6M) 5767168 | 2816 x 2048 x 1 x 1 | F16 | 16.0000 | | 96 | blk.12.attn_output.weight | Block 12 Attention Output (W) | ( ~12M) 11534336 | 4096 x 2816 x 1 x 1 | F16 | 16.0000 | | 97 | blk.12.attn_q_norm.weight | Block 12 Attn_Q_Norm (W) | ( 256) 256 | 256 x 1 x 1 x 1 | F32 | 32.0000 | | 98 | blk.12.attn_q.weight | Block 12 Attention Query (W) | ( ~12M) 11534336 | 2816 x 4096 x 1 x 1 | F16 | 16.0000 | | 99 | blk.12.attn_v.weight | Block 12 Attention Value (W) | ( ~6M) 5767168 | 2816 x 2048 x 1 x 1 | F16 | 16.0000 | - Total elements in blk.12: (~814M) 814094977 - Percentage of total elements: 3.23% - Bits per Weight (BPW) for blk.12: 16.0075 bits ### Block 13 Tensor Group : ~814M Elements | T_ID | Tensor Layer Name | Human Friendly Tensor Layer Name | Elements | Shape | Type | BPW | | ---: | :-------------------------------- | :------------------------------------------------------------------------------------------- | :---------------- | :-------------------- | :--- | ------: | | 100 | blk.13.ffn_down_exps.weight | Block 13 Ffn_Down_Exps (W) | (~254M) 253755392 | 704 x 2816 x 128 x 1 | F16 | 16.0000 | | 101 | blk.13.ffn_gate_up_exps.weight | Block 13 Ffn_Gate_Up_Exps (W) | (~508M) 507510784 | 2816 x 1408 x 128 x 1 | F16 | 16.0000 | | 102 | blk.13.attn_norm.weight | Block 13 Attention Normalization (W) | ( ~3K) 2816 | 2816 x 1 x 1 x 1 | F32 | 32.0000 | | 103 | blk.13.layer_output_scale.weight | Block 13 Layer_Output_Scale (W) | ( 1) 1 | 1 x 1 x 1 x 1 | F32 | 32.0000 | | 104 | blk.13.ffn_down.weight | Block 13 Feed-Forward Network "Down" (W) | ( ~6M) 5947392 | 2112 x 2816 x 1 x 1 | F16 | 16.0000 | | 105 | blk.13.ffn_gate.weight | Block 13 Feed-Forward Network "Gate" (W) | ( ~6M) 5947392 | 2816 x 2112 x 1 x 1 | F16 | 16.0000 | | 106 | blk.13.ffn_up.weight | Block 13 Feed-Forward Network "Up" (W) | ( ~6M) 5947392 | 2816 x 2112 x 1 x 1 | F16 | 16.0000 | | 107 | blk.13.post_attention_norm.weight | Block 13 Post_Attention_Norm (W) | ( ~3K) 2816 | 2816 x 1 x 1 x 1 | F32 | 32.0000 | | 108 | blk.13.post_ffw_norm.weight | Block 13 Post_Ffw_Norm (W) | ( ~3K) 2816 | 2816 x 1 x 1 x 1 | F32 | 32.0000 | | 109 | blk.13.post_ffw_norm_1.weight | Block 13 Post_Ffw_Norm_1 (W) | ( ~3K) 2816 | 2816 x 1 x 1 x 1 | F32 | 32.0000 | | 110 | blk.13.post_ffw_norm_2.weight | Block 13 Post_Ffw_Norm_2 (W) | ( ~3K) 2816 | 2816 x 1 x 1 x 1 | F32 | 32.0000 | | 111 | blk.13.ffn_norm.weight | Block 13 Feed-Forward Network Normalization (W) | ( ~3K) 2816 | 2816 x 1 x 1 x 1 | F32 | 32.0000 | | 112 | blk.13.pre_ffw_norm_2.weight | Block 13 Pre_Ffw_Norm_2 (W) | ( ~3K) 2816 | 2816 x 1 x 1 x 1 | F32 | 32.0000 | | 113 | blk.13.ffn_down_exps.scale | Block 13 Ffn_Down_Exps Scale | ( 128) 128 | 128 x 1 x 1 x 1 | F32 | 32.0000 | | 114 | blk.13.ffn_gate_inp.weight | Block 13 Expert-Routing Layer For The Feed-Forward Network In Mixture Of Expert Models (W) | (~360K) 360448 | 2816 x 128 x 1 x 1 | F32 | 32.0000 | | 115 | blk.13.ffn_gate_inp.scale | Block 13 Expert-Routing Layer For The Feed-Forward Network In Mixture Of Expert Models Scale | ( ~3K) 2816 | 2816 x 1 x 1 x 1 | F32 | 32.0000 | | 116 | blk.13.attn_k_norm.weight | Block 13 Attn_K_Norm (W) | ( 256) 256 | 256 x 1 x 1 x 1 | F32 | 32.0000 | | 117 | blk.13.attn_k.weight | Block 13 Attention Key (W) | ( ~6M) 5767168 | 2816 x 2048 x 1 x 1 | F16 | 16.0000 | | 118 | blk.13.attn_output.weight | Block 13 Attention Output (W) | ( ~12M) 11534336 | 4096 x 2816 x 1 x 1 | F16 | 16.0000 | | 119 | blk.13.attn_q_norm.weight | Block 13 Attn_Q_Norm (W) | ( 256) 256 | 256 x 1 x 1 x 1 | F32 | 32.0000 | | 120 | blk.13.attn_q.weight | Block 13 Attention Query (W) | ( ~12M) 11534336 | 2816 x 4096 x 1 x 1 | F16 | 16.0000 | | 121 | blk.13.attn_v.weight | Block 13 Attention Value (W) | ( ~6M) 5767168 | 2816 x 2048 x 1 x 1 | F16 | 16.0000 | - Total elements in blk.13: (~814M) 814094977 - Percentage of total elements: 3.23% - Bits per Weight (BPW) for blk.13: 16.0075 bits ### Block 14 Tensor Group : ~814M Elements | T_ID | Tensor Layer Name | Human Friendly Tensor Layer Name | Elements | Shape | Type | BPW | | ---: | :-------------------------------- | :------------------------------------------------------------------------------------------- | :---------------- | :-------------------- | :--- | ------: | | 122 | blk.14.ffn_down_exps.weight | Block 14 Ffn_Down_Exps (W) | (~254M) 253755392 | 704 x 2816 x 128 x 1 | F16 | 16.0000 | | 123 | blk.14.ffn_gate_up_exps.weight | Block 14 Ffn_Gate_Up_Exps (W) | (~508M) 507510784 | 2816 x 1408 x 128 x 1 | F16 | 16.0000 | | 124 | blk.14.attn_norm.weight | Block 14 Attention Normalization (W) | ( ~3K) 2816 | 2816 x 1 x 1 x 1 | F32 | 32.0000 | | 125 | blk.14.layer_output_scale.weight | Block 14 Layer_Output_Scale (W) | ( 1) 1 | 1 x 1 x 1 x 1 | F32 | 32.0000 | | 126 | blk.14.ffn_down.weight | Block 14 Feed-Forward Network "Down" (W) | ( ~6M) 5947392 | 2112 x 2816 x 1 x 1 | F16 | 16.0000 | | 127 | blk.14.ffn_gate.weight | Block 14 Feed-Forward Network "Gate" (W) | ( ~6M) 5947392 | 2816 x 2112 x 1 x 1 | F16 | 16.0000 | | 128 | blk.14.ffn_up.weight | Block 14 Feed-Forward Network "Up" (W) | ( ~6M) 5947392 | 2816 x 2112 x 1 x 1 | F16 | 16.0000 | | 129 | blk.14.post_attention_norm.weight | Block 14 Post_Attention_Norm (W) | ( ~3K) 2816 | 2816 x 1 x 1 x 1 | F32 | 32.0000 | | 130 | blk.14.post_ffw_norm.weight | Block 14 Post_Ffw_Norm (W) | ( ~3K) 2816 | 2816 x 1 x 1 x 1 | F32 | 32.0000 | | 131 | blk.14.post_ffw_norm_1.weight | Block 14 Post_Ffw_Norm_1 (W) | ( ~3K) 2816 | 2816 x 1 x 1 x 1 | F32 | 32.0000 | | 132 | blk.14.post_ffw_norm_2.weight | Block 14 Post_Ffw_Norm_2 (W) | ( ~3K) 2816 | 2816 x 1 x 1 x 1 | F32 | 32.0000 | | 133 | blk.14.ffn_norm.weight | Block 14 Feed-Forward Network Normalization (W) | ( ~3K) 2816 | 2816 x 1 x 1 x 1 | F32 | 32.0000 | | 134 | blk.14.pre_ffw_norm_2.weight | Block 14 Pre_Ffw_Norm_2 (W) | ( ~3K) 2816 | 2816 x 1 x 1 x 1 | F32 | 32.0000 | | 135 | blk.14.ffn_down_exps.scale | Block 14 Ffn_Down_Exps Scale | ( 128) 128 | 128 x 1 x 1 x 1 | F32 | 32.0000 | | 136 | blk.14.ffn_gate_inp.weight | Block 14 Expert-Routing Layer For The Feed-Forward Network In Mixture Of Expert Models (W) | (~360K) 360448 | 2816 x 128 x 1 x 1 | F32 | 32.0000 | | 137 | blk.14.ffn_gate_inp.scale | Block 14 Expert-Routing Layer For The Feed-Forward Network In Mixture Of Expert Models Scale | ( ~3K) 2816 | 2816 x 1 x 1 x 1 | F32 | 32.0000 | | 138 | blk.14.attn_k_norm.weight | Block 14 Attn_K_Norm (W) | ( 256) 256 | 256 x 1 x 1 x 1 | F32 | 32.0000 | | 139 | blk.14.attn_k.weight | Block 14 Attention Key (W) | ( ~6M) 5767168 | 2816 x 2048 x 1 x 1 | F16 | 16.0000 | | 140 | blk.14.attn_output.weight | Block 14 Attention Output (W) | ( ~12M) 11534336 | 4096 x 2816 x 1 x 1 | F16 | 16.0000 | | 141 | blk.14.attn_q_norm.weight | Block 14 Attn_Q_Norm (W) | ( 256) 256 | 256 x 1 x 1 x 1 | F32 | 32.0000 | | 142 | blk.14.attn_q.weight | Block 14 Attention Query (W) | ( ~12M) 11534336 | 2816 x 4096 x 1 x 1 | F16 | 16.0000 | | 143 | blk.14.attn_v.weight | Block 14 Attention Value (W) | ( ~6M) 5767168 | 2816 x 2048 x 1 x 1 | F16 | 16.0000 | - Total elements in blk.14: (~814M) 814094977 - Percentage of total elements: 3.23% - Bits per Weight (BPW) for blk.14: 16.0075 bits ### Block 15 Tensor Group : ~814M Elements | T_ID | Tensor Layer Name | Human Friendly Tensor Layer Name | Elements | Shape | Type | BPW | | ---: | :-------------------------------- | :------------------------------------------------------------------------------------------- | :---------------- | :-------------------- | :--- | ------: | | 144 | blk.15.ffn_down_exps.weight | Block 15 Ffn_Down_Exps (W) | (~254M) 253755392 | 704 x 2816 x 128 x 1 | F16 | 16.0000 | | 145 | blk.15.ffn_gate_up_exps.weight | Block 15 Ffn_Gate_Up_Exps (W) | (~508M) 507510784 | 2816 x 1408 x 128 x 1 | F16 | 16.0000 | | 146 | blk.15.attn_norm.weight | Block 15 Attention Normalization (W) | ( ~3K) 2816 | 2816 x 1 x 1 x 1 | F32 | 32.0000 | | 147 | blk.15.layer_output_scale.weight | Block 15 Layer_Output_Scale (W) | ( 1) 1 | 1 x 1 x 1 x 1 | F32 | 32.0000 | | 148 | blk.15.ffn_down.weight | Block 15 Feed-Forward Network "Down" (W) | ( ~6M) 5947392 | 2112 x 2816 x 1 x 1 | F16 | 16.0000 | | 149 | blk.15.ffn_gate.weight | Block 15 Feed-Forward Network "Gate" (W) | ( ~6M) 5947392 | 2816 x 2112 x 1 x 1 | F16 | 16.0000 | | 150 | blk.15.ffn_up.weight | Block 15 Feed-Forward Network "Up" (W) | ( ~6M) 5947392 | 2816 x 2112 x 1 x 1 | F16 | 16.0000 | | 151 | blk.15.post_attention_norm.weight | Block 15 Post_Attention_Norm (W) | ( ~3K) 2816 | 2816 x 1 x 1 x 1 | F32 | 32.0000 | | 152 | blk.15.post_ffw_norm.weight | Block 15 Post_Ffw_Norm (W) | ( ~3K) 2816 | 2816 x 1 x 1 x 1 | F32 | 32.0000 | | 153 | blk.15.post_ffw_norm_1.weight | Block 15 Post_Ffw_Norm_1 (W) | ( ~3K) 2816 | 2816 x 1 x 1 x 1 | F32 | 32.0000 | | 154 | blk.15.post_ffw_norm_2.weight | Block 15 Post_Ffw_Norm_2 (W) | ( ~3K) 2816 | 2816 x 1 x 1 x 1 | F32 | 32.0000 | | 155 | blk.15.ffn_norm.weight | Block 15 Feed-Forward Network Normalization (W) | ( ~3K) 2816 | 2816 x 1 x 1 x 1 | F32 | 32.0000 | | 156 | blk.15.pre_ffw_norm_2.weight | Block 15 Pre_Ffw_Norm_2 (W) | ( ~3K) 2816 | 2816 x 1 x 1 x 1 | F32 | 32.0000 | | 157 | blk.15.ffn_down_exps.scale | Block 15 Ffn_Down_Exps Scale | ( 128) 128 | 128 x 1 x 1 x 1 | F32 | 32.0000 | | 158 | blk.15.ffn_gate_inp.weight | Block 15 Expert-Routing Layer For The Feed-Forward Network In Mixture Of Expert Models (W) | (~360K) 360448 | 2816 x 128 x 1 x 1 | F32 | 32.0000 | | 159 | blk.15.ffn_gate_inp.scale | Block 15 Expert-Routing Layer For The Feed-Forward Network In Mixture Of Expert Models Scale | ( ~3K) 2816 | 2816 x 1 x 1 x 1 | F32 | 32.0000 | | 160 | blk.15.attn_k_norm.weight | Block 15 Attn_K_Norm (W) | ( 256) 256 | 256 x 1 x 1 x 1 | F32 | 32.0000 | | 161 | blk.15.attn_k.weight | Block 15 Attention Key (W) | ( ~6M) 5767168 | 2816 x 2048 x 1 x 1 | F16 | 16.0000 | | 162 | blk.15.attn_output.weight | Block 15 Attention Output (W) | ( ~12M) 11534336 | 4096 x 2816 x 1 x 1 | F16 | 16.0000 | | 163 | blk.15.attn_q_norm.weight | Block 15 Attn_Q_Norm (W) | ( 256) 256 | 256 x 1 x 1 x 1 | F32 | 32.0000 | | 164 | blk.15.attn_q.weight | Block 15 Attention Query (W) | ( ~12M) 11534336 | 2816 x 4096 x 1 x 1 | F16 | 16.0000 | | 165 | blk.15.attn_v.weight | Block 15 Attention Value (W) | ( ~6M) 5767168 | 2816 x 2048 x 1 x 1 | F16 | 16.0000 | - Total elements in blk.15: (~814M) 814094977 - Percentage of total elements: 3.23% - Bits per Weight (BPW) for blk.15: 16.0075 bits ### Block 16 Tensor Group : ~814M Elements | T_ID | Tensor Layer Name | Human Friendly Tensor Layer Name | Elements | Shape | Type | BPW | | ---: | :-------------------------------- | :------------------------------------------------------------------------------------------- | :---------------- | :-------------------- | :--- | ------: | | 166 | blk.16.ffn_down_exps.weight | Block 16 Ffn_Down_Exps (W) | (~254M) 253755392 | 704 x 2816 x 128 x 1 | F16 | 16.0000 | | 167 | blk.16.ffn_gate_up_exps.weight | Block 16 Ffn_Gate_Up_Exps (W) | (~508M) 507510784 | 2816 x 1408 x 128 x 1 | F16 | 16.0000 | | 168 | blk.16.attn_norm.weight | Block 16 Attention Normalization (W) | ( ~3K) 2816 | 2816 x 1 x 1 x 1 | F32 | 32.0000 | | 169 | blk.16.layer_output_scale.weight | Block 16 Layer_Output_Scale (W) | ( 1) 1 | 1 x 1 x 1 x 1 | F32 | 32.0000 | | 170 | blk.16.ffn_down.weight | Block 16 Feed-Forward Network "Down" (W) | ( ~6M) 5947392 | 2112 x 2816 x 1 x 1 | F16 | 16.0000 | | 171 | blk.16.ffn_gate.weight | Block 16 Feed-Forward Network "Gate" (W) | ( ~6M) 5947392 | 2816 x 2112 x 1 x 1 | F16 | 16.0000 | | 172 | blk.16.ffn_up.weight | Block 16 Feed-Forward Network "Up" (W) | ( ~6M) 5947392 | 2816 x 2112 x 1 x 1 | F16 | 16.0000 | | 173 | blk.16.post_attention_norm.weight | Block 16 Post_Attention_Norm (W) | ( ~3K) 2816 | 2816 x 1 x 1 x 1 | F32 | 32.0000 | | 174 | blk.16.post_ffw_norm.weight | Block 16 Post_Ffw_Norm (W) | ( ~3K) 2816 | 2816 x 1 x 1 x 1 | F32 | 32.0000 | | 175 | blk.16.post_ffw_norm_1.weight | Block 16 Post_Ffw_Norm_1 (W) | ( ~3K) 2816 | 2816 x 1 x 1 x 1 | F32 | 32.0000 | | 176 | blk.16.post_ffw_norm_2.weight | Block 16 Post_Ffw_Norm_2 (W) | ( ~3K) 2816 | 2816 x 1 x 1 x 1 | F32 | 32.0000 | | 177 | blk.16.ffn_norm.weight | Block 16 Feed-Forward Network Normalization (W) | ( ~3K) 2816 | 2816 x 1 x 1 x 1 | F32 | 32.0000 | | 178 | blk.16.pre_ffw_norm_2.weight | Block 16 Pre_Ffw_Norm_2 (W) | ( ~3K) 2816 | 2816 x 1 x 1 x 1 | F32 | 32.0000 | | 179 | blk.16.ffn_down_exps.scale | Block 16 Ffn_Down_Exps Scale | ( 128) 128 | 128 x 1 x 1 x 1 | F32 | 32.0000 | | 180 | blk.16.ffn_gate_inp.weight | Block 16 Expert-Routing Layer For The Feed-Forward Network In Mixture Of Expert Models (W) | (~360K) 360448 | 2816 x 128 x 1 x 1 | F32 | 32.0000 | | 181 | blk.16.ffn_gate_inp.scale | Block 16 Expert-Routing Layer For The Feed-Forward Network In Mixture Of Expert Models Scale | ( ~3K) 2816 | 2816 x 1 x 1 x 1 | F32 | 32.0000 | | 182 | blk.16.attn_k_norm.weight | Block 16 Attn_K_Norm (W) | ( 256) 256 | 256 x 1 x 1 x 1 | F32 | 32.0000 | | 183 | blk.16.attn_k.weight | Block 16 Attention Key (W) | ( ~6M) 5767168 | 2816 x 2048 x 1 x 1 | F16 | 16.0000 | | 184 | blk.16.attn_output.weight | Block 16 Attention Output (W) | ( ~12M) 11534336 | 4096 x 2816 x 1 x 1 | F16 | 16.0000 | | 185 | blk.16.attn_q_norm.weight | Block 16 Attn_Q_Norm (W) | ( 256) 256 | 256 x 1 x 1 x 1 | F32 | 32.0000 | | 186 | blk.16.attn_q.weight | Block 16 Attention Query (W) | ( ~12M) 11534336 | 2816 x 4096 x 1 x 1 | F16 | 16.0000 | | 187 | blk.16.attn_v.weight | Block 16 Attention Value (W) | ( ~6M) 5767168 | 2816 x 2048 x 1 x 1 | F16 | 16.0000 | - Total elements in blk.16: (~814M) 814094977 - Percentage of total elements: 3.23% - Bits per Weight (BPW) for blk.16: 16.0075 bits ### Block 17 Tensor Group : ~829M Elements | T_ID | Tensor Layer Name | Human Friendly Tensor Layer Name | Elements | Shape | Type | BPW | | ---: | :-------------------------------- | :------------------------------------------------------------------------------------------- | :---------------- | :-------------------- | :--- | ------: | | 188 | blk.17.ffn_gate_up_exps.weight | Block 17 Ffn_Gate_Up_Exps (W) | (~508M) 507510784 | 2816 x 1408 x 128 x 1 | F16 | 16.0000 | | 189 | blk.17.layer_output_scale.weight | Block 17 Layer_Output_Scale (W) | ( 1) 1 | 1 x 1 x 1 x 1 | F32 | 32.0000 | | 190 | blk.17.ffn_down_exps.scale | Block 17 Ffn_Down_Exps Scale | ( 128) 128 | 128 x 1 x 1 x 1 | F32 | 32.0000 | | 191 | blk.17.ffn_gate_inp.scale | Block 17 Expert-Routing Layer For The Feed-Forward Network In Mixture Of Expert Models Scale | ( ~3K) 2816 | 2816 x 1 x 1 x 1 | F32 | 32.0000 | | 192 | blk.17.attn_k_norm.weight | Block 17 Attn_K_Norm (W) | ( 512) 512 | 512 x 1 x 1 x 1 | F32 | 32.0000 | | 193 | blk.17.attn_k.weight | Block 17 Attention Key (W) | ( ~3M) 2883584 | 2816 x 1024 x 1 x 1 | F16 | 16.0000 | | 194 | blk.17.attn_output.weight | Block 17 Attention Output (W) | ( ~23M) 23068672 | 8192 x 2816 x 1 x 1 | F16 | 16.0000 | | 195 | blk.17.attn_q_norm.weight | Block 17 Attn_Q_Norm (W) | ( 512) 512 | 512 x 1 x 1 x 1 | F32 | 32.0000 | | 196 | blk.17.attn_q.weight | Block 17 Attention Query (W) | ( ~23M) 23068672 | 2816 x 8192 x 1 x 1 | F16 | 16.0000 | | 611 | blk.17.ffn_down_exps.weight | Block 17 Ffn_Down_Exps (W) | (~254M) 253755392 | 704 x 2816 x 128 x 1 | F16 | 16.0000 | | 612 | blk.17.attn_norm.weight | Block 17 Attention Normalization (W) | ( ~3K) 2816 | 2816 x 1 x 1 x 1 | F32 | 32.0000 | | 613 | blk.17.ffn_down.weight | Block 17 Feed-Forward Network "Down" (W) | ( ~6M) 5947392 | 2112 x 2816 x 1 x 1 | F16 | 16.0000 | | 614 | blk.17.ffn_gate.weight | Block 17 Feed-Forward Network "Gate" (W) | ( ~6M) 5947392 | 2816 x 2112 x 1 x 1 | F16 | 16.0000 | | 615 | blk.17.ffn_up.weight | Block 17 Feed-Forward Network "Up" (W) | ( ~6M) 5947392 | 2816 x 2112 x 1 x 1 | F16 | 16.0000 | | 616 | blk.17.post_attention_norm.weight | Block 17 Post_Attention_Norm (W) | ( ~3K) 2816 | 2816 x 1 x 1 x 1 | F32 | 32.0000 | | 617 | blk.17.post_ffw_norm.weight | Block 17 Post_Ffw_Norm (W) | ( ~3K) 2816 | 2816 x 1 x 1 x 1 | F32 | 32.0000 | | 618 | blk.17.post_ffw_norm_1.weight | Block 17 Post_Ffw_Norm_1 (W) | ( ~3K) 2816 | 2816 x 1 x 1 x 1 | F32 | 32.0000 | | 619 | blk.17.post_ffw_norm_2.weight | Block 17 Post_Ffw_Norm_2 (W) | ( ~3K) 2816 | 2816 x 1 x 1 x 1 | F32 | 32.0000 | | 620 | blk.17.ffn_norm.weight | Block 17 Feed-Forward Network Normalization (W) | ( ~3K) 2816 | 2816 x 1 x 1 x 1 | F32 | 32.0000 | | 621 | blk.17.pre_ffw_norm_2.weight | Block 17 Pre_Ffw_Norm_2 (W) | ( ~3K) 2816 | 2816 x 1 x 1 x 1 | F32 | 32.0000 | | 622 | blk.17.ffn_gate_inp.weight | Block 17 Expert-Routing Layer For The Feed-Forward Network In Mixture Of Expert Models (W) | (~360K) 360448 | 2816 x 128 x 1 x 1 | F32 | 32.0000 | - Total elements in blk.17: (~829M) 828513409 - Percentage of total elements: 3.28% - Bits per Weight (BPW) for blk.17: 16.0074 bits ### Block 18 Tensor Group : ~814M Elements | T_ID | Tensor Layer Name | Human Friendly Tensor Layer Name | Elements | Shape | Type | BPW | | ---: | :-------------------------------- | :------------------------------------------------------------------------------------------- | :---------------- | :-------------------- | :--- | ------: | | 197 | blk.18.ffn_down_exps.weight | Block 18 Ffn_Down_Exps (W) | (~254M) 253755392 | 704 x 2816 x 128 x 1 | F16 | 16.0000 | | 198 | blk.18.ffn_gate_up_exps.weight | Block 18 Ffn_Gate_Up_Exps (W) | (~508M) 507510784 | 2816 x 1408 x 128 x 1 | F16 | 16.0000 | | 199 | blk.18.attn_norm.weight | Block 18 Attention Normalization (W) | ( ~3K) 2816 | 2816 x 1 x 1 x 1 | F32 | 32.0000 | | 200 | blk.18.layer_output_scale.weight | Block 18 Layer_Output_Scale (W) | ( 1) 1 | 1 x 1 x 1 x 1 | F32 | 32.0000 | | 201 | blk.18.ffn_down.weight | Block 18 Feed-Forward Network "Down" (W) | ( ~6M) 5947392 | 2112 x 2816 x 1 x 1 | F16 | 16.0000 | | 202 | blk.18.ffn_gate.weight | Block 18 Feed-Forward Network "Gate" (W) | ( ~6M) 5947392 | 2816 x 2112 x 1 x 1 | F16 | 16.0000 | | 203 | blk.18.ffn_up.weight | Block 18 Feed-Forward Network "Up" (W) | ( ~6M) 5947392 | 2816 x 2112 x 1 x 1 | F16 | 16.0000 | | 204 | blk.18.post_attention_norm.weight | Block 18 Post_Attention_Norm (W) | ( ~3K) 2816 | 2816 x 1 x 1 x 1 | F32 | 32.0000 | | 205 | blk.18.post_ffw_norm.weight | Block 18 Post_Ffw_Norm (W) | ( ~3K) 2816 | 2816 x 1 x 1 x 1 | F32 | 32.0000 | | 206 | blk.18.post_ffw_norm_1.weight | Block 18 Post_Ffw_Norm_1 (W) | ( ~3K) 2816 | 2816 x 1 x 1 x 1 | F32 | 32.0000 | | 207 | blk.18.post_ffw_norm_2.weight | Block 18 Post_Ffw_Norm_2 (W) | ( ~3K) 2816 | 2816 x 1 x 1 x 1 | F32 | 32.0000 | | 208 | blk.18.ffn_norm.weight | Block 18 Feed-Forward Network Normalization (W) | ( ~3K) 2816 | 2816 x 1 x 1 x 1 | F32 | 32.0000 | | 209 | blk.18.pre_ffw_norm_2.weight | Block 18 Pre_Ffw_Norm_2 (W) | ( ~3K) 2816 | 2816 x 1 x 1 x 1 | F32 | 32.0000 | | 210 | blk.18.ffn_down_exps.scale | Block 18 Ffn_Down_Exps Scale | ( 128) 128 | 128 x 1 x 1 x 1 | F32 | 32.0000 | | 211 | blk.18.ffn_gate_inp.weight | Block 18 Expert-Routing Layer For The Feed-Forward Network In Mixture Of Expert Models (W) | (~360K) 360448 | 2816 x 128 x 1 x 1 | F32 | 32.0000 | | 212 | blk.18.ffn_gate_inp.scale | Block 18 Expert-Routing Layer For The Feed-Forward Network In Mixture Of Expert Models Scale | ( ~3K) 2816 | 2816 x 1 x 1 x 1 | F32 | 32.0000 | | 213 | blk.18.attn_k_norm.weight | Block 18 Attn_K_Norm (W) | ( 256) 256 | 256 x 1 x 1 x 1 | F32 | 32.0000 | | 214 | blk.18.attn_k.weight | Block 18 Attention Key (W) | ( ~6M) 5767168 | 2816 x 2048 x 1 x 1 | F16 | 16.0000 | | 215 | blk.18.attn_output.weight | Block 18 Attention Output (W) | ( ~12M) 11534336 | 4096 x 2816 x 1 x 1 | F16 | 16.0000 | | 216 | blk.18.attn_q_norm.weight | Block 18 Attn_Q_Norm (W) | ( 256) 256 | 256 x 1 x 1 x 1 | F32 | 32.0000 | | 217 | blk.18.attn_q.weight | Block 18 Attention Query (W) | ( ~12M) 11534336 | 2816 x 4096 x 1 x 1 | F16 | 16.0000 | | 218 | blk.18.attn_v.weight | Block 18 Attention Value (W) | ( ~6M) 5767168 | 2816 x 2048 x 1 x 1 | F16 | 16.0000 | - Total elements in blk.18: (~814M) 814094977 - Percentage of total elements: 3.23% - Bits per Weight (BPW) for blk.18: 16.0075 bits ### Block 19 Tensor Group : ~814M Elements | T_ID | Tensor Layer Name | Human Friendly Tensor Layer Name | Elements | Shape | Type | BPW | | ---: | :-------------------------------- | :------------------------------------------------------------------------------------------- | :---------------- | :-------------------- | :--- | ------: | | 219 | blk.19.ffn_down_exps.weight | Block 19 Ffn_Down_Exps (W) | (~254M) 253755392 | 704 x 2816 x 128 x 1 | F16 | 16.0000 | | 220 | blk.19.ffn_gate_up_exps.weight | Block 19 Ffn_Gate_Up_Exps (W) | (~508M) 507510784 | 2816 x 1408 x 128 x 1 | F16 | 16.0000 | | 221 | blk.19.attn_norm.weight | Block 19 Attention Normalization (W) | ( ~3K) 2816 | 2816 x 1 x 1 x 1 | F32 | 32.0000 | | 222 | blk.19.layer_output_scale.weight | Block 19 Layer_Output_Scale (W) | ( 1) 1 | 1 x 1 x 1 x 1 | F32 | 32.0000 | | 223 | blk.19.ffn_down.weight | Block 19 Feed-Forward Network "Down" (W) | ( ~6M) 5947392 | 2112 x 2816 x 1 x 1 | F16 | 16.0000 | | 224 | blk.19.ffn_gate.weight | Block 19 Feed-Forward Network "Gate" (W) | ( ~6M) 5947392 | 2816 x 2112 x 1 x 1 | F16 | 16.0000 | | 225 | blk.19.ffn_up.weight | Block 19 Feed-Forward Network "Up" (W) | ( ~6M) 5947392 | 2816 x 2112 x 1 x 1 | F16 | 16.0000 | | 226 | blk.19.post_attention_norm.weight | Block 19 Post_Attention_Norm (W) | ( ~3K) 2816 | 2816 x 1 x 1 x 1 | F32 | 32.0000 | | 227 | blk.19.post_ffw_norm.weight | Block 19 Post_Ffw_Norm (W) | ( ~3K) 2816 | 2816 x 1 x 1 x 1 | F32 | 32.0000 | | 228 | blk.19.post_ffw_norm_1.weight | Block 19 Post_Ffw_Norm_1 (W) | ( ~3K) 2816 | 2816 x 1 x 1 x 1 | F32 | 32.0000 | | 229 | blk.19.post_ffw_norm_2.weight | Block 19 Post_Ffw_Norm_2 (W) | ( ~3K) 2816 | 2816 x 1 x 1 x 1 | F32 | 32.0000 | | 230 | blk.19.ffn_norm.weight | Block 19 Feed-Forward Network Normalization (W) | ( ~3K) 2816 | 2816 x 1 x 1 x 1 | F32 | 32.0000 | | 231 | blk.19.pre_ffw_norm_2.weight | Block 19 Pre_Ffw_Norm_2 (W) | ( ~3K) 2816 | 2816 x 1 x 1 x 1 | F32 | 32.0000 | | 232 | blk.19.ffn_down_exps.scale | Block 19 Ffn_Down_Exps Scale | ( 128) 128 | 128 x 1 x 1 x 1 | F32 | 32.0000 | | 233 | blk.19.ffn_gate_inp.weight | Block 19 Expert-Routing Layer For The Feed-Forward Network In Mixture Of Expert Models (W) | (~360K) 360448 | 2816 x 128 x 1 x 1 | F32 | 32.0000 | | 234 | blk.19.ffn_gate_inp.scale | Block 19 Expert-Routing Layer For The Feed-Forward Network In Mixture Of Expert Models Scale | ( ~3K) 2816 | 2816 x 1 x 1 x 1 | F32 | 32.0000 | | 235 | blk.19.attn_k_norm.weight | Block 19 Attn_K_Norm (W) | ( 256) 256 | 256 x 1 x 1 x 1 | F32 | 32.0000 | | 236 | blk.19.attn_k.weight | Block 19 Attention Key (W) | ( ~6M) 5767168 | 2816 x 2048 x 1 x 1 | F16 | 16.0000 | | 237 | blk.19.attn_output.weight | Block 19 Attention Output (W) | ( ~12M) 11534336 | 4096 x 2816 x 1 x 1 | F16 | 16.0000 | | 238 | blk.19.attn_q_norm.weight | Block 19 Attn_Q_Norm (W) | ( 256) 256 | 256 x 1 x 1 x 1 | F32 | 32.0000 | | 239 | blk.19.attn_q.weight | Block 19 Attention Query (W) | ( ~12M) 11534336 | 2816 x 4096 x 1 x 1 | F16 | 16.0000 | | 240 | blk.19.attn_v.weight | Block 19 Attention Value (W) | ( ~6M) 5767168 | 2816 x 2048 x 1 x 1 | F16 | 16.0000 | - Total elements in blk.19: (~814M) 814094977 - Percentage of total elements: 3.23% - Bits per Weight (BPW) for blk.19: 16.0075 bits ### Block 2 Tensor Group : ~814M Elements | T_ID | Tensor Layer Name | Human Friendly Tensor Layer Name | Elements | Shape | Type | BPW | | ---: | :------------------------------- | :------------------------------------------------------------------------------------------ | :---------------- | :-------------------- | :--- | ------: | | 241 | blk.2.ffn_down_exps.weight | Block 2 Ffn_Down_Exps (W) | (~254M) 253755392 | 704 x 2816 x 128 x 1 | F16 | 16.0000 | | 242 | blk.2.ffn_gate_up_exps.weight | Block 2 Ffn_Gate_Up_Exps (W) | (~508M) 507510784 | 2816 x 1408 x 128 x 1 | F16 | 16.0000 | | 243 | blk.2.attn_norm.weight | Block 2 Attention Normalization (W) | ( ~3K) 2816 | 2816 x 1 x 1 x 1 | F32 | 32.0000 | | 244 | blk.2.layer_output_scale.weight | Block 2 Layer_Output_Scale (W) | ( 1) 1 | 1 x 1 x 1 x 1 | F32 | 32.0000 | | 245 | blk.2.ffn_down.weight | Block 2 Feed-Forward Network "Down" (W) | ( ~6M) 5947392 | 2112 x 2816 x 1 x 1 | F16 | 16.0000 | | 246 | blk.2.ffn_gate.weight | Block 2 Feed-Forward Network "Gate" (W) | ( ~6M) 5947392 | 2816 x 2112 x 1 x 1 | F16 | 16.0000 | | 247 | blk.2.ffn_up.weight | Block 2 Feed-Forward Network "Up" (W) | ( ~6M) 5947392 | 2816 x 2112 x 1 x 1 | F16 | 16.0000 | | 248 | blk.2.post_attention_norm.weight | Block 2 Post_Attention_Norm (W) | ( ~3K) 2816 | 2816 x 1 x 1 x 1 | F32 | 32.0000 | | 249 | blk.2.post_ffw_norm.weight | Block 2 Post_Ffw_Norm (W) | ( ~3K) 2816 | 2816 x 1 x 1 x 1 | F32 | 32.0000 | | 250 | blk.2.post_ffw_norm_1.weight | Block 2 Post_Ffw_Norm_1 (W) | ( ~3K) 2816 | 2816 x 1 x 1 x 1 | F32 | 32.0000 | | 251 | blk.2.post_ffw_norm_2.weight | Block 2 Post_Ffw_Norm_2 (W) | ( ~3K) 2816 | 2816 x 1 x 1 x 1 | F32 | 32.0000 | | 252 | blk.2.ffn_norm.weight | Block 2 Feed-Forward Network Normalization (W) | ( ~3K) 2816 | 2816 x 1 x 1 x 1 | F32 | 32.0000 | | 253 | blk.2.pre_ffw_norm_2.weight | Block 2 Pre_Ffw_Norm_2 (W) | ( ~3K) 2816 | 2816 x 1 x 1 x 1 | F32 | 32.0000 | | 254 | blk.2.ffn_down_exps.scale | Block 2 Ffn_Down_Exps Scale | ( 128) 128 | 128 x 1 x 1 x 1 | F32 | 32.0000 | | 255 | blk.2.ffn_gate_inp.weight | Block 2 Expert-Routing Layer For The Feed-Forward Network In Mixture Of Expert Models (W) | (~360K) 360448 | 2816 x 128 x 1 x 1 | F32 | 32.0000 | | 256 | blk.2.ffn_gate_inp.scale | Block 2 Expert-Routing Layer For The Feed-Forward Network In Mixture Of Expert Models Scale | ( ~3K) 2816 | 2816 x 1 x 1 x 1 | F32 | 32.0000 | | 257 | blk.2.attn_k_norm.weight | Block 2 Attn_K_Norm (W) | ( 256) 256 | 256 x 1 x 1 x 1 | F32 | 32.0000 | | 258 | blk.2.attn_k.weight | Block 2 Attention Key (W) | ( ~6M) 5767168 | 2816 x 2048 x 1 x 1 | F16 | 16.0000 | | 259 | blk.2.attn_output.weight | Block 2 Attention Output (W) | ( ~12M) 11534336 | 4096 x 2816 x 1 x 1 | F16 | 16.0000 | | 260 | blk.2.attn_q_norm.weight | Block 2 Attn_Q_Norm (W) | ( 256) 256 | 256 x 1 x 1 x 1 | F32 | 32.0000 | | 261 | blk.2.attn_q.weight | Block 2 Attention Query (W) | ( ~12M) 11534336 | 2816 x 4096 x 1 x 1 | F16 | 16.0000 | | 262 | blk.2.attn_v.weight | Block 2 Attention Value (W) | ( ~6M) 5767168 | 2816 x 2048 x 1 x 1 | F16 | 16.0000 | - Total elements in blk.2: (~814M) 814094977 - Percentage of total elements: 3.23% - Bits per Weight (BPW) for blk.2: 16.0075 bits ### Block 20 Tensor Group : ~814M Elements | T_ID | Tensor Layer Name | Human Friendly Tensor Layer Name | Elements | Shape | Type | BPW | | ---: | :-------------------------------- | :------------------------------------------------------------------------------------------- | :---------------- | :-------------------- | :--- | ------: | | 263 | blk.20.ffn_down_exps.weight | Block 20 Ffn_Down_Exps (W) | (~254M) 253755392 | 704 x 2816 x 128 x 1 | F16 | 16.0000 | | 264 | blk.20.ffn_gate_up_exps.weight | Block 20 Ffn_Gate_Up_Exps (W) | (~508M) 507510784 | 2816 x 1408 x 128 x 1 | F16 | 16.0000 | | 265 | blk.20.attn_norm.weight | Block 20 Attention Normalization (W) | ( ~3K) 2816 | 2816 x 1 x 1 x 1 | F32 | 32.0000 | | 266 | blk.20.layer_output_scale.weight | Block 20 Layer_Output_Scale (W) | ( 1) 1 | 1 x 1 x 1 x 1 | F32 | 32.0000 | | 267 | blk.20.ffn_down.weight | Block 20 Feed-Forward Network "Down" (W) | ( ~6M) 5947392 | 2112 x 2816 x 1 x 1 | F16 | 16.0000 | | 268 | blk.20.ffn_gate.weight | Block 20 Feed-Forward Network "Gate" (W) | ( ~6M) 5947392 | 2816 x 2112 x 1 x 1 | F16 | 16.0000 | | 269 | blk.20.ffn_up.weight | Block 20 Feed-Forward Network "Up" (W) | ( ~6M) 5947392 | 2816 x 2112 x 1 x 1 | F16 | 16.0000 | | 270 | blk.20.post_attention_norm.weight | Block 20 Post_Attention_Norm (W) | ( ~3K) 2816 | 2816 x 1 x 1 x 1 | F32 | 32.0000 | | 271 | blk.20.post_ffw_norm.weight | Block 20 Post_Ffw_Norm (W) | ( ~3K) 2816 | 2816 x 1 x 1 x 1 | F32 | 32.0000 | | 272 | blk.20.post_ffw_norm_1.weight | Block 20 Post_Ffw_Norm_1 (W) | ( ~3K) 2816 | 2816 x 1 x 1 x 1 | F32 | 32.0000 | | 273 | blk.20.post_ffw_norm_2.weight | Block 20 Post_Ffw_Norm_2 (W) | ( ~3K) 2816 | 2816 x 1 x 1 x 1 | F32 | 32.0000 | | 274 | blk.20.ffn_norm.weight | Block 20 Feed-Forward Network Normalization (W) | ( ~3K) 2816 | 2816 x 1 x 1 x 1 | F32 | 32.0000 | | 275 | blk.20.pre_ffw_norm_2.weight | Block 20 Pre_Ffw_Norm_2 (W) | ( ~3K) 2816 | 2816 x 1 x 1 x 1 | F32 | 32.0000 | | 276 | blk.20.ffn_down_exps.scale | Block 20 Ffn_Down_Exps Scale | ( 128) 128 | 128 x 1 x 1 x 1 | F32 | 32.0000 | | 277 | blk.20.ffn_gate_inp.weight | Block 20 Expert-Routing Layer For The Feed-Forward Network In Mixture Of Expert Models (W) | (~360K) 360448 | 2816 x 128 x 1 x 1 | F32 | 32.0000 | | 278 | blk.20.ffn_gate_inp.scale | Block 20 Expert-Routing Layer For The Feed-Forward Network In Mixture Of Expert Models Scale | ( ~3K) 2816 | 2816 x 1 x 1 x 1 | F32 | 32.0000 | | 279 | blk.20.attn_k_norm.weight | Block 20 Attn_K_Norm (W) | ( 256) 256 | 256 x 1 x 1 x 1 | F32 | 32.0000 | | 280 | blk.20.attn_k.weight | Block 20 Attention Key (W) | ( ~6M) 5767168 | 2816 x 2048 x 1 x 1 | F16 | 16.0000 | | 281 | blk.20.attn_output.weight | Block 20 Attention Output (W) | ( ~12M) 11534336 | 4096 x 2816 x 1 x 1 | F16 | 16.0000 | | 282 | blk.20.attn_q_norm.weight | Block 20 Attn_Q_Norm (W) | ( 256) 256 | 256 x 1 x 1 x 1 | F32 | 32.0000 | | 283 | blk.20.attn_q.weight | Block 20 Attention Query (W) | ( ~12M) 11534336 | 2816 x 4096 x 1 x 1 | F16 | 16.0000 | | 284 | blk.20.attn_v.weight | Block 20 Attention Value (W) | ( ~6M) 5767168 | 2816 x 2048 x 1 x 1 | F16 | 16.0000 | - Total elements in blk.20: (~814M) 814094977 - Percentage of total elements: 3.23% - Bits per Weight (BPW) for blk.20: 16.0075 bits ### Block 21 Tensor Group : ~814M Elements | T_ID | Tensor Layer Name | Human Friendly Tensor Layer Name | Elements | Shape | Type | BPW | | ---: | :-------------------------------- | :------------------------------------------------------------------------------------------- | :---------------- | :-------------------- | :--- | ------: | | 285 | blk.21.ffn_down_exps.weight | Block 21 Ffn_Down_Exps (W) | (~254M) 253755392 | 704 x 2816 x 128 x 1 | F16 | 16.0000 | | 286 | blk.21.ffn_gate_up_exps.weight | Block 21 Ffn_Gate_Up_Exps (W) | (~508M) 507510784 | 2816 x 1408 x 128 x 1 | F16 | 16.0000 | | 287 | blk.21.attn_norm.weight | Block 21 Attention Normalization (W) | ( ~3K) 2816 | 2816 x 1 x 1 x 1 | F32 | 32.0000 | | 288 | blk.21.layer_output_scale.weight | Block 21 Layer_Output_Scale (W) | ( 1) 1 | 1 x 1 x 1 x 1 | F32 | 32.0000 | | 289 | blk.21.ffn_down.weight | Block 21 Feed-Forward Network "Down" (W) | ( ~6M) 5947392 | 2112 x 2816 x 1 x 1 | F16 | 16.0000 | | 290 | blk.21.ffn_gate.weight | Block 21 Feed-Forward Network "Gate" (W) | ( ~6M) 5947392 | 2816 x 2112 x 1 x 1 | F16 | 16.0000 | | 291 | blk.21.ffn_up.weight | Block 21 Feed-Forward Network "Up" (W) | ( ~6M) 5947392 | 2816 x 2112 x 1 x 1 | F16 | 16.0000 | | 292 | blk.21.post_attention_norm.weight | Block 21 Post_Attention_Norm (W) | ( ~3K) 2816 | 2816 x 1 x 1 x 1 | F32 | 32.0000 | | 293 | blk.21.post_ffw_norm.weight | Block 21 Post_Ffw_Norm (W) | ( ~3K) 2816 | 2816 x 1 x 1 x 1 | F32 | 32.0000 | | 294 | blk.21.post_ffw_norm_1.weight | Block 21 Post_Ffw_Norm_1 (W) | ( ~3K) 2816 | 2816 x 1 x 1 x 1 | F32 | 32.0000 | | 295 | blk.21.post_ffw_norm_2.weight | Block 21 Post_Ffw_Norm_2 (W) | ( ~3K) 2816 | 2816 x 1 x 1 x 1 | F32 | 32.0000 | | 296 | blk.21.ffn_norm.weight | Block 21 Feed-Forward Network Normalization (W) | ( ~3K) 2816 | 2816 x 1 x 1 x 1 | F32 | 32.0000 | | 297 | blk.21.pre_ffw_norm_2.weight | Block 21 Pre_Ffw_Norm_2 (W) | ( ~3K) 2816 | 2816 x 1 x 1 x 1 | F32 | 32.0000 | | 298 | blk.21.ffn_down_exps.scale | Block 21 Ffn_Down_Exps Scale | ( 128) 128 | 128 x 1 x 1 x 1 | F32 | 32.0000 | | 299 | blk.21.ffn_gate_inp.weight | Block 21 Expert-Routing Layer For The Feed-Forward Network In Mixture Of Expert Models (W) | (~360K) 360448 | 2816 x 128 x 1 x 1 | F32 | 32.0000 | | 300 | blk.21.ffn_gate_inp.scale | Block 21 Expert-Routing Layer For The Feed-Forward Network In Mixture Of Expert Models Scale | ( ~3K) 2816 | 2816 x 1 x 1 x 1 | F32 | 32.0000 | | 301 | blk.21.attn_k_norm.weight | Block 21 Attn_K_Norm (W) | ( 256) 256 | 256 x 1 x 1 x 1 | F32 | 32.0000 | | 302 | blk.21.attn_k.weight | Block 21 Attention Key (W) | ( ~6M) 5767168 | 2816 x 2048 x 1 x 1 | F16 | 16.0000 | | 303 | blk.21.attn_output.weight | Block 21 Attention Output (W) | ( ~12M) 11534336 | 4096 x 2816 x 1 x 1 | F16 | 16.0000 | | 304 | blk.21.attn_q_norm.weight | Block 21 Attn_Q_Norm (W) | ( 256) 256 | 256 x 1 x 1 x 1 | F32 | 32.0000 | | 305 | blk.21.attn_q.weight | Block 21 Attention Query (W) | ( ~12M) 11534336 | 2816 x 4096 x 1 x 1 | F16 | 16.0000 | | 306 | blk.21.attn_v.weight | Block 21 Attention Value (W) | ( ~6M) 5767168 | 2816 x 2048 x 1 x 1 | F16 | 16.0000 | - Total elements in blk.21: (~814M) 814094977 - Percentage of total elements: 3.23% - Bits per Weight (BPW) for blk.21: 16.0075 bits ### Block 22 Tensor Group : ~814M Elements | T_ID | Tensor Layer Name | Human Friendly Tensor Layer Name | Elements | Shape | Type | BPW | | ---: | :-------------------------------- | :------------------------------------------------------------------------------------------- | :---------------- | :-------------------- | :--- | ------: | | 307 | blk.22.ffn_down_exps.weight | Block 22 Ffn_Down_Exps (W) | (~254M) 253755392 | 704 x 2816 x 128 x 1 | F16 | 16.0000 | | 308 | blk.22.ffn_gate_up_exps.weight | Block 22 Ffn_Gate_Up_Exps (W) | (~508M) 507510784 | 2816 x 1408 x 128 x 1 | F16 | 16.0000 | | 309 | blk.22.attn_norm.weight | Block 22 Attention Normalization (W) | ( ~3K) 2816 | 2816 x 1 x 1 x 1 | F32 | 32.0000 | | 310 | blk.22.layer_output_scale.weight | Block 22 Layer_Output_Scale (W) | ( 1) 1 | 1 x 1 x 1 x 1 | F32 | 32.0000 | | 311 | blk.22.ffn_down.weight | Block 22 Feed-Forward Network "Down" (W) | ( ~6M) 5947392 | 2112 x 2816 x 1 x 1 | F16 | 16.0000 | | 312 | blk.22.ffn_gate.weight | Block 22 Feed-Forward Network "Gate" (W) | ( ~6M) 5947392 | 2816 x 2112 x 1 x 1 | F16 | 16.0000 | | 313 | blk.22.ffn_up.weight | Block 22 Feed-Forward Network "Up" (W) | ( ~6M) 5947392 | 2816 x 2112 x 1 x 1 | F16 | 16.0000 | | 314 | blk.22.post_attention_norm.weight | Block 22 Post_Attention_Norm (W) | ( ~3K) 2816 | 2816 x 1 x 1 x 1 | F32 | 32.0000 | | 315 | blk.22.post_ffw_norm.weight | Block 22 Post_Ffw_Norm (W) | ( ~3K) 2816 | 2816 x 1 x 1 x 1 | F32 | 32.0000 | | 316 | blk.22.post_ffw_norm_1.weight | Block 22 Post_Ffw_Norm_1 (W) | ( ~3K) 2816 | 2816 x 1 x 1 x 1 | F32 | 32.0000 | | 317 | blk.22.post_ffw_norm_2.weight | Block 22 Post_Ffw_Norm_2 (W) | ( ~3K) 2816 | 2816 x 1 x 1 x 1 | F32 | 32.0000 | | 318 | blk.22.ffn_norm.weight | Block 22 Feed-Forward Network Normalization (W) | ( ~3K) 2816 | 2816 x 1 x 1 x 1 | F32 | 32.0000 | | 319 | blk.22.pre_ffw_norm_2.weight | Block 22 Pre_Ffw_Norm_2 (W) | ( ~3K) 2816 | 2816 x 1 x 1 x 1 | F32 | 32.0000 | | 320 | blk.22.ffn_down_exps.scale | Block 22 Ffn_Down_Exps Scale | ( 128) 128 | 128 x 1 x 1 x 1 | F32 | 32.0000 | | 321 | blk.22.ffn_gate_inp.weight | Block 22 Expert-Routing Layer For The Feed-Forward Network In Mixture Of Expert Models (W) | (~360K) 360448 | 2816 x 128 x 1 x 1 | F32 | 32.0000 | | 322 | blk.22.ffn_gate_inp.scale | Block 22 Expert-Routing Layer For The Feed-Forward Network In Mixture Of Expert Models Scale | ( ~3K) 2816 | 2816 x 1 x 1 x 1 | F32 | 32.0000 | | 323 | blk.22.attn_k_norm.weight | Block 22 Attn_K_Norm (W) | ( 256) 256 | 256 x 1 x 1 x 1 | F32 | 32.0000 | | 324 | blk.22.attn_k.weight | Block 22 Attention Key (W) | ( ~6M) 5767168 | 2816 x 2048 x 1 x 1 | F16 | 16.0000 | | 325 | blk.22.attn_output.weight | Block 22 Attention Output (W) | ( ~12M) 11534336 | 4096 x 2816 x 1 x 1 | F16 | 16.0000 | | 326 | blk.22.attn_q_norm.weight | Block 22 Attn_Q_Norm (W) | ( 256) 256 | 256 x 1 x 1 x 1 | F32 | 32.0000 | | 327 | blk.22.attn_q.weight | Block 22 Attention Query (W) | ( ~12M) 11534336 | 2816 x 4096 x 1 x 1 | F16 | 16.0000 | | 328 | blk.22.attn_v.weight | Block 22 Attention Value (W) | ( ~6M) 5767168 | 2816 x 2048 x 1 x 1 | F16 | 16.0000 | - Total elements in blk.22: (~814M) 814094977 - Percentage of total elements: 3.23% - Bits per Weight (BPW) for blk.22: 16.0075 bits ### Block 23 Tensor Group : ~829M Elements | T_ID | Tensor Layer Name | Human Friendly Tensor Layer Name | Elements | Shape | Type | BPW | | ---: | :-------------------------------- | :------------------------------------------------------------------------------------------- | :---------------- | :-------------------- | :--- | ------: | | 329 | blk.23.ffn_gate_up_exps.weight | Block 23 Ffn_Gate_Up_Exps (W) | (~508M) 507510784 | 2816 x 1408 x 128 x 1 | F16 | 16.0000 | | 330 | blk.23.layer_output_scale.weight | Block 23 Layer_Output_Scale (W) | ( 1) 1 | 1 x 1 x 1 x 1 | F32 | 32.0000 | | 331 | blk.23.ffn_down_exps.scale | Block 23 Ffn_Down_Exps Scale | ( 128) 128 | 128 x 1 x 1 x 1 | F32 | 32.0000 | | 332 | blk.23.ffn_gate_inp.scale | Block 23 Expert-Routing Layer For The Feed-Forward Network In Mixture Of Expert Models Scale | ( ~3K) 2816 | 2816 x 1 x 1 x 1 | F32 | 32.0000 | | 333 | blk.23.attn_k_norm.weight | Block 23 Attn_K_Norm (W) | ( 512) 512 | 512 x 1 x 1 x 1 | F32 | 32.0000 | | 334 | blk.23.attn_k.weight | Block 23 Attention Key (W) | ( ~3M) 2883584 | 2816 x 1024 x 1 x 1 | F16 | 16.0000 | | 335 | blk.23.attn_output.weight | Block 23 Attention Output (W) | ( ~23M) 23068672 | 8192 x 2816 x 1 x 1 | F16 | 16.0000 | | 336 | blk.23.attn_q_norm.weight | Block 23 Attn_Q_Norm (W) | ( 512) 512 | 512 x 1 x 1 x 1 | F32 | 32.0000 | | 337 | blk.23.attn_q.weight | Block 23 Attention Query (W) | ( ~23M) 23068672 | 2816 x 8192 x 1 x 1 | F16 | 16.0000 | | 623 | blk.23.ffn_down_exps.weight | Block 23 Ffn_Down_Exps (W) | (~254M) 253755392 | 704 x 2816 x 128 x 1 | F16 | 16.0000 | | 624 | blk.23.attn_norm.weight | Block 23 Attention Normalization (W) | ( ~3K) 2816 | 2816 x 1 x 1 x 1 | F32 | 32.0000 | | 625 | blk.23.ffn_down.weight | Block 23 Feed-Forward Network "Down" (W) | ( ~6M) 5947392 | 2112 x 2816 x 1 x 1 | F16 | 16.0000 | | 626 | blk.23.ffn_gate.weight | Block 23 Feed-Forward Network "Gate" (W) | ( ~6M) 5947392 | 2816 x 2112 x 1 x 1 | F16 | 16.0000 | | 627 | blk.23.ffn_up.weight | Block 23 Feed-Forward Network "Up" (W) | ( ~6M) 5947392 | 2816 x 2112 x 1 x 1 | F16 | 16.0000 | | 628 | blk.23.post_attention_norm.weight | Block 23 Post_Attention_Norm (W) | ( ~3K) 2816 | 2816 x 1 x 1 x 1 | F32 | 32.0000 | | 629 | blk.23.post_ffw_norm.weight | Block 23 Post_Ffw_Norm (W) | ( ~3K) 2816 | 2816 x 1 x 1 x 1 | F32 | 32.0000 | | 630 | blk.23.post_ffw_norm_1.weight | Block 23 Post_Ffw_Norm_1 (W) | ( ~3K) 2816 | 2816 x 1 x 1 x 1 | F32 | 32.0000 | | 631 | blk.23.post_ffw_norm_2.weight | Block 23 Post_Ffw_Norm_2 (W) | ( ~3K) 2816 | 2816 x 1 x 1 x 1 | F32 | 32.0000 | | 632 | blk.23.ffn_norm.weight | Block 23 Feed-Forward Network Normalization (W) | ( ~3K) 2816 | 2816 x 1 x 1 x 1 | F32 | 32.0000 | | 633 | blk.23.pre_ffw_norm_2.weight | Block 23 Pre_Ffw_Norm_2 (W) | ( ~3K) 2816 | 2816 x 1 x 1 x 1 | F32 | 32.0000 | | 634 | blk.23.ffn_gate_inp.weight | Block 23 Expert-Routing Layer For The Feed-Forward Network In Mixture Of Expert Models (W) | (~360K) 360448 | 2816 x 128 x 1 x 1 | F32 | 32.0000 | - Total elements in blk.23: (~829M) 828513409 - Percentage of total elements: 3.28% - Bits per Weight (BPW) for blk.23: 16.0074 bits ### Block 24 Tensor Group : ~814M Elements | T_ID | Tensor Layer Name | Human Friendly Tensor Layer Name | Elements | Shape | Type | BPW | | ---: | :-------------------------------- | :------------------------------------------------------------------------------------------- | :---------------- | :-------------------- | :--- | ------: | | 338 | blk.24.ffn_down_exps.weight | Block 24 Ffn_Down_Exps (W) | (~254M) 253755392 | 704 x 2816 x 128 x 1 | F16 | 16.0000 | | 339 | blk.24.ffn_gate_up_exps.weight | Block 24 Ffn_Gate_Up_Exps (W) | (~508M) 507510784 | 2816 x 1408 x 128 x 1 | F16 | 16.0000 | | 340 | blk.24.attn_norm.weight | Block 24 Attention Normalization (W) | ( ~3K) 2816 | 2816 x 1 x 1 x 1 | F32 | 32.0000 | | 341 | blk.24.layer_output_scale.weight | Block 24 Layer_Output_Scale (W) | ( 1) 1 | 1 x 1 x 1 x 1 | F32 | 32.0000 | | 342 | blk.24.ffn_down.weight | Block 24 Feed-Forward Network "Down" (W) | ( ~6M) 5947392 | 2112 x 2816 x 1 x 1 | F16 | 16.0000 | | 343 | blk.24.ffn_gate.weight | Block 24 Feed-Forward Network "Gate" (W) | ( ~6M) 5947392 | 2816 x 2112 x 1 x 1 | F16 | 16.0000 | | 344 | blk.24.ffn_up.weight | Block 24 Feed-Forward Network "Up" (W) | ( ~6M) 5947392 | 2816 x 2112 x 1 x 1 | F16 | 16.0000 | | 345 | blk.24.post_attention_norm.weight | Block 24 Post_Attention_Norm (W) | ( ~3K) 2816 | 2816 x 1 x 1 x 1 | F32 | 32.0000 | | 346 | blk.24.post_ffw_norm.weight | Block 24 Post_Ffw_Norm (W) | ( ~3K) 2816 | 2816 x 1 x 1 x 1 | F32 | 32.0000 | | 347 | blk.24.post_ffw_norm_1.weight | Block 24 Post_Ffw_Norm_1 (W) | ( ~3K) 2816 | 2816 x 1 x 1 x 1 | F32 | 32.0000 | | 348 | blk.24.post_ffw_norm_2.weight | Block 24 Post_Ffw_Norm_2 (W) | ( ~3K) 2816 | 2816 x 1 x 1 x 1 | F32 | 32.0000 | | 349 | blk.24.ffn_norm.weight | Block 24 Feed-Forward Network Normalization (W) | ( ~3K) 2816 | 2816 x 1 x 1 x 1 | F32 | 32.0000 | | 350 | blk.24.pre_ffw_norm_2.weight | Block 24 Pre_Ffw_Norm_2 (W) | ( ~3K) 2816 | 2816 x 1 x 1 x 1 | F32 | 32.0000 | | 351 | blk.24.ffn_down_exps.scale | Block 24 Ffn_Down_Exps Scale | ( 128) 128 | 128 x 1 x 1 x 1 | F32 | 32.0000 | | 352 | blk.24.ffn_gate_inp.weight | Block 24 Expert-Routing Layer For The Feed-Forward Network In Mixture Of Expert Models (W) | (~360K) 360448 | 2816 x 128 x 1 x 1 | F32 | 32.0000 | | 353 | blk.24.ffn_gate_inp.scale | Block 24 Expert-Routing Layer For The Feed-Forward Network In Mixture Of Expert Models Scale | ( ~3K) 2816 | 2816 x 1 x 1 x 1 | F32 | 32.0000 | | 354 | blk.24.attn_k_norm.weight | Block 24 Attn_K_Norm (W) | ( 256) 256 | 256 x 1 x 1 x 1 | F32 | 32.0000 | | 355 | blk.24.attn_k.weight | Block 24 Attention Key (W) | ( ~6M) 5767168 | 2816 x 2048 x 1 x 1 | F16 | 16.0000 | | 356 | blk.24.attn_output.weight | Block 24 Attention Output (W) | ( ~12M) 11534336 | 4096 x 2816 x 1 x 1 | F16 | 16.0000 | | 357 | blk.24.attn_q_norm.weight | Block 24 Attn_Q_Norm (W) | ( 256) 256 | 256 x 1 x 1 x 1 | F32 | 32.0000 | | 358 | blk.24.attn_q.weight | Block 24 Attention Query (W) | ( ~12M) 11534336 | 2816 x 4096 x 1 x 1 | F16 | 16.0000 | | 359 | blk.24.attn_v.weight | Block 24 Attention Value (W) | ( ~6M) 5767168 | 2816 x 2048 x 1 x 1 | F16 | 16.0000 | - Total elements in blk.24: (~814M) 814094977 - Percentage of total elements: 3.23% - Bits per Weight (BPW) for blk.24: 16.0075 bits ### Block 25 Tensor Group : ~814M Elements | T_ID | Tensor Layer Name | Human Friendly Tensor Layer Name | Elements | Shape | Type | BPW | | ---: | :-------------------------------- | :------------------------------------------------------------------------------------------- | :---------------- | :-------------------- | :--- | ------: | | 360 | blk.25.ffn_down_exps.weight | Block 25 Ffn_Down_Exps (W) | (~254M) 253755392 | 704 x 2816 x 128 x 1 | F16 | 16.0000 | | 361 | blk.25.ffn_gate_up_exps.weight | Block 25 Ffn_Gate_Up_Exps (W) | (~508M) 507510784 | 2816 x 1408 x 128 x 1 | F16 | 16.0000 | | 362 | blk.25.attn_norm.weight | Block 25 Attention Normalization (W) | ( ~3K) 2816 | 2816 x 1 x 1 x 1 | F32 | 32.0000 | | 363 | blk.25.layer_output_scale.weight | Block 25 Layer_Output_Scale (W) | ( 1) 1 | 1 x 1 x 1 x 1 | F32 | 32.0000 | | 364 | blk.25.ffn_down.weight | Block 25 Feed-Forward Network "Down" (W) | ( ~6M) 5947392 | 2112 x 2816 x 1 x 1 | F16 | 16.0000 | | 365 | blk.25.ffn_gate.weight | Block 25 Feed-Forward Network "Gate" (W) | ( ~6M) 5947392 | 2816 x 2112 x 1 x 1 | F16 | 16.0000 | | 366 | blk.25.ffn_up.weight | Block 25 Feed-Forward Network "Up" (W) | ( ~6M) 5947392 | 2816 x 2112 x 1 x 1 | F16 | 16.0000 | | 367 | blk.25.post_attention_norm.weight | Block 25 Post_Attention_Norm (W) | ( ~3K) 2816 | 2816 x 1 x 1 x 1 | F32 | 32.0000 | | 368 | blk.25.post_ffw_norm.weight | Block 25 Post_Ffw_Norm (W) | ( ~3K) 2816 | 2816 x 1 x 1 x 1 | F32 | 32.0000 | | 369 | blk.25.post_ffw_norm_1.weight | Block 25 Post_Ffw_Norm_1 (W) | ( ~3K) 2816 | 2816 x 1 x 1 x 1 | F32 | 32.0000 | | 370 | blk.25.post_ffw_norm_2.weight | Block 25 Post_Ffw_Norm_2 (W) | ( ~3K) 2816 | 2816 x 1 x 1 x 1 | F32 | 32.0000 | | 371 | blk.25.ffn_norm.weight | Block 25 Feed-Forward Network Normalization (W) | ( ~3K) 2816 | 2816 x 1 x 1 x 1 | F32 | 32.0000 | | 372 | blk.25.pre_ffw_norm_2.weight | Block 25 Pre_Ffw_Norm_2 (W) | ( ~3K) 2816 | 2816 x 1 x 1 x 1 | F32 | 32.0000 | | 373 | blk.25.ffn_down_exps.scale | Block 25 Ffn_Down_Exps Scale | ( 128) 128 | 128 x 1 x 1 x 1 | F32 | 32.0000 | | 374 | blk.25.ffn_gate_inp.weight | Block 25 Expert-Routing Layer For The Feed-Forward Network In Mixture Of Expert Models (W) | (~360K) 360448 | 2816 x 128 x 1 x 1 | F32 | 32.0000 | | 375 | blk.25.ffn_gate_inp.scale | Block 25 Expert-Routing Layer For The Feed-Forward Network In Mixture Of Expert Models Scale | ( ~3K) 2816 | 2816 x 1 x 1 x 1 | F32 | 32.0000 | | 376 | blk.25.attn_k_norm.weight | Block 25 Attn_K_Norm (W) | ( 256) 256 | 256 x 1 x 1 x 1 | F32 | 32.0000 | | 377 | blk.25.attn_k.weight | Block 25 Attention Key (W) | ( ~6M) 5767168 | 2816 x 2048 x 1 x 1 | F16 | 16.0000 | | 378 | blk.25.attn_output.weight | Block 25 Attention Output (W) | ( ~12M) 11534336 | 4096 x 2816 x 1 x 1 | F16 | 16.0000 | | 379 | blk.25.attn_q_norm.weight | Block 25 Attn_Q_Norm (W) | ( 256) 256 | 256 x 1 x 1 x 1 | F32 | 32.0000 | | 380 | blk.25.attn_q.weight | Block 25 Attention Query (W) | ( ~12M) 11534336 | 2816 x 4096 x 1 x 1 | F16 | 16.0000 | | 381 | blk.25.attn_v.weight | Block 25 Attention Value (W) | ( ~6M) 5767168 | 2816 x 2048 x 1 x 1 | F16 | 16.0000 | - Total elements in blk.25: (~814M) 814094977 - Percentage of total elements: 3.23% - Bits per Weight (BPW) for blk.25: 16.0075 bits ### Block 26 Tensor Group : ~814M Elements | T_ID | Tensor Layer Name | Human Friendly Tensor Layer Name | Elements | Shape | Type | BPW | | ---: | :-------------------------------- | :------------------------------------------------------------------------------------------- | :---------------- | :-------------------- | :--- | ------: | | 382 | blk.26.ffn_down_exps.weight | Block 26 Ffn_Down_Exps (W) | (~254M) 253755392 | 704 x 2816 x 128 x 1 | F16 | 16.0000 | | 383 | blk.26.ffn_gate_up_exps.weight | Block 26 Ffn_Gate_Up_Exps (W) | (~508M) 507510784 | 2816 x 1408 x 128 x 1 | F16 | 16.0000 | | 384 | blk.26.attn_norm.weight | Block 26 Attention Normalization (W) | ( ~3K) 2816 | 2816 x 1 x 1 x 1 | F32 | 32.0000 | | 385 | blk.26.layer_output_scale.weight | Block 26 Layer_Output_Scale (W) | ( 1) 1 | 1 x 1 x 1 x 1 | F32 | 32.0000 | | 386 | blk.26.ffn_down.weight | Block 26 Feed-Forward Network "Down" (W) | ( ~6M) 5947392 | 2112 x 2816 x 1 x 1 | F16 | 16.0000 | | 387 | blk.26.ffn_gate.weight | Block 26 Feed-Forward Network "Gate" (W) | ( ~6M) 5947392 | 2816 x 2112 x 1 x 1 | F16 | 16.0000 | | 388 | blk.26.ffn_up.weight | Block 26 Feed-Forward Network "Up" (W) | ( ~6M) 5947392 | 2816 x 2112 x 1 x 1 | F16 | 16.0000 | | 389 | blk.26.post_attention_norm.weight | Block 26 Post_Attention_Norm (W) | ( ~3K) 2816 | 2816 x 1 x 1 x 1 | F32 | 32.0000 | | 390 | blk.26.post_ffw_norm.weight | Block 26 Post_Ffw_Norm (W) | ( ~3K) 2816 | 2816 x 1 x 1 x 1 | F32 | 32.0000 | | 391 | blk.26.post_ffw_norm_1.weight | Block 26 Post_Ffw_Norm_1 (W) | ( ~3K) 2816 | 2816 x 1 x 1 x 1 | F32 | 32.0000 | | 392 | blk.26.post_ffw_norm_2.weight | Block 26 Post_Ffw_Norm_2 (W) | ( ~3K) 2816 | 2816 x 1 x 1 x 1 | F32 | 32.0000 | | 393 | blk.26.ffn_norm.weight | Block 26 Feed-Forward Network Normalization (W) | ( ~3K) 2816 | 2816 x 1 x 1 x 1 | F32 | 32.0000 | | 394 | blk.26.pre_ffw_norm_2.weight | Block 26 Pre_Ffw_Norm_2 (W) | ( ~3K) 2816 | 2816 x 1 x 1 x 1 | F32 | 32.0000 | | 395 | blk.26.ffn_down_exps.scale | Block 26 Ffn_Down_Exps Scale | ( 128) 128 | 128 x 1 x 1 x 1 | F32 | 32.0000 | | 396 | blk.26.ffn_gate_inp.weight | Block 26 Expert-Routing Layer For The Feed-Forward Network In Mixture Of Expert Models (W) | (~360K) 360448 | 2816 x 128 x 1 x 1 | F32 | 32.0000 | | 397 | blk.26.ffn_gate_inp.scale | Block 26 Expert-Routing Layer For The Feed-Forward Network In Mixture Of Expert Models Scale | ( ~3K) 2816 | 2816 x 1 x 1 x 1 | F32 | 32.0000 | | 398 | blk.26.attn_k_norm.weight | Block 26 Attn_K_Norm (W) | ( 256) 256 | 256 x 1 x 1 x 1 | F32 | 32.0000 | | 399 | blk.26.attn_k.weight | Block 26 Attention Key (W) | ( ~6M) 5767168 | 2816 x 2048 x 1 x 1 | F16 | 16.0000 | | 400 | blk.26.attn_output.weight | Block 26 Attention Output (W) | ( ~12M) 11534336 | 4096 x 2816 x 1 x 1 | F16 | 16.0000 | | 401 | blk.26.attn_q_norm.weight | Block 26 Attn_Q_Norm (W) | ( 256) 256 | 256 x 1 x 1 x 1 | F32 | 32.0000 | | 402 | blk.26.attn_q.weight | Block 26 Attention Query (W) | ( ~12M) 11534336 | 2816 x 4096 x 1 x 1 | F16 | 16.0000 | | 403 | blk.26.attn_v.weight | Block 26 Attention Value (W) | ( ~6M) 5767168 | 2816 x 2048 x 1 x 1 | F16 | 16.0000 | - Total elements in blk.26: (~814M) 814094977 - Percentage of total elements: 3.23% - Bits per Weight (BPW) for blk.26: 16.0075 bits ### Block 27 Tensor Group : ~814M Elements | T_ID | Tensor Layer Name | Human Friendly Tensor Layer Name | Elements | Shape | Type | BPW | | ---: | :-------------------------------- | :------------------------------------------------------------------------------------------- | :---------------- | :-------------------- | :--- | ------: | | 404 | blk.27.ffn_down_exps.weight | Block 27 Ffn_Down_Exps (W) | (~254M) 253755392 | 704 x 2816 x 128 x 1 | F16 | 16.0000 | | 405 | blk.27.ffn_gate_up_exps.weight | Block 27 Ffn_Gate_Up_Exps (W) | (~508M) 507510784 | 2816 x 1408 x 128 x 1 | F16 | 16.0000 | | 406 | blk.27.attn_norm.weight | Block 27 Attention Normalization (W) | ( ~3K) 2816 | 2816 x 1 x 1 x 1 | F32 | 32.0000 | | 407 | blk.27.layer_output_scale.weight | Block 27 Layer_Output_Scale (W) | ( 1) 1 | 1 x 1 x 1 x 1 | F32 | 32.0000 | | 408 | blk.27.ffn_down.weight | Block 27 Feed-Forward Network "Down" (W) | ( ~6M) 5947392 | 2112 x 2816 x 1 x 1 | F16 | 16.0000 | | 409 | blk.27.ffn_gate.weight | Block 27 Feed-Forward Network "Gate" (W) | ( ~6M) 5947392 | 2816 x 2112 x 1 x 1 | F16 | 16.0000 | | 410 | blk.27.ffn_up.weight | Block 27 Feed-Forward Network "Up" (W) | ( ~6M) 5947392 | 2816 x 2112 x 1 x 1 | F16 | 16.0000 | | 411 | blk.27.post_attention_norm.weight | Block 27 Post_Attention_Norm (W) | ( ~3K) 2816 | 2816 x 1 x 1 x 1 | F32 | 32.0000 | | 412 | blk.27.post_ffw_norm.weight | Block 27 Post_Ffw_Norm (W) | ( ~3K) 2816 | 2816 x 1 x 1 x 1 | F32 | 32.0000 | | 413 | blk.27.post_ffw_norm_1.weight | Block 27 Post_Ffw_Norm_1 (W) | ( ~3K) 2816 | 2816 x 1 x 1 x 1 | F32 | 32.0000 | | 414 | blk.27.post_ffw_norm_2.weight | Block 27 Post_Ffw_Norm_2 (W) | ( ~3K) 2816 | 2816 x 1 x 1 x 1 | F32 | 32.0000 | | 415 | blk.27.ffn_norm.weight | Block 27 Feed-Forward Network Normalization (W) | ( ~3K) 2816 | 2816 x 1 x 1 x 1 | F32 | 32.0000 | | 416 | blk.27.pre_ffw_norm_2.weight | Block 27 Pre_Ffw_Norm_2 (W) | ( ~3K) 2816 | 2816 x 1 x 1 x 1 | F32 | 32.0000 | | 417 | blk.27.ffn_down_exps.scale | Block 27 Ffn_Down_Exps Scale | ( 128) 128 | 128 x 1 x 1 x 1 | F32 | 32.0000 | | 418 | blk.27.ffn_gate_inp.weight | Block 27 Expert-Routing Layer For The Feed-Forward Network In Mixture Of Expert Models (W) | (~360K) 360448 | 2816 x 128 x 1 x 1 | F32 | 32.0000 | | 419 | blk.27.ffn_gate_inp.scale | Block 27 Expert-Routing Layer For The Feed-Forward Network In Mixture Of Expert Models Scale | ( ~3K) 2816 | 2816 x 1 x 1 x 1 | F32 | 32.0000 | | 420 | blk.27.attn_k_norm.weight | Block 27 Attn_K_Norm (W) | ( 256) 256 | 256 x 1 x 1 x 1 | F32 | 32.0000 | | 421 | blk.27.attn_k.weight | Block 27 Attention Key (W) | ( ~6M) 5767168 | 2816 x 2048 x 1 x 1 | F16 | 16.0000 | | 422 | blk.27.attn_output.weight | Block 27 Attention Output (W) | ( ~12M) 11534336 | 4096 x 2816 x 1 x 1 | F16 | 16.0000 | | 423 | blk.27.attn_q_norm.weight | Block 27 Attn_Q_Norm (W) | ( 256) 256 | 256 x 1 x 1 x 1 | F32 | 32.0000 | | 424 | blk.27.attn_q.weight | Block 27 Attention Query (W) | ( ~12M) 11534336 | 2816 x 4096 x 1 x 1 | F16 | 16.0000 | | 425 | blk.27.attn_v.weight | Block 27 Attention Value (W) | ( ~6M) 5767168 | 2816 x 2048 x 1 x 1 | F16 | 16.0000 | - Total elements in blk.27: (~814M) 814094977 - Percentage of total elements: 3.23% - Bits per Weight (BPW) for blk.27: 16.0075 bits ### Block 28 Tensor Group : ~814M Elements | T_ID | Tensor Layer Name | Human Friendly Tensor Layer Name | Elements | Shape | Type | BPW | | ---: | :-------------------------------- | :------------------------------------------------------------------------------------------- | :---------------- | :-------------------- | :--- | ------: | | 426 | blk.28.ffn_down_exps.weight | Block 28 Ffn_Down_Exps (W) | (~254M) 253755392 | 704 x 2816 x 128 x 1 | F16 | 16.0000 | | 427 | blk.28.ffn_gate_up_exps.weight | Block 28 Ffn_Gate_Up_Exps (W) | (~508M) 507510784 | 2816 x 1408 x 128 x 1 | F16 | 16.0000 | | 428 | blk.28.attn_norm.weight | Block 28 Attention Normalization (W) | ( ~3K) 2816 | 2816 x 1 x 1 x 1 | F32 | 32.0000 | | 429 | blk.28.layer_output_scale.weight | Block 28 Layer_Output_Scale (W) | ( 1) 1 | 1 x 1 x 1 x 1 | F32 | 32.0000 | | 430 | blk.28.ffn_down.weight | Block 28 Feed-Forward Network "Down" (W) | ( ~6M) 5947392 | 2112 x 2816 x 1 x 1 | F16 | 16.0000 | | 431 | blk.28.ffn_gate.weight | Block 28 Feed-Forward Network "Gate" (W) | ( ~6M) 5947392 | 2816 x 2112 x 1 x 1 | F16 | 16.0000 | | 432 | blk.28.ffn_up.weight | Block 28 Feed-Forward Network "Up" (W) | ( ~6M) 5947392 | 2816 x 2112 x 1 x 1 | F16 | 16.0000 | | 433 | blk.28.post_attention_norm.weight | Block 28 Post_Attention_Norm (W) | ( ~3K) 2816 | 2816 x 1 x 1 x 1 | F32 | 32.0000 | | 434 | blk.28.post_ffw_norm.weight | Block 28 Post_Ffw_Norm (W) | ( ~3K) 2816 | 2816 x 1 x 1 x 1 | F32 | 32.0000 | | 435 | blk.28.post_ffw_norm_1.weight | Block 28 Post_Ffw_Norm_1 (W) | ( ~3K) 2816 | 2816 x 1 x 1 x 1 | F32 | 32.0000 | | 436 | blk.28.post_ffw_norm_2.weight | Block 28 Post_Ffw_Norm_2 (W) | ( ~3K) 2816 | 2816 x 1 x 1 x 1 | F32 | 32.0000 | | 437 | blk.28.ffn_norm.weight | Block 28 Feed-Forward Network Normalization (W) | ( ~3K) 2816 | 2816 x 1 x 1 x 1 | F32 | 32.0000 | | 438 | blk.28.pre_ffw_norm_2.weight | Block 28 Pre_Ffw_Norm_2 (W) | ( ~3K) 2816 | 2816 x 1 x 1 x 1 | F32 | 32.0000 | | 439 | blk.28.ffn_down_exps.scale | Block 28 Ffn_Down_Exps Scale | ( 128) 128 | 128 x 1 x 1 x 1 | F32 | 32.0000 | | 440 | blk.28.ffn_gate_inp.weight | Block 28 Expert-Routing Layer For The Feed-Forward Network In Mixture Of Expert Models (W) | (~360K) 360448 | 2816 x 128 x 1 x 1 | F32 | 32.0000 | | 441 | blk.28.ffn_gate_inp.scale | Block 28 Expert-Routing Layer For The Feed-Forward Network In Mixture Of Expert Models Scale | ( ~3K) 2816 | 2816 x 1 x 1 x 1 | F32 | 32.0000 | | 442 | blk.28.attn_k_norm.weight | Block 28 Attn_K_Norm (W) | ( 256) 256 | 256 x 1 x 1 x 1 | F32 | 32.0000 | | 443 | blk.28.attn_k.weight | Block 28 Attention Key (W) | ( ~6M) 5767168 | 2816 x 2048 x 1 x 1 | F16 | 16.0000 | | 444 | blk.28.attn_output.weight | Block 28 Attention Output (W) | ( ~12M) 11534336 | 4096 x 2816 x 1 x 1 | F16 | 16.0000 | | 445 | blk.28.attn_q_norm.weight | Block 28 Attn_Q_Norm (W) | ( 256) 256 | 256 x 1 x 1 x 1 | F32 | 32.0000 | | 446 | blk.28.attn_q.weight | Block 28 Attention Query (W) | ( ~12M) 11534336 | 2816 x 4096 x 1 x 1 | F16 | 16.0000 | | 447 | blk.28.attn_v.weight | Block 28 Attention Value (W) | ( ~6M) 5767168 | 2816 x 2048 x 1 x 1 | F16 | 16.0000 | - Total elements in blk.28: (~814M) 814094977 - Percentage of total elements: 3.23% - Bits per Weight (BPW) for blk.28: 16.0075 bits ### Block 29 Tensor Group : ~829M Elements | T_ID | Tensor Layer Name | Human Friendly Tensor Layer Name | Elements | Shape | Type | BPW | | ---: | :-------------------------------- | :------------------------------------------------------------------------------------------- | :---------------- | :-------------------- | :--- | ------: | | 448 | blk.29.ffn_gate_up_exps.weight | Block 29 Ffn_Gate_Up_Exps (W) | (~508M) 507510784 | 2816 x 1408 x 128 x 1 | F16 | 16.0000 | | 449 | blk.29.layer_output_scale.weight | Block 29 Layer_Output_Scale (W) | ( 1) 1 | 1 x 1 x 1 x 1 | F32 | 32.0000 | | 450 | blk.29.ffn_down_exps.scale | Block 29 Ffn_Down_Exps Scale | ( 128) 128 | 128 x 1 x 1 x 1 | F32 | 32.0000 | | 451 | blk.29.ffn_gate_inp.scale | Block 29 Expert-Routing Layer For The Feed-Forward Network In Mixture Of Expert Models Scale | ( ~3K) 2816 | 2816 x 1 x 1 x 1 | F32 | 32.0000 | | 452 | blk.29.attn_k_norm.weight | Block 29 Attn_K_Norm (W) | ( 512) 512 | 512 x 1 x 1 x 1 | F32 | 32.0000 | | 453 | blk.29.attn_k.weight | Block 29 Attention Key (W) | ( ~3M) 2883584 | 2816 x 1024 x 1 x 1 | F16 | 16.0000 | | 454 | blk.29.attn_output.weight | Block 29 Attention Output (W) | ( ~23M) 23068672 | 8192 x 2816 x 1 x 1 | F16 | 16.0000 | | 455 | blk.29.attn_q_norm.weight | Block 29 Attn_Q_Norm (W) | ( 512) 512 | 512 x 1 x 1 x 1 | F32 | 32.0000 | | 456 | blk.29.attn_q.weight | Block 29 Attention Query (W) | ( ~23M) 23068672 | 2816 x 8192 x 1 x 1 | F16 | 16.0000 | | 635 | blk.29.ffn_down_exps.weight | Block 29 Ffn_Down_Exps (W) | (~254M) 253755392 | 704 x 2816 x 128 x 1 | F16 | 16.0000 | | 636 | blk.29.attn_norm.weight | Block 29 Attention Normalization (W) | ( ~3K) 2816 | 2816 x 1 x 1 x 1 | F32 | 32.0000 | | 637 | blk.29.ffn_down.weight | Block 29 Feed-Forward Network "Down" (W) | ( ~6M) 5947392 | 2112 x 2816 x 1 x 1 | F16 | 16.0000 | | 638 | blk.29.ffn_gate.weight | Block 29 Feed-Forward Network "Gate" (W) | ( ~6M) 5947392 | 2816 x 2112 x 1 x 1 | F16 | 16.0000 | | 639 | blk.29.ffn_up.weight | Block 29 Feed-Forward Network "Up" (W) | ( ~6M) 5947392 | 2816 x 2112 x 1 x 1 | F16 | 16.0000 | | 640 | blk.29.post_attention_norm.weight | Block 29 Post_Attention_Norm (W) | ( ~3K) 2816 | 2816 x 1 x 1 x 1 | F32 | 32.0000 | | 641 | blk.29.post_ffw_norm.weight | Block 29 Post_Ffw_Norm (W) | ( ~3K) 2816 | 2816 x 1 x 1 x 1 | F32 | 32.0000 | | 642 | blk.29.post_ffw_norm_1.weight | Block 29 Post_Ffw_Norm_1 (W) | ( ~3K) 2816 | 2816 x 1 x 1 x 1 | F32 | 32.0000 | | 643 | blk.29.post_ffw_norm_2.weight | Block 29 Post_Ffw_Norm_2 (W) | ( ~3K) 2816 | 2816 x 1 x 1 x 1 | F32 | 32.0000 | | 644 | blk.29.ffn_norm.weight | Block 29 Feed-Forward Network Normalization (W) | ( ~3K) 2816 | 2816 x 1 x 1 x 1 | F32 | 32.0000 | | 645 | blk.29.pre_ffw_norm_2.weight | Block 29 Pre_Ffw_Norm_2 (W) | ( ~3K) 2816 | 2816 x 1 x 1 x 1 | F32 | 32.0000 | | 646 | blk.29.ffn_gate_inp.weight | Block 29 Expert-Routing Layer For The Feed-Forward Network In Mixture Of Expert Models (W) | (~360K) 360448 | 2816 x 128 x 1 x 1 | F32 | 32.0000 | - Total elements in blk.29: (~829M) 828513409 - Percentage of total elements: 3.28% - Bits per Weight (BPW) for blk.29: 16.0074 bits ### Block 3 Tensor Group : ~814M Elements | T_ID | Tensor Layer Name | Human Friendly Tensor Layer Name | Elements | Shape | Type | BPW | | ---: | :------------------------------- | :------------------------------------------------------------------------------------------ | :---------------- | :-------------------- | :--- | ------: | | 457 | blk.3.ffn_down_exps.weight | Block 3 Ffn_Down_Exps (W) | (~254M) 253755392 | 704 x 2816 x 128 x 1 | F16 | 16.0000 | | 458 | blk.3.ffn_gate_up_exps.weight | Block 3 Ffn_Gate_Up_Exps (W) | (~508M) 507510784 | 2816 x 1408 x 128 x 1 | F16 | 16.0000 | | 459 | blk.3.attn_norm.weight | Block 3 Attention Normalization (W) | ( ~3K) 2816 | 2816 x 1 x 1 x 1 | F32 | 32.0000 | | 460 | blk.3.layer_output_scale.weight | Block 3 Layer_Output_Scale (W) | ( 1) 1 | 1 x 1 x 1 x 1 | F32 | 32.0000 | | 461 | blk.3.ffn_down.weight | Block 3 Feed-Forward Network "Down" (W) | ( ~6M) 5947392 | 2112 x 2816 x 1 x 1 | F16 | 16.0000 | | 462 | blk.3.ffn_gate.weight | Block 3 Feed-Forward Network "Gate" (W) | ( ~6M) 5947392 | 2816 x 2112 x 1 x 1 | F16 | 16.0000 | | 463 | blk.3.ffn_up.weight | Block 3 Feed-Forward Network "Up" (W) | ( ~6M) 5947392 | 2816 x 2112 x 1 x 1 | F16 | 16.0000 | | 464 | blk.3.post_attention_norm.weight | Block 3 Post_Attention_Norm (W) | ( ~3K) 2816 | 2816 x 1 x 1 x 1 | F32 | 32.0000 | | 465 | blk.3.post_ffw_norm.weight | Block 3 Post_Ffw_Norm (W) | ( ~3K) 2816 | 2816 x 1 x 1 x 1 | F32 | 32.0000 | | 466 | blk.3.post_ffw_norm_1.weight | Block 3 Post_Ffw_Norm_1 (W) | ( ~3K) 2816 | 2816 x 1 x 1 x 1 | F32 | 32.0000 | | 467 | blk.3.post_ffw_norm_2.weight | Block 3 Post_Ffw_Norm_2 (W) | ( ~3K) 2816 | 2816 x 1 x 1 x 1 | F32 | 32.0000 | | 468 | blk.3.ffn_norm.weight | Block 3 Feed-Forward Network Normalization (W) | ( ~3K) 2816 | 2816 x 1 x 1 x 1 | F32 | 32.0000 | | 469 | blk.3.pre_ffw_norm_2.weight | Block 3 Pre_Ffw_Norm_2 (W) | ( ~3K) 2816 | 2816 x 1 x 1 x 1 | F32 | 32.0000 | | 470 | blk.3.ffn_down_exps.scale | Block 3 Ffn_Down_Exps Scale | ( 128) 128 | 128 x 1 x 1 x 1 | F32 | 32.0000 | | 471 | blk.3.ffn_gate_inp.weight | Block 3 Expert-Routing Layer For The Feed-Forward Network In Mixture Of Expert Models (W) | (~360K) 360448 | 2816 x 128 x 1 x 1 | F32 | 32.0000 | | 472 | blk.3.ffn_gate_inp.scale | Block 3 Expert-Routing Layer For The Feed-Forward Network In Mixture Of Expert Models Scale | ( ~3K) 2816 | 2816 x 1 x 1 x 1 | F32 | 32.0000 | | 473 | blk.3.attn_k_norm.weight | Block 3 Attn_K_Norm (W) | ( 256) 256 | 256 x 1 x 1 x 1 | F32 | 32.0000 | | 474 | blk.3.attn_k.weight | Block 3 Attention Key (W) | ( ~6M) 5767168 | 2816 x 2048 x 1 x 1 | F16 | 16.0000 | | 475 | blk.3.attn_output.weight | Block 3 Attention Output (W) | ( ~12M) 11534336 | 4096 x 2816 x 1 x 1 | F16 | 16.0000 | | 476 | blk.3.attn_q_norm.weight | Block 3 Attn_Q_Norm (W) | ( 256) 256 | 256 x 1 x 1 x 1 | F32 | 32.0000 | | 477 | blk.3.attn_q.weight | Block 3 Attention Query (W) | ( ~12M) 11534336 | 2816 x 4096 x 1 x 1 | F16 | 16.0000 | | 478 | blk.3.attn_v.weight | Block 3 Attention Value (W) | ( ~6M) 5767168 | 2816 x 2048 x 1 x 1 | F16 | 16.0000 | - Total elements in blk.3: (~814M) 814094977 - Percentage of total elements: 3.23% - Bits per Weight (BPW) for blk.3: 16.0075 bits ### Block 4 Tensor Group : ~814M Elements | T_ID | Tensor Layer Name | Human Friendly Tensor Layer Name | Elements | Shape | Type | BPW | | ---: | :------------------------------- | :------------------------------------------------------------------------------------------ | :---------------- | :-------------------- | :--- | ------: | | 479 | blk.4.ffn_down_exps.weight | Block 4 Ffn_Down_Exps (W) | (~254M) 253755392 | 704 x 2816 x 128 x 1 | F16 | 16.0000 | | 480 | blk.4.ffn_gate_up_exps.weight | Block 4 Ffn_Gate_Up_Exps (W) | (~508M) 507510784 | 2816 x 1408 x 128 x 1 | F16 | 16.0000 | | 481 | blk.4.attn_norm.weight | Block 4 Attention Normalization (W) | ( ~3K) 2816 | 2816 x 1 x 1 x 1 | F32 | 32.0000 | | 482 | blk.4.layer_output_scale.weight | Block 4 Layer_Output_Scale (W) | ( 1) 1 | 1 x 1 x 1 x 1 | F32 | 32.0000 | | 483 | blk.4.ffn_down.weight | Block 4 Feed-Forward Network "Down" (W) | ( ~6M) 5947392 | 2112 x 2816 x 1 x 1 | F16 | 16.0000 | | 484 | blk.4.ffn_gate.weight | Block 4 Feed-Forward Network "Gate" (W) | ( ~6M) 5947392 | 2816 x 2112 x 1 x 1 | F16 | 16.0000 | | 485 | blk.4.ffn_up.weight | Block 4 Feed-Forward Network "Up" (W) | ( ~6M) 5947392 | 2816 x 2112 x 1 x 1 | F16 | 16.0000 | | 486 | blk.4.post_attention_norm.weight | Block 4 Post_Attention_Norm (W) | ( ~3K) 2816 | 2816 x 1 x 1 x 1 | F32 | 32.0000 | | 487 | blk.4.post_ffw_norm.weight | Block 4 Post_Ffw_Norm (W) | ( ~3K) 2816 | 2816 x 1 x 1 x 1 | F32 | 32.0000 | | 488 | blk.4.post_ffw_norm_1.weight | Block 4 Post_Ffw_Norm_1 (W) | ( ~3K) 2816 | 2816 x 1 x 1 x 1 | F32 | 32.0000 | | 489 | blk.4.post_ffw_norm_2.weight | Block 4 Post_Ffw_Norm_2 (W) | ( ~3K) 2816 | 2816 x 1 x 1 x 1 | F32 | 32.0000 | | 490 | blk.4.ffn_norm.weight | Block 4 Feed-Forward Network Normalization (W) | ( ~3K) 2816 | 2816 x 1 x 1 x 1 | F32 | 32.0000 | | 491 | blk.4.pre_ffw_norm_2.weight | Block 4 Pre_Ffw_Norm_2 (W) | ( ~3K) 2816 | 2816 x 1 x 1 x 1 | F32 | 32.0000 | | 492 | blk.4.ffn_down_exps.scale | Block 4 Ffn_Down_Exps Scale | ( 128) 128 | 128 x 1 x 1 x 1 | F32 | 32.0000 | | 493 | blk.4.ffn_gate_inp.weight | Block 4 Expert-Routing Layer For The Feed-Forward Network In Mixture Of Expert Models (W) | (~360K) 360448 | 2816 x 128 x 1 x 1 | F32 | 32.0000 | | 494 | blk.4.ffn_gate_inp.scale | Block 4 Expert-Routing Layer For The Feed-Forward Network In Mixture Of Expert Models Scale | ( ~3K) 2816 | 2816 x 1 x 1 x 1 | F32 | 32.0000 | | 495 | blk.4.attn_k_norm.weight | Block 4 Attn_K_Norm (W) | ( 256) 256 | 256 x 1 x 1 x 1 | F32 | 32.0000 | | 496 | blk.4.attn_k.weight | Block 4 Attention Key (W) | ( ~6M) 5767168 | 2816 x 2048 x 1 x 1 | F16 | 16.0000 | | 497 | blk.4.attn_output.weight | Block 4 Attention Output (W) | ( ~12M) 11534336 | 4096 x 2816 x 1 x 1 | F16 | 16.0000 | | 498 | blk.4.attn_q_norm.weight | Block 4 Attn_Q_Norm (W) | ( 256) 256 | 256 x 1 x 1 x 1 | F32 | 32.0000 | | 499 | blk.4.attn_q.weight | Block 4 Attention Query (W) | ( ~12M) 11534336 | 2816 x 4096 x 1 x 1 | F16 | 16.0000 | | 500 | blk.4.attn_v.weight | Block 4 Attention Value (W) | ( ~6M) 5767168 | 2816 x 2048 x 1 x 1 | F16 | 16.0000 | - Total elements in blk.4: (~814M) 814094977 - Percentage of total elements: 3.23% - Bits per Weight (BPW) for blk.4: 16.0075 bits ### Block 5 Tensor Group : ~829M Elements | T_ID | Tensor Layer Name | Human Friendly Tensor Layer Name | Elements | Shape | Type | BPW | | ---: | :------------------------------- | :------------------------------------------------------------------------------------------ | :---------------- | :-------------------- | :--- | ------: | | 501 | blk.5.ffn_down_exps.weight | Block 5 Ffn_Down_Exps (W) | (~254M) 253755392 | 704 x 2816 x 128 x 1 | F16 | 16.0000 | | 502 | blk.5.ffn_gate_up_exps.weight | Block 5 Ffn_Gate_Up_Exps (W) | (~508M) 507510784 | 2816 x 1408 x 128 x 1 | F16 | 16.0000 | | 503 | blk.5.layer_output_scale.weight | Block 5 Layer_Output_Scale (W) | ( 1) 1 | 1 x 1 x 1 x 1 | F32 | 32.0000 | | 504 | blk.5.ffn_down_exps.scale | Block 5 Ffn_Down_Exps Scale | ( 128) 128 | 128 x 1 x 1 x 1 | F32 | 32.0000 | | 505 | blk.5.ffn_gate_inp.scale | Block 5 Expert-Routing Layer For The Feed-Forward Network In Mixture Of Expert Models Scale | ( ~3K) 2816 | 2816 x 1 x 1 x 1 | F32 | 32.0000 | | 506 | blk.5.attn_k_norm.weight | Block 5 Attn_K_Norm (W) | ( 512) 512 | 512 x 1 x 1 x 1 | F32 | 32.0000 | | 507 | blk.5.attn_k.weight | Block 5 Attention Key (W) | ( ~3M) 2883584 | 2816 x 1024 x 1 x 1 | F16 | 16.0000 | | 508 | blk.5.attn_output.weight | Block 5 Attention Output (W) | ( ~23M) 23068672 | 8192 x 2816 x 1 x 1 | F16 | 16.0000 | | 509 | blk.5.attn_q_norm.weight | Block 5 Attn_Q_Norm (W) | ( 512) 512 | 512 x 1 x 1 x 1 | F32 | 32.0000 | | 510 | blk.5.attn_q.weight | Block 5 Attention Query (W) | ( ~23M) 23068672 | 2816 x 8192 x 1 x 1 | F16 | 16.0000 | | 647 | blk.5.attn_norm.weight | Block 5 Attention Normalization (W) | ( ~3K) 2816 | 2816 x 1 x 1 x 1 | F32 | 32.0000 | | 648 | blk.5.ffn_down.weight | Block 5 Feed-Forward Network "Down" (W) | ( ~6M) 5947392 | 2112 x 2816 x 1 x 1 | F16 | 16.0000 | | 649 | blk.5.ffn_gate.weight | Block 5 Feed-Forward Network "Gate" (W) | ( ~6M) 5947392 | 2816 x 2112 x 1 x 1 | F16 | 16.0000 | | 650 | blk.5.ffn_up.weight | Block 5 Feed-Forward Network "Up" (W) | ( ~6M) 5947392 | 2816 x 2112 x 1 x 1 | F16 | 16.0000 | | 651 | blk.5.post_attention_norm.weight | Block 5 Post_Attention_Norm (W) | ( ~3K) 2816 | 2816 x 1 x 1 x 1 | F32 | 32.0000 | | 652 | blk.5.post_ffw_norm.weight | Block 5 Post_Ffw_Norm (W) | ( ~3K) 2816 | 2816 x 1 x 1 x 1 | F32 | 32.0000 | | 653 | blk.5.post_ffw_norm_1.weight | Block 5 Post_Ffw_Norm_1 (W) | ( ~3K) 2816 | 2816 x 1 x 1 x 1 | F32 | 32.0000 | | 654 | blk.5.post_ffw_norm_2.weight | Block 5 Post_Ffw_Norm_2 (W) | ( ~3K) 2816 | 2816 x 1 x 1 x 1 | F32 | 32.0000 | | 655 | blk.5.ffn_norm.weight | Block 5 Feed-Forward Network Normalization (W) | ( ~3K) 2816 | 2816 x 1 x 1 x 1 | F32 | 32.0000 | | 656 | blk.5.pre_ffw_norm_2.weight | Block 5 Pre_Ffw_Norm_2 (W) | ( ~3K) 2816 | 2816 x 1 x 1 x 1 | F32 | 32.0000 | | 657 | blk.5.ffn_gate_inp.weight | Block 5 Expert-Routing Layer For The Feed-Forward Network In Mixture Of Expert Models (W) | (~360K) 360448 | 2816 x 128 x 1 x 1 | F32 | 32.0000 | - Total elements in blk.5: (~829M) 828513409 - Percentage of total elements: 3.28% - Bits per Weight (BPW) for blk.5: 16.0074 bits ### Block 6 Tensor Group : ~814M Elements | T_ID | Tensor Layer Name | Human Friendly Tensor Layer Name | Elements | Shape | Type | BPW | | ---: | :------------------------------- | :------------------------------------------------------------------------------------------ | :---------------- | :-------------------- | :--- | ------: | | 511 | blk.6.ffn_down_exps.weight | Block 6 Ffn_Down_Exps (W) | (~254M) 253755392 | 704 x 2816 x 128 x 1 | F16 | 16.0000 | | 512 | blk.6.ffn_gate_up_exps.weight | Block 6 Ffn_Gate_Up_Exps (W) | (~508M) 507510784 | 2816 x 1408 x 128 x 1 | F16 | 16.0000 | | 513 | blk.6.attn_norm.weight | Block 6 Attention Normalization (W) | ( ~3K) 2816 | 2816 x 1 x 1 x 1 | F32 | 32.0000 | | 514 | blk.6.layer_output_scale.weight | Block 6 Layer_Output_Scale (W) | ( 1) 1 | 1 x 1 x 1 x 1 | F32 | 32.0000 | | 515 | blk.6.ffn_down.weight | Block 6 Feed-Forward Network "Down" (W) | ( ~6M) 5947392 | 2112 x 2816 x 1 x 1 | F16 | 16.0000 | | 516 | blk.6.ffn_gate.weight | Block 6 Feed-Forward Network "Gate" (W) | ( ~6M) 5947392 | 2816 x 2112 x 1 x 1 | F16 | 16.0000 | | 517 | blk.6.ffn_up.weight | Block 6 Feed-Forward Network "Up" (W) | ( ~6M) 5947392 | 2816 x 2112 x 1 x 1 | F16 | 16.0000 | | 518 | blk.6.post_attention_norm.weight | Block 6 Post_Attention_Norm (W) | ( ~3K) 2816 | 2816 x 1 x 1 x 1 | F32 | 32.0000 | | 519 | blk.6.post_ffw_norm.weight | Block 6 Post_Ffw_Norm (W) | ( ~3K) 2816 | 2816 x 1 x 1 x 1 | F32 | 32.0000 | | 520 | blk.6.post_ffw_norm_1.weight | Block 6 Post_Ffw_Norm_1 (W) | ( ~3K) 2816 | 2816 x 1 x 1 x 1 | F32 | 32.0000 | | 521 | blk.6.post_ffw_norm_2.weight | Block 6 Post_Ffw_Norm_2 (W) | ( ~3K) 2816 | 2816 x 1 x 1 x 1 | F32 | 32.0000 | | 522 | blk.6.ffn_norm.weight | Block 6 Feed-Forward Network Normalization (W) | ( ~3K) 2816 | 2816 x 1 x 1 x 1 | F32 | 32.0000 | | 523 | blk.6.pre_ffw_norm_2.weight | Block 6 Pre_Ffw_Norm_2 (W) | ( ~3K) 2816 | 2816 x 1 x 1 x 1 | F32 | 32.0000 | | 524 | blk.6.ffn_down_exps.scale | Block 6 Ffn_Down_Exps Scale | ( 128) 128 | 128 x 1 x 1 x 1 | F32 | 32.0000 | | 525 | blk.6.ffn_gate_inp.weight | Block 6 Expert-Routing Layer For The Feed-Forward Network In Mixture Of Expert Models (W) | (~360K) 360448 | 2816 x 128 x 1 x 1 | F32 | 32.0000 | | 526 | blk.6.ffn_gate_inp.scale | Block 6 Expert-Routing Layer For The Feed-Forward Network In Mixture Of Expert Models Scale | ( ~3K) 2816 | 2816 x 1 x 1 x 1 | F32 | 32.0000 | | 527 | blk.6.attn_k_norm.weight | Block 6 Attn_K_Norm (W) | ( 256) 256 | 256 x 1 x 1 x 1 | F32 | 32.0000 | | 528 | blk.6.attn_k.weight | Block 6 Attention Key (W) | ( ~6M) 5767168 | 2816 x 2048 x 1 x 1 | F16 | 16.0000 | | 529 | blk.6.attn_output.weight | Block 6 Attention Output (W) | ( ~12M) 11534336 | 4096 x 2816 x 1 x 1 | F16 | 16.0000 | | 530 | blk.6.attn_q_norm.weight | Block 6 Attn_Q_Norm (W) | ( 256) 256 | 256 x 1 x 1 x 1 | F32 | 32.0000 | | 531 | blk.6.attn_q.weight | Block 6 Attention Query (W) | ( ~12M) 11534336 | 2816 x 4096 x 1 x 1 | F16 | 16.0000 | | 532 | blk.6.attn_v.weight | Block 6 Attention Value (W) | ( ~6M) 5767168 | 2816 x 2048 x 1 x 1 | F16 | 16.0000 | - Total elements in blk.6: (~814M) 814094977 - Percentage of total elements: 3.23% - Bits per Weight (BPW) for blk.6: 16.0075 bits ### Block 7 Tensor Group : ~814M Elements | T_ID | Tensor Layer Name | Human Friendly Tensor Layer Name | Elements | Shape | Type | BPW | | ---: | :------------------------------- | :------------------------------------------------------------------------------------------ | :---------------- | :-------------------- | :--- | ------: | | 533 | blk.7.ffn_down_exps.weight | Block 7 Ffn_Down_Exps (W) | (~254M) 253755392 | 704 x 2816 x 128 x 1 | F16 | 16.0000 | | 534 | blk.7.ffn_gate_up_exps.weight | Block 7 Ffn_Gate_Up_Exps (W) | (~508M) 507510784 | 2816 x 1408 x 128 x 1 | F16 | 16.0000 | | 535 | blk.7.attn_norm.weight | Block 7 Attention Normalization (W) | ( ~3K) 2816 | 2816 x 1 x 1 x 1 | F32 | 32.0000 | | 536 | blk.7.layer_output_scale.weight | Block 7 Layer_Output_Scale (W) | ( 1) 1 | 1 x 1 x 1 x 1 | F32 | 32.0000 | | 537 | blk.7.ffn_down.weight | Block 7 Feed-Forward Network "Down" (W) | ( ~6M) 5947392 | 2112 x 2816 x 1 x 1 | F16 | 16.0000 | | 538 | blk.7.ffn_gate.weight | Block 7 Feed-Forward Network "Gate" (W) | ( ~6M) 5947392 | 2816 x 2112 x 1 x 1 | F16 | 16.0000 | | 539 | blk.7.ffn_up.weight | Block 7 Feed-Forward Network "Up" (W) | ( ~6M) 5947392 | 2816 x 2112 x 1 x 1 | F16 | 16.0000 | | 540 | blk.7.post_attention_norm.weight | Block 7 Post_Attention_Norm (W) | ( ~3K) 2816 | 2816 x 1 x 1 x 1 | F32 | 32.0000 | | 541 | blk.7.post_ffw_norm.weight | Block 7 Post_Ffw_Norm (W) | ( ~3K) 2816 | 2816 x 1 x 1 x 1 | F32 | 32.0000 | | 542 | blk.7.post_ffw_norm_1.weight | Block 7 Post_Ffw_Norm_1 (W) | ( ~3K) 2816 | 2816 x 1 x 1 x 1 | F32 | 32.0000 | | 543 | blk.7.post_ffw_norm_2.weight | Block 7 Post_Ffw_Norm_2 (W) | ( ~3K) 2816 | 2816 x 1 x 1 x 1 | F32 | 32.0000 | | 544 | blk.7.ffn_norm.weight | Block 7 Feed-Forward Network Normalization (W) | ( ~3K) 2816 | 2816 x 1 x 1 x 1 | F32 | 32.0000 | | 545 | blk.7.pre_ffw_norm_2.weight | Block 7 Pre_Ffw_Norm_2 (W) | ( ~3K) 2816 | 2816 x 1 x 1 x 1 | F32 | 32.0000 | | 546 | blk.7.ffn_down_exps.scale | Block 7 Ffn_Down_Exps Scale | ( 128) 128 | 128 x 1 x 1 x 1 | F32 | 32.0000 | | 547 | blk.7.ffn_gate_inp.weight | Block 7 Expert-Routing Layer For The Feed-Forward Network In Mixture Of Expert Models (W) | (~360K) 360448 | 2816 x 128 x 1 x 1 | F32 | 32.0000 | | 548 | blk.7.ffn_gate_inp.scale | Block 7 Expert-Routing Layer For The Feed-Forward Network In Mixture Of Expert Models Scale | ( ~3K) 2816 | 2816 x 1 x 1 x 1 | F32 | 32.0000 | | 549 | blk.7.attn_k_norm.weight | Block 7 Attn_K_Norm (W) | ( 256) 256 | 256 x 1 x 1 x 1 | F32 | 32.0000 | | 550 | blk.7.attn_k.weight | Block 7 Attention Key (W) | ( ~6M) 5767168 | 2816 x 2048 x 1 x 1 | F16 | 16.0000 | | 551 | blk.7.attn_output.weight | Block 7 Attention Output (W) | ( ~12M) 11534336 | 4096 x 2816 x 1 x 1 | F16 | 16.0000 | | 552 | blk.7.attn_q_norm.weight | Block 7 Attn_Q_Norm (W) | ( 256) 256 | 256 x 1 x 1 x 1 | F32 | 32.0000 | | 553 | blk.7.attn_q.weight | Block 7 Attention Query (W) | ( ~12M) 11534336 | 2816 x 4096 x 1 x 1 | F16 | 16.0000 | | 554 | blk.7.attn_v.weight | Block 7 Attention Value (W) | ( ~6M) 5767168 | 2816 x 2048 x 1 x 1 | F16 | 16.0000 | - Total elements in blk.7: (~814M) 814094977 - Percentage of total elements: 3.23% - Bits per Weight (BPW) for blk.7: 16.0075 bits ### Block 8 Tensor Group : ~814M Elements | T_ID | Tensor Layer Name | Human Friendly Tensor Layer Name | Elements | Shape | Type | BPW | | ---: | :------------------------------- | :------------------------------------------------------------------------------------------ | :---------------- | :-------------------- | :--- | ------: | | 555 | blk.8.ffn_down_exps.weight | Block 8 Ffn_Down_Exps (W) | (~254M) 253755392 | 704 x 2816 x 128 x 1 | F16 | 16.0000 | | 556 | blk.8.ffn_gate_up_exps.weight | Block 8 Ffn_Gate_Up_Exps (W) | (~508M) 507510784 | 2816 x 1408 x 128 x 1 | F16 | 16.0000 | | 557 | blk.8.attn_norm.weight | Block 8 Attention Normalization (W) | ( ~3K) 2816 | 2816 x 1 x 1 x 1 | F32 | 32.0000 | | 558 | blk.8.layer_output_scale.weight | Block 8 Layer_Output_Scale (W) | ( 1) 1 | 1 x 1 x 1 x 1 | F32 | 32.0000 | | 559 | blk.8.ffn_down.weight | Block 8 Feed-Forward Network "Down" (W) | ( ~6M) 5947392 | 2112 x 2816 x 1 x 1 | F16 | 16.0000 | | 560 | blk.8.ffn_gate.weight | Block 8 Feed-Forward Network "Gate" (W) | ( ~6M) 5947392 | 2816 x 2112 x 1 x 1 | F16 | 16.0000 | | 561 | blk.8.ffn_up.weight | Block 8 Feed-Forward Network "Up" (W) | ( ~6M) 5947392 | 2816 x 2112 x 1 x 1 | F16 | 16.0000 | | 562 | blk.8.post_attention_norm.weight | Block 8 Post_Attention_Norm (W) | ( ~3K) 2816 | 2816 x 1 x 1 x 1 | F32 | 32.0000 | | 563 | blk.8.post_ffw_norm.weight | Block 8 Post_Ffw_Norm (W) | ( ~3K) 2816 | 2816 x 1 x 1 x 1 | F32 | 32.0000 | | 564 | blk.8.post_ffw_norm_1.weight | Block 8 Post_Ffw_Norm_1 (W) | ( ~3K) 2816 | 2816 x 1 x 1 x 1 | F32 | 32.0000 | | 565 | blk.8.post_ffw_norm_2.weight | Block 8 Post_Ffw_Norm_2 (W) | ( ~3K) 2816 | 2816 x 1 x 1 x 1 | F32 | 32.0000 | | 566 | blk.8.ffn_norm.weight | Block 8 Feed-Forward Network Normalization (W) | ( ~3K) 2816 | 2816 x 1 x 1 x 1 | F32 | 32.0000 | | 567 | blk.8.pre_ffw_norm_2.weight | Block 8 Pre_Ffw_Norm_2 (W) | ( ~3K) 2816 | 2816 x 1 x 1 x 1 | F32 | 32.0000 | | 568 | blk.8.ffn_down_exps.scale | Block 8 Ffn_Down_Exps Scale | ( 128) 128 | 128 x 1 x 1 x 1 | F32 | 32.0000 | | 569 | blk.8.ffn_gate_inp.weight | Block 8 Expert-Routing Layer For The Feed-Forward Network In Mixture Of Expert Models (W) | (~360K) 360448 | 2816 x 128 x 1 x 1 | F32 | 32.0000 | | 570 | blk.8.ffn_gate_inp.scale | Block 8 Expert-Routing Layer For The Feed-Forward Network In Mixture Of Expert Models Scale | ( ~3K) 2816 | 2816 x 1 x 1 x 1 | F32 | 32.0000 | | 571 | blk.8.attn_k_norm.weight | Block 8 Attn_K_Norm (W) | ( 256) 256 | 256 x 1 x 1 x 1 | F32 | 32.0000 | | 572 | blk.8.attn_k.weight | Block 8 Attention Key (W) | ( ~6M) 5767168 | 2816 x 2048 x 1 x 1 | F16 | 16.0000 | | 573 | blk.8.attn_output.weight | Block 8 Attention Output (W) | ( ~12M) 11534336 | 4096 x 2816 x 1 x 1 | F16 | 16.0000 | | 574 | blk.8.attn_q_norm.weight | Block 8 Attn_Q_Norm (W) | ( 256) 256 | 256 x 1 x 1 x 1 | F32 | 32.0000 | | 575 | blk.8.attn_q.weight | Block 8 Attention Query (W) | ( ~12M) 11534336 | 2816 x 4096 x 1 x 1 | F16 | 16.0000 | | 576 | blk.8.attn_v.weight | Block 8 Attention Value (W) | ( ~6M) 5767168 | 2816 x 2048 x 1 x 1 | F16 | 16.0000 | - Total elements in blk.8: (~814M) 814094977 - Percentage of total elements: 3.23% - Bits per Weight (BPW) for blk.8: 16.0075 bits ### Block 9 Tensor Group : ~814M Elements | T_ID | Tensor Layer Name | Human Friendly Tensor Layer Name | Elements | Shape | Type | BPW | | ---: | :------------------------------- | :------------------------------------------------------------------------------------------ | :---------------- | :-------------------- | :--- | ------: | | 577 | blk.9.ffn_down_exps.weight | Block 9 Ffn_Down_Exps (W) | (~254M) 253755392 | 704 x 2816 x 128 x 1 | F16 | 16.0000 | | 578 | blk.9.ffn_gate_up_exps.weight | Block 9 Ffn_Gate_Up_Exps (W) | (~508M) 507510784 | 2816 x 1408 x 128 x 1 | F16 | 16.0000 | | 579 | blk.9.attn_norm.weight | Block 9 Attention Normalization (W) | ( ~3K) 2816 | 2816 x 1 x 1 x 1 | F32 | 32.0000 | | 580 | blk.9.layer_output_scale.weight | Block 9 Layer_Output_Scale (W) | ( 1) 1 | 1 x 1 x 1 x 1 | F32 | 32.0000 | | 581 | blk.9.ffn_down.weight | Block 9 Feed-Forward Network "Down" (W) | ( ~6M) 5947392 | 2112 x 2816 x 1 x 1 | F16 | 16.0000 | | 582 | blk.9.ffn_gate.weight | Block 9 Feed-Forward Network "Gate" (W) | ( ~6M) 5947392 | 2816 x 2112 x 1 x 1 | F16 | 16.0000 | | 583 | blk.9.ffn_up.weight | Block 9 Feed-Forward Network "Up" (W) | ( ~6M) 5947392 | 2816 x 2112 x 1 x 1 | F16 | 16.0000 | | 584 | blk.9.post_attention_norm.weight | Block 9 Post_Attention_Norm (W) | ( ~3K) 2816 | 2816 x 1 x 1 x 1 | F32 | 32.0000 | | 585 | blk.9.post_ffw_norm.weight | Block 9 Post_Ffw_Norm (W) | ( ~3K) 2816 | 2816 x 1 x 1 x 1 | F32 | 32.0000 | | 586 | blk.9.post_ffw_norm_1.weight | Block 9 Post_Ffw_Norm_1 (W) | ( ~3K) 2816 | 2816 x 1 x 1 x 1 | F32 | 32.0000 | | 587 | blk.9.post_ffw_norm_2.weight | Block 9 Post_Ffw_Norm_2 (W) | ( ~3K) 2816 | 2816 x 1 x 1 x 1 | F32 | 32.0000 | | 588 | blk.9.ffn_norm.weight | Block 9 Feed-Forward Network Normalization (W) | ( ~3K) 2816 | 2816 x 1 x 1 x 1 | F32 | 32.0000 | | 589 | blk.9.pre_ffw_norm_2.weight | Block 9 Pre_Ffw_Norm_2 (W) | ( ~3K) 2816 | 2816 x 1 x 1 x 1 | F32 | 32.0000 | | 590 | blk.9.ffn_down_exps.scale | Block 9 Ffn_Down_Exps Scale | ( 128) 128 | 128 x 1 x 1 x 1 | F32 | 32.0000 | | 591 | blk.9.ffn_gate_inp.weight | Block 9 Expert-Routing Layer For The Feed-Forward Network In Mixture Of Expert Models (W) | (~360K) 360448 | 2816 x 128 x 1 x 1 | F32 | 32.0000 | | 592 | blk.9.ffn_gate_inp.scale | Block 9 Expert-Routing Layer For The Feed-Forward Network In Mixture Of Expert Models Scale | ( ~3K) 2816 | 2816 x 1 x 1 x 1 | F32 | 32.0000 | | 593 | blk.9.attn_k_norm.weight | Block 9 Attn_K_Norm (W) | ( 256) 256 | 256 x 1 x 1 x 1 | F32 | 32.0000 | | 594 | blk.9.attn_k.weight | Block 9 Attention Key (W) | ( ~6M) 5767168 | 2816 x 2048 x 1 x 1 | F16 | 16.0000 | | 595 | blk.9.attn_output.weight | Block 9 Attention Output (W) | ( ~12M) 11534336 | 4096 x 2816 x 1 x 1 | F16 | 16.0000 | | 596 | blk.9.attn_q_norm.weight | Block 9 Attn_Q_Norm (W) | ( 256) 256 | 256 x 1 x 1 x 1 | F32 | 32.0000 | | 597 | blk.9.attn_q.weight | Block 9 Attention Query (W) | ( ~12M) 11534336 | 2816 x 4096 x 1 x 1 | F16 | 16.0000 | | 598 | blk.9.attn_v.weight | Block 9 Attention Value (W) | ( ~6M) 5767168 | 2816 x 2048 x 1 x 1 | F16 | 16.0000 | - Total elements in blk.9: (~814M) 814094977 - Percentage of total elements: 3.23% - Bits per Weight (BPW) for blk.9: 16.0075 bits Total BPW for gemma-4-26B-A4B-it-F16.gguf: 16.0073 bits