# gemma-4-E4B-it-F16.gguf - GGUF Internal File Dump - Endian: LITTLE endian ## Key Value Metadata Store There are 48 key-value pairs in this file | POS | TYPE | Count | Key | Value | | ---: | :-------- | -----: | :-------------------------------------- | :--------------------------------------------------------------------------------------------------------------- | | 1 | UINT32 | 1 | GGUF.version | 3 | | 2 | UINT64 | 1 | GGUF.tensor_count | 720 | | 3 | UINT64 | 1 | GGUF.kv_count | 45 | | 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 E4B It` | | 10 | STRING | 1 | general.size_label | `7.5B` | | 11 | STRING | 1 | general.license | `apache-2.0` | | 12 | STRING | 1 | general.license.link | `https://ai.google.dev/gemma/docs/gemma_4_license` | | 13 | [STRING] | 1 | general.tags | [ `any-to-any` ] | | 14 | UINT32 | 1 | gemma4.block_count | 42 | | 15 | UINT32 | 1 | gemma4.context_length | 131072 | | 16 | UINT32 | 1 | gemma4.embedding_length | 2560 | | 17 | UINT32 | 1 | gemma4.feed_forward_length | 10240 | | 18 | UINT32 | 1 | gemma4.attention.head_count | 8 | | 19 | UINT32 | 1 | gemma4.attention.head_count_kv | 2 | | 20 | FLOAT32 | 1 | gemma4.rope.freq_base | 1e+06 | | 21 | FLOAT32 | 1 | gemma4.rope.freq_base_swa | 10000.0 | | 22 | FLOAT32 | 1 | gemma4.attention.layer_norm_rms_epsilon | 1e-06 | | 23 | UINT32 | 1 | gemma4.attention.key_length | 512 | | 24 | UINT32 | 1 | gemma4.attention.value_length | 512 | | 25 | UINT32 | 1 | general.file_type | 1 | | 26 | FLOAT32 | 1 | gemma4.final_logit_softcapping | 30.0 | | 27 | UINT32 | 1 | gemma4.attention.sliding_window | 512 | | 28 | UINT32 | 1 | gemma4.attention.shared_kv_layers | 18 | | 29 | UINT32 | 1 | gemma4.embedding_length_per_layer_input | 256 | | 30 | [BOOL] | 42 | gemma4.attention.sliding_window_pattern | [ True, True, True, True, True, False, True, ... ] | | 31 | UINT32 | 1 | gemma4.attention.key_length_swa | 256 | | 32 | UINT32 | 1 | gemma4.attention.value_length_swa | 256 | | 33 | UINT32 | 1 | gemma4.rope.dimension_count | 512 | | 34 | UINT32 | 1 | gemma4.rope.dimension_count_swa | 256 | | 35 | UINT32 | 1 | general.quantization_version | 2 | | 36 | STRING | 1 | tokenizer.ggml.model | `gemma4` | | 37 | [STRING] | 262144 | tokenizer.ggml.tokens | [ ``, ``, ``, ``, ``, ... ] | | 38 | [FLOAT32] | 262144 | tokenizer.ggml.scores | [ -1000.0, -1000.0, -1000.0, -1000.0, -1000.0, -1000.0, -1000.0, ... ] | | 39 | [INT32] | 262144 | tokenizer.ggml.token_type | [ 3, 3, 3, 3, 3, 1, 1, ... ] | | 40 | [STRING] | 514906 | tokenizer.ggml.merges | [ ``...``, `▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁`...`▁▁▁▁▁▁▁▁▁▁▁▁▁ ▁`, ``...``, ``...``, `▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁`...`▁▁▁▁▁▁▁▁▁▁▁▁ ▁▁`, ... ] | | 41 | UINT32 | 1 | tokenizer.ggml.bos_token_id | 2 | | 42 | UINT32 | 1 | tokenizer.ggml.eos_token_id | 1 | | 43 | UINT32 | 1 | tokenizer.ggml.unknown_token_id | 3 | | 44 | UINT32 | 1 | tokenizer.ggml.padding_token_id | 0 | | 45 | UINT32 | 1 | tokenizer.ggml.mask_token_id | 4 | | 46 | STRING | 1 | tokenizer.chat_template | `{%- macro format_parameters(pr`...` {%- endif -%} {%- endif -%}` | | 47 | BOOL | 1 | tokenizer.ggml.add_space_prefix | False | | 48 | BOOL | 1 | tokenizer.ggml.add_bos_token | True | ## Tensors Overview ~8B Elements Total number of elements in all tensors: 7518069290 Elements - [gemma-4-E4B-it-F16.gguf - GGUF Internal File Dump](#gemma-4-e4b-it-f16gguf---gguf-internal-file-dump) - [Key Value Metadata Store](#key-value-metadata-store) - [Tensors Overview ~8B Elements](#tensors-overview-8b-elements) - [Tensor Data Offset](#tensor-data-offset) - [Base Tensor Group : ~4B Elements](#base-tensor-group--4b-elements) - [Block 0 Tensor Group : ~93M Elements](#block-0-tensor-group--93m-elements) - [Block 1 Tensor Group : ~93M Elements](#block-1-tensor-group--93m-elements) - [Block 10 Tensor Group : ~93M Elements](#block-10-tensor-group--93m-elements) - [Block 11 Tensor Group : ~106M Elements](#block-11-tensor-group--106m-elements) - [Block 12 Tensor Group : ~93M Elements](#block-12-tensor-group--93m-elements) - [Block 13 Tensor Group : ~93M Elements](#block-13-tensor-group--93m-elements) - [Block 14 Tensor Group : ~93M Elements](#block-14-tensor-group--93m-elements) - [Block 15 Tensor Group : ~93M Elements](#block-15-tensor-group--93m-elements) - [Block 16 Tensor Group : ~93M Elements](#block-16-tensor-group--93m-elements) - [Block 17 Tensor Group : ~106M Elements](#block-17-tensor-group--106m-elements) - [Block 18 Tensor Group : ~93M Elements](#block-18-tensor-group--93m-elements) - [Block 19 Tensor Group : ~93M Elements](#block-19-tensor-group--93m-elements) - [Block 2 Tensor Group : ~93M Elements](#block-2-tensor-group--93m-elements) - [Block 20 Tensor Group : ~93M Elements](#block-20-tensor-group--93m-elements) - [Block 21 Tensor Group : ~93M Elements](#block-21-tensor-group--93m-elements) - [Block 22 Tensor Group : ~93M Elements](#block-22-tensor-group--93m-elements) - [Block 23 Tensor Group : ~106M Elements](#block-23-tensor-group--106m-elements) - [Block 24 Tensor Group : ~93M Elements](#block-24-tensor-group--93m-elements) - [Block 25 Tensor Group : ~93M Elements](#block-25-tensor-group--93m-elements) - [Block 26 Tensor Group : ~93M Elements](#block-26-tensor-group--93m-elements) - [Block 27 Tensor Group : ~93M Elements](#block-27-tensor-group--93m-elements) - [Block 28 Tensor Group : ~93M Elements](#block-28-tensor-group--93m-elements) - [Block 29 Tensor Group : ~106M Elements](#block-29-tensor-group--106m-elements) - [Block 3 Tensor Group : ~93M Elements](#block-3-tensor-group--93m-elements) - [Block 30 Tensor Group : ~93M Elements](#block-30-tensor-group--93m-elements) - [Block 31 Tensor Group : ~93M Elements](#block-31-tensor-group--93m-elements) - [Block 32 Tensor Group : ~93M Elements](#block-32-tensor-group--93m-elements) - [Block 33 Tensor Group : ~93M Elements](#block-33-tensor-group--93m-elements) - [Block 34 Tensor Group : ~93M Elements](#block-34-tensor-group--93m-elements) - [Block 35 Tensor Group : ~106M Elements](#block-35-tensor-group--106m-elements) - [Block 36 Tensor Group : ~93M Elements](#block-36-tensor-group--93m-elements) - [Block 37 Tensor Group : ~93M Elements](#block-37-tensor-group--93m-elements) - [Block 38 Tensor Group : ~93M Elements](#block-38-tensor-group--93m-elements) - [Block 39 Tensor Group : ~93M Elements](#block-39-tensor-group--93m-elements) - [Block 4 Tensor Group : ~93M Elements](#block-4-tensor-group--93m-elements) - [Block 40 Tensor Group : ~93M Elements](#block-40-tensor-group--93m-elements) - [Block 41 Tensor Group : ~106M Elements](#block-41-tensor-group--106m-elements) - [Block 5 Tensor Group : ~106M Elements](#block-5-tensor-group--106m-elements) - [Block 6 Tensor Group : ~93M Elements](#block-6-tensor-group--93m-elements) - [Block 7 Tensor Group : ~93M Elements](#block-7-tensor-group--93m-elements) - [Block 8 Tensor Group : ~93M Elements](#block-8-tensor-group--93m-elements) - [Block 9 Tensor Group : ~93M Elements](#block-9-tensor-group--93m-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 | 0xf172c0 | 0x400 | | 1 | token_embd.weight | 0xf176c0 | 0x50000000 | | 2 | per_layer_token_embd.weight | 0x50f176c0 | 0x150000000 | | 3 | blk.0.attn_norm.weight | 0x1a0f176c0 | 0x2800 | | 4 | blk.0.layer_output_scale.weight | 0x1a0f19ec0 | 0x4 | | 5 | blk.0.ffn_down.weight | 0x1a0f19ee0 | 0x3200000 | | 6 | blk.0.ffn_gate.weight | 0x1a4119ee0 | 0x3200000 | | 7 | blk.0.ffn_up.weight | 0x1a7319ee0 | 0x3200000 | | 8 | blk.0.inp_gate.weight | 0x1aa519ee0 | 0x140000 | | 9 | blk.0.proj.weight | 0x1aa659ee0 | 0x140000 | | 10 | blk.0.post_attention_norm.weight | 0x1aa799ee0 | 0x2800 | | 11 | blk.0.post_ffw_norm.weight | 0x1aa79c6e0 | 0x2800 | | 12 | blk.0.post_norm.weight | 0x1aa79eee0 | 0x2800 | | 13 | blk.0.ffn_norm.weight | 0x1aa7a16e0 | 0x2800 | | 14 | blk.0.attn_k_norm.weight | 0x1aa7a3ee0 | 0x400 | | 15 | blk.0.attn_k.weight | 0x1aa7a42e0 | 0x280000 | | 16 | blk.0.attn_output.weight | 0x1aaa242e0 | 0xa00000 | | 17 | blk.0.attn_q_norm.weight | 0x1ab4242e0 | 0x400 | | 18 | blk.0.attn_q.weight | 0x1ab4246e0 | 0xa00000 | | 19 | blk.0.attn_v.weight | 0x1abe246e0 | 0x280000 | | 20 | blk.1.attn_norm.weight | 0x1ac0a46e0 | 0x2800 | | 21 | blk.1.layer_output_scale.weight | 0x1ac0a6ee0 | 0x4 | | 22 | blk.1.ffn_down.weight | 0x1ac0a6f00 | 0x3200000 | | 23 | blk.1.ffn_gate.weight | 0x1af2a6f00 | 0x3200000 | | 24 | blk.1.ffn_up.weight | 0x1b24a6f00 | 0x3200000 | | 25 | blk.1.inp_gate.weight | 0x1b56a6f00 | 0x140000 | | 26 | blk.1.proj.weight | 0x1b57e6f00 | 0x140000 | | 27 | blk.1.post_attention_norm.weight | 0x1b5926f00 | 0x2800 | | 28 | blk.1.post_ffw_norm.weight | 0x1b5929700 | 0x2800 | | 29 | blk.1.post_norm.weight | 0x1b592bf00 | 0x2800 | | 30 | blk.1.ffn_norm.weight | 0x1b592e700 | 0x2800 | | 31 | blk.1.attn_k_norm.weight | 0x1b5930f00 | 0x400 | | 32 | blk.1.attn_k.weight | 0x1b5931300 | 0x280000 | | 33 | blk.1.attn_output.weight | 0x1b5bb1300 | 0xa00000 | | 34 | blk.1.attn_q_norm.weight | 0x1b65b1300 | 0x400 | | 35 | blk.1.attn_q.weight | 0x1b65b1700 | 0xa00000 | | 36 | blk.1.attn_v.weight | 0x1b6fb1700 | 0x280000 | | 37 | blk.10.attn_norm.weight | 0x1b7231700 | 0x2800 | | 38 | blk.10.layer_output_scale.weight | 0x1b7233f00 | 0x4 | | 39 | blk.10.ffn_down.weight | 0x1b7233f20 | 0x3200000 | | 40 | blk.10.ffn_gate.weight | 0x1ba433f20 | 0x3200000 | | 41 | blk.10.ffn_up.weight | 0x1bd633f20 | 0x3200000 | | 42 | blk.10.inp_gate.weight | 0x1c0833f20 | 0x140000 | | 43 | blk.10.proj.weight | 0x1c0973f20 | 0x140000 | | 44 | blk.10.post_attention_norm.weight | 0x1c0ab3f20 | 0x2800 | | 45 | blk.10.post_ffw_norm.weight | 0x1c0ab6720 | 0x2800 | | 46 | blk.10.post_norm.weight | 0x1c0ab8f20 | 0x2800 | | 47 | blk.10.ffn_norm.weight | 0x1c0abb720 | 0x2800 | | 48 | blk.10.attn_k_norm.weight | 0x1c0abdf20 | 0x400 | | 49 | blk.10.attn_k.weight | 0x1c0abe320 | 0x280000 | | 50 | blk.10.attn_output.weight | 0x1c0d3e320 | 0xa00000 | | 51 | blk.10.attn_q_norm.weight | 0x1c173e320 | 0x400 | | 52 | blk.10.attn_q.weight | 0x1c173e720 | 0xa00000 | | 53 | blk.10.attn_v.weight | 0x1c213e720 | 0x280000 | | 54 | blk.11.attn_norm.weight | 0x1c23be720 | 0x2800 | | 55 | blk.11.layer_output_scale.weight | 0x1c23c0f20 | 0x4 | | 56 | blk.11.ffn_down.weight | 0x1c23c0f40 | 0x3200000 | | 57 | blk.11.ffn_gate.weight | 0x1c55c0f40 | 0x3200000 | | 58 | blk.11.ffn_up.weight | 0x1c87c0f40 | 0x3200000 | | 59 | blk.11.inp_gate.weight | 0x1cb9c0f40 | 0x140000 | | 60 | blk.11.proj.weight | 0x1cbb00f40 | 0x140000 | | 61 | blk.11.post_attention_norm.weight | 0x1cbc40f40 | 0x2800 | | 62 | blk.11.post_ffw_norm.weight | 0x1cbc43740 | 0x2800 | | 63 | blk.11.post_norm.weight | 0x1cbc45f40 | 0x2800 | | 64 | blk.11.ffn_norm.weight | 0x1cbc48740 | 0x2800 | | 65 | blk.11.attn_k_norm.weight | 0x1cbc4af40 | 0x800 | | 66 | blk.11.attn_k.weight | 0x1cbc4b740 | 0x500000 | | 67 | blk.11.attn_output.weight | 0x1cc14b740 | 0x1400000 | | 68 | blk.11.attn_q_norm.weight | 0x1cd54b740 | 0x800 | | 69 | blk.11.attn_q.weight | 0x1cd54bf40 | 0x1400000 | | 70 | blk.11.attn_v.weight | 0x1ce94bf40 | 0x500000 | | 71 | blk.12.attn_norm.weight | 0x1cee4bf40 | 0x2800 | | 72 | blk.12.layer_output_scale.weight | 0x1cee4e740 | 0x4 | | 73 | blk.12.ffn_down.weight | 0x1cee4e760 | 0x3200000 | | 74 | blk.12.ffn_gate.weight | 0x1d204e760 | 0x3200000 | | 75 | blk.12.ffn_up.weight | 0x1d524e760 | 0x3200000 | | 76 | blk.12.inp_gate.weight | 0x1d844e760 | 0x140000 | | 77 | blk.12.proj.weight | 0x1d858e760 | 0x140000 | | 78 | blk.12.post_attention_norm.weight | 0x1d86ce760 | 0x2800 | | 79 | blk.12.post_ffw_norm.weight | 0x1d86d0f60 | 0x2800 | | 80 | blk.12.post_norm.weight | 0x1d86d3760 | 0x2800 | | 81 | blk.12.ffn_norm.weight | 0x1d86d5f60 | 0x2800 | | 82 | blk.12.attn_k_norm.weight | 0x1d86d8760 | 0x400 | | 83 | blk.12.attn_k.weight | 0x1d86d8b60 | 0x280000 | | 84 | blk.12.attn_output.weight | 0x1d8958b60 | 0xa00000 | | 85 | blk.12.attn_q_norm.weight | 0x1d9358b60 | 0x400 | | 86 | blk.12.attn_q.weight | 0x1d9358f60 | 0xa00000 | | 87 | blk.12.attn_v.weight | 0x1d9d58f60 | 0x280000 | | 88 | blk.13.attn_norm.weight | 0x1d9fd8f60 | 0x2800 | | 89 | blk.13.layer_output_scale.weight | 0x1d9fdb760 | 0x4 | | 90 | blk.13.ffn_down.weight | 0x1d9fdb780 | 0x3200000 | | 91 | blk.13.ffn_gate.weight | 0x1dd1db780 | 0x3200000 | | 92 | blk.13.ffn_up.weight | 0x1e03db780 | 0x3200000 | | 93 | blk.13.inp_gate.weight | 0x1e35db780 | 0x140000 | | 94 | blk.13.proj.weight | 0x1e371b780 | 0x140000 | | 95 | blk.13.post_attention_norm.weight | 0x1e385b780 | 0x2800 | | 96 | blk.13.post_ffw_norm.weight | 0x1e385df80 | 0x2800 | | 97 | blk.13.post_norm.weight | 0x1e3860780 | 0x2800 | | 98 | blk.13.ffn_norm.weight | 0x1e3862f80 | 0x2800 | | 99 | blk.13.attn_k_norm.weight | 0x1e3865780 | 0x400 | | 100 | blk.13.attn_k.weight | 0x1e3865b80 | 0x280000 | | 101 | blk.13.attn_output.weight | 0x1e3ae5b80 | 0xa00000 | | 102 | blk.13.attn_q_norm.weight | 0x1e44e5b80 | 0x400 | | 103 | blk.13.attn_q.weight | 0x1e44e5f80 | 0xa00000 | | 104 | blk.13.attn_v.weight | 0x1e4ee5f80 | 0x280000 | | 105 | blk.14.attn_norm.weight | 0x1e5165f80 | 0x2800 | | 106 | blk.14.layer_output_scale.weight | 0x1e5168780 | 0x4 | | 107 | blk.14.ffn_down.weight | 0x1e51687a0 | 0x3200000 | | 108 | blk.14.ffn_gate.weight | 0x1e83687a0 | 0x3200000 | | 109 | blk.14.ffn_up.weight | 0x1eb5687a0 | 0x3200000 | | 110 | blk.14.inp_gate.weight | 0x1ee7687a0 | 0x140000 | | 111 | blk.14.proj.weight | 0x1ee8a87a0 | 0x140000 | | 112 | blk.14.post_attention_norm.weight | 0x1ee9e87a0 | 0x2800 | | 113 | blk.14.post_ffw_norm.weight | 0x1ee9eafa0 | 0x2800 | | 114 | blk.14.post_norm.weight | 0x1ee9ed7a0 | 0x2800 | | 115 | blk.14.ffn_norm.weight | 0x1ee9effa0 | 0x2800 | | 116 | blk.14.attn_k_norm.weight | 0x1ee9f27a0 | 0x400 | | 117 | blk.14.attn_k.weight | 0x1ee9f2ba0 | 0x280000 | | 118 | blk.14.attn_output.weight | 0x1eec72ba0 | 0xa00000 | | 119 | blk.14.attn_q_norm.weight | 0x1ef672ba0 | 0x400 | | 120 | blk.14.attn_q.weight | 0x1ef672fa0 | 0xa00000 | | 121 | blk.14.attn_v.weight | 0x1f0072fa0 | 0x280000 | | 122 | blk.15.attn_norm.weight | 0x1f02f2fa0 | 0x2800 | | 123 | blk.15.layer_output_scale.weight | 0x1f02f57a0 | 0x4 | | 124 | blk.15.ffn_down.weight | 0x1f02f57c0 | 0x3200000 | | 125 | blk.15.ffn_gate.weight | 0x1f34f57c0 | 0x3200000 | | 126 | blk.15.ffn_up.weight | 0x1f66f57c0 | 0x3200000 | | 127 | blk.15.inp_gate.weight | 0x1f98f57c0 | 0x140000 | | 128 | blk.15.proj.weight | 0x1f9a357c0 | 0x140000 | | 129 | blk.15.post_attention_norm.weight | 0x1f9b757c0 | 0x2800 | | 130 | blk.15.post_ffw_norm.weight | 0x1f9b77fc0 | 0x2800 | | 131 | blk.15.post_norm.weight | 0x1f9b7a7c0 | 0x2800 | | 132 | blk.15.ffn_norm.weight | 0x1f9b7cfc0 | 0x2800 | | 133 | blk.15.attn_k_norm.weight | 0x1f9b7f7c0 | 0x400 | | 134 | blk.15.attn_k.weight | 0x1f9b7fbc0 | 0x280000 | | 135 | blk.15.attn_output.weight | 0x1f9dffbc0 | 0xa00000 | | 136 | blk.15.attn_q_norm.weight | 0x1fa7ffbc0 | 0x400 | | 137 | blk.15.attn_q.weight | 0x1fa7fffc0 | 0xa00000 | | 138 | blk.15.attn_v.weight | 0x1fb1fffc0 | 0x280000 | | 139 | blk.16.attn_norm.weight | 0x1fb47ffc0 | 0x2800 | | 140 | blk.16.layer_output_scale.weight | 0x1fb4827c0 | 0x4 | | 141 | blk.16.ffn_down.weight | 0x1fb4827e0 | 0x3200000 | | 142 | blk.16.ffn_gate.weight | 0x1fe6827e0 | 0x3200000 | | 143 | blk.16.ffn_up.weight | 0x2018827e0 | 0x3200000 | | 144 | blk.16.inp_gate.weight | 0x204a827e0 | 0x140000 | | 145 | blk.16.proj.weight | 0x204bc27e0 | 0x140000 | | 146 | blk.16.post_attention_norm.weight | 0x204d027e0 | 0x2800 | | 147 | blk.16.post_ffw_norm.weight | 0x204d04fe0 | 0x2800 | | 148 | blk.16.post_norm.weight | 0x204d077e0 | 0x2800 | | 149 | blk.16.ffn_norm.weight | 0x204d09fe0 | 0x2800 | | 150 | blk.16.attn_k_norm.weight | 0x204d0c7e0 | 0x400 | | 151 | blk.16.attn_k.weight | 0x204d0cbe0 | 0x280000 | | 152 | blk.16.attn_output.weight | 0x204f8cbe0 | 0xa00000 | | 153 | blk.16.attn_q_norm.weight | 0x20598cbe0 | 0x400 | | 154 | blk.16.attn_q.weight | 0x20598cfe0 | 0xa00000 | | 155 | blk.16.attn_v.weight | 0x20638cfe0 | 0x280000 | | 156 | blk.17.attn_norm.weight | 0x20660cfe0 | 0x2800 | | 157 | blk.17.layer_output_scale.weight | 0x20660f7e0 | 0x4 | | 158 | blk.17.ffn_down.weight | 0x20660f800 | 0x3200000 | | 159 | blk.17.ffn_gate.weight | 0x20980f800 | 0x3200000 | | 160 | blk.17.ffn_up.weight | 0x20ca0f800 | 0x3200000 | | 161 | blk.17.inp_gate.weight | 0x20fc0f800 | 0x140000 | | 162 | blk.17.proj.weight | 0x20fd4f800 | 0x140000 | | 163 | blk.17.post_attention_norm.weight | 0x20fe8f800 | 0x2800 | | 164 | blk.17.post_ffw_norm.weight | 0x20fe92000 | 0x2800 | | 165 | blk.17.post_norm.weight | 0x20fe94800 | 0x2800 | | 166 | blk.17.ffn_norm.weight | 0x20fe97000 | 0x2800 | | 167 | blk.17.attn_k_norm.weight | 0x20fe99800 | 0x800 | | 168 | blk.17.attn_k.weight | 0x20fe9a000 | 0x500000 | | 169 | blk.17.attn_output.weight | 0x21039a000 | 0x1400000 | | 170 | blk.17.attn_q_norm.weight | 0x21179a000 | 0x800 | | 171 | blk.17.attn_q.weight | 0x21179a800 | 0x1400000 | | 172 | blk.17.attn_v.weight | 0x212b9a800 | 0x500000 | | 173 | blk.18.attn_norm.weight | 0x21309a800 | 0x2800 | | 174 | blk.18.layer_output_scale.weight | 0x21309d000 | 0x4 | | 175 | blk.18.ffn_down.weight | 0x21309d020 | 0x3200000 | | 176 | blk.18.ffn_gate.weight | 0x21629d020 | 0x3200000 | | 177 | blk.18.ffn_up.weight | 0x21949d020 | 0x3200000 | | 178 | blk.18.inp_gate.weight | 0x21c69d020 | 0x140000 | | 179 | blk.18.proj.weight | 0x21c7dd020 | 0x140000 | | 180 | blk.18.post_attention_norm.weight | 0x21c91d020 | 0x2800 | | 181 | blk.18.post_ffw_norm.weight | 0x21c91f820 | 0x2800 | | 182 | blk.18.post_norm.weight | 0x21c922020 | 0x2800 | | 183 | blk.18.ffn_norm.weight | 0x21c924820 | 0x2800 | | 184 | blk.18.attn_k_norm.weight | 0x21c927020 | 0x400 | | 185 | blk.18.attn_k.weight | 0x21c927420 | 0x280000 | | 186 | blk.18.attn_output.weight | 0x21cba7420 | 0xa00000 | | 187 | blk.18.attn_q_norm.weight | 0x21d5a7420 | 0x400 | | 188 | blk.18.attn_q.weight | 0x21d5a7820 | 0xa00000 | | 189 | blk.18.attn_v.weight | 0x21dfa7820 | 0x280000 | | 190 | blk.19.attn_norm.weight | 0x21e227820 | 0x2800 | | 191 | blk.19.layer_output_scale.weight | 0x21e22a020 | 0x4 | | 192 | blk.19.ffn_down.weight | 0x21e22a040 | 0x3200000 | | 193 | blk.19.ffn_gate.weight | 0x22142a040 | 0x3200000 | | 194 | blk.19.ffn_up.weight | 0x22462a040 | 0x3200000 | | 195 | blk.19.inp_gate.weight | 0x22782a040 | 0x140000 | | 196 | blk.19.proj.weight | 0x22796a040 | 0x140000 | | 197 | blk.19.post_attention_norm.weight | 0x227aaa040 | 0x2800 | | 198 | blk.19.post_ffw_norm.weight | 0x227aac840 | 0x2800 | | 199 | blk.19.post_norm.weight | 0x227aaf040 | 0x2800 | | 200 | blk.19.ffn_norm.weight | 0x227ab1840 | 0x2800 | | 201 | blk.19.attn_k_norm.weight | 0x227ab4040 | 0x400 | | 202 | blk.19.attn_k.weight | 0x227ab4440 | 0x280000 | | 203 | blk.19.attn_output.weight | 0x227d34440 | 0xa00000 | | 204 | blk.19.attn_q_norm.weight | 0x228734440 | 0x400 | | 205 | blk.19.attn_q.weight | 0x228734840 | 0xa00000 | | 206 | blk.19.attn_v.weight | 0x229134840 | 0x280000 | | 207 | blk.2.attn_norm.weight | 0x2293b4840 | 0x2800 | | 208 | blk.2.layer_output_scale.weight | 0x2293b7040 | 0x4 | | 209 | blk.2.ffn_down.weight | 0x2293b7060 | 0x3200000 | | 210 | blk.2.ffn_gate.weight | 0x22c5b7060 | 0x3200000 | | 211 | blk.2.ffn_up.weight | 0x22f7b7060 | 0x3200000 | | 212 | blk.2.inp_gate.weight | 0x2329b7060 | 0x140000 | | 213 | blk.2.proj.weight | 0x232af7060 | 0x140000 | | 214 | blk.2.post_attention_norm.weight | 0x232c37060 | 0x2800 | | 215 | blk.2.post_ffw_norm.weight | 0x232c39860 | 0x2800 | | 216 | blk.2.post_norm.weight | 0x232c3c060 | 0x2800 | | 217 | blk.2.ffn_norm.weight | 0x232c3e860 | 0x2800 | | 218 | blk.2.attn_k_norm.weight | 0x232c41060 | 0x400 | | 219 | blk.2.attn_k.weight | 0x232c41460 | 0x280000 | | 220 | blk.2.attn_output.weight | 0x232ec1460 | 0xa00000 | | 221 | blk.2.attn_q_norm.weight | 0x2338c1460 | 0x400 | | 222 | blk.2.attn_q.weight | 0x2338c1860 | 0xa00000 | | 223 | blk.2.attn_v.weight | 0x2342c1860 | 0x280000 | | 224 | blk.20.attn_norm.weight | 0x234541860 | 0x2800 | | 225 | blk.20.layer_output_scale.weight | 0x234544060 | 0x4 | | 226 | blk.20.ffn_down.weight | 0x234544080 | 0x3200000 | | 227 | blk.20.ffn_gate.weight | 0x237744080 | 0x3200000 | | 228 | blk.20.ffn_up.weight | 0x23a944080 | 0x3200000 | | 229 | blk.20.inp_gate.weight | 0x23db44080 | 0x140000 | | 230 | blk.20.proj.weight | 0x23dc84080 | 0x140000 | | 231 | blk.20.post_attention_norm.weight | 0x23ddc4080 | 0x2800 | | 232 | blk.20.post_ffw_norm.weight | 0x23ddc6880 | 0x2800 | | 233 | blk.20.post_norm.weight | 0x23ddc9080 | 0x2800 | | 234 | blk.20.ffn_norm.weight | 0x23ddcb880 | 0x2800 | | 235 | blk.20.attn_k_norm.weight | 0x23ddce080 | 0x400 | | 236 | blk.20.attn_k.weight | 0x23ddce480 | 0x280000 | | 237 | blk.20.attn_output.weight | 0x23e04e480 | 0xa00000 | | 238 | blk.20.attn_q_norm.weight | 0x23ea4e480 | 0x400 | | 239 | blk.20.attn_q.weight | 0x23ea4e880 | 0xa00000 | | 240 | blk.20.attn_v.weight | 0x23f44e880 | 0x280000 | | 241 | blk.21.attn_norm.weight | 0x23f6ce880 | 0x2800 | | 242 | blk.21.layer_output_scale.weight | 0x23f6d1080 | 0x4 | | 243 | blk.21.ffn_down.weight | 0x23f6d10a0 | 0x3200000 | | 244 | blk.21.ffn_gate.weight | 0x2428d10a0 | 0x3200000 | | 245 | blk.21.ffn_up.weight | 0x245ad10a0 | 0x3200000 | | 246 | blk.21.inp_gate.weight | 0x248cd10a0 | 0x140000 | | 247 | blk.21.proj.weight | 0x248e110a0 | 0x140000 | | 248 | blk.21.post_attention_norm.weight | 0x248f510a0 | 0x2800 | | 249 | blk.21.post_ffw_norm.weight | 0x248f538a0 | 0x2800 | | 250 | blk.21.post_norm.weight | 0x248f560a0 | 0x2800 | | 251 | blk.21.ffn_norm.weight | 0x248f588a0 | 0x2800 | | 252 | blk.21.attn_k_norm.weight | 0x248f5b0a0 | 0x400 | | 253 | blk.21.attn_k.weight | 0x248f5b4a0 | 0x280000 | | 254 | blk.21.attn_output.weight | 0x2491db4a0 | 0xa00000 | | 255 | blk.21.attn_q_norm.weight | 0x249bdb4a0 | 0x400 | | 256 | blk.21.attn_q.weight | 0x249bdb8a0 | 0xa00000 | | 257 | blk.21.attn_v.weight | 0x24a5db8a0 | 0x280000 | | 258 | blk.22.attn_norm.weight | 0x24a85b8a0 | 0x2800 | | 259 | blk.22.layer_output_scale.weight | 0x24a85e0a0 | 0x4 | | 260 | blk.22.ffn_down.weight | 0x24a85e0c0 | 0x3200000 | | 261 | blk.22.ffn_gate.weight | 0x24da5e0c0 | 0x3200000 | | 262 | blk.22.ffn_up.weight | 0x250c5e0c0 | 0x3200000 | | 263 | blk.22.inp_gate.weight | 0x253e5e0c0 | 0x140000 | | 264 | blk.22.proj.weight | 0x253f9e0c0 | 0x140000 | | 265 | blk.22.post_attention_norm.weight | 0x2540de0c0 | 0x2800 | | 266 | blk.22.post_ffw_norm.weight | 0x2540e08c0 | 0x2800 | | 267 | blk.22.post_norm.weight | 0x2540e30c0 | 0x2800 | | 268 | blk.22.ffn_norm.weight | 0x2540e58c0 | 0x2800 | | 269 | blk.22.attn_k_norm.weight | 0x2540e80c0 | 0x400 | | 270 | blk.22.attn_k.weight | 0x2540e84c0 | 0x280000 | | 271 | blk.22.attn_output.weight | 0x2543684c0 | 0xa00000 | | 272 | blk.22.attn_q_norm.weight | 0x254d684c0 | 0x400 | | 273 | blk.22.attn_q.weight | 0x254d688c0 | 0xa00000 | | 274 | blk.22.attn_v.weight | 0x2557688c0 | 0x280000 | | 275 | blk.23.attn_norm.weight | 0x2559e88c0 | 0x2800 | | 276 | blk.23.layer_output_scale.weight | 0x2559eb0c0 | 0x4 | | 277 | blk.23.ffn_down.weight | 0x2559eb0e0 | 0x3200000 | | 278 | blk.23.ffn_gate.weight | 0x258beb0e0 | 0x3200000 | | 279 | blk.23.ffn_up.weight | 0x25bdeb0e0 | 0x3200000 | | 280 | blk.23.inp_gate.weight | 0x25efeb0e0 | 0x140000 | | 281 | blk.23.proj.weight | 0x25f12b0e0 | 0x140000 | | 282 | blk.23.post_attention_norm.weight | 0x25f26b0e0 | 0x2800 | | 283 | blk.23.post_ffw_norm.weight | 0x25f26d8e0 | 0x2800 | | 284 | blk.23.post_norm.weight | 0x25f2700e0 | 0x2800 | | 285 | blk.23.ffn_norm.weight | 0x25f2728e0 | 0x2800 | | 286 | blk.23.attn_k_norm.weight | 0x25f2750e0 | 0x800 | | 287 | blk.23.attn_k.weight | 0x25f2758e0 | 0x500000 | | 288 | blk.23.attn_output.weight | 0x25f7758e0 | 0x1400000 | | 289 | blk.23.attn_q_norm.weight | 0x260b758e0 | 0x800 | | 290 | blk.23.attn_q.weight | 0x260b760e0 | 0x1400000 | | 291 | blk.23.attn_v.weight | 0x261f760e0 | 0x500000 | | 292 | blk.24.attn_norm.weight | 0x2624760e0 | 0x2800 | | 293 | blk.24.layer_output_scale.weight | 0x2624788e0 | 0x4 | | 294 | blk.24.ffn_down.weight | 0x262478900 | 0x3200000 | | 295 | blk.24.ffn_gate.weight | 0x265678900 | 0x3200000 | | 296 | blk.24.ffn_up.weight | 0x268878900 | 0x3200000 | | 297 | blk.24.inp_gate.weight | 0x26ba78900 | 0x140000 | | 298 | blk.24.proj.weight | 0x26bbb8900 | 0x140000 | | 299 | blk.24.post_attention_norm.weight | 0x26bcf8900 | 0x2800 | | 300 | blk.24.post_ffw_norm.weight | 0x26bcfb100 | 0x2800 | | 301 | blk.24.post_norm.weight | 0x26bcfd900 | 0x2800 | | 302 | blk.24.ffn_norm.weight | 0x26bd00100 | 0x2800 | | 303 | blk.24.attn_k_norm.weight | 0x26bd02900 | 0x400 | | 304 | blk.24.attn_k.weight | 0x26bd02d00 | 0x280000 | | 305 | blk.24.attn_output.weight | 0x26bf82d00 | 0xa00000 | | 306 | blk.24.attn_q_norm.weight | 0x26c982d00 | 0x400 | | 307 | blk.24.attn_q.weight | 0x26c983100 | 0xa00000 | | 308 | blk.24.attn_v.weight | 0x26d383100 | 0x280000 | | 309 | blk.25.attn_norm.weight | 0x26d603100 | 0x2800 | | 310 | blk.25.layer_output_scale.weight | 0x26d605900 | 0x4 | | 311 | blk.25.ffn_down.weight | 0x26d605920 | 0x3200000 | | 312 | blk.25.ffn_gate.weight | 0x270805920 | 0x3200000 | | 313 | blk.25.ffn_up.weight | 0x273a05920 | 0x3200000 | | 314 | blk.25.inp_gate.weight | 0x276c05920 | 0x140000 | | 315 | blk.25.proj.weight | 0x276d45920 | 0x140000 | | 316 | blk.25.post_attention_norm.weight | 0x276e85920 | 0x2800 | | 317 | blk.25.post_ffw_norm.weight | 0x276e88120 | 0x2800 | | 318 | blk.25.post_norm.weight | 0x276e8a920 | 0x2800 | | 319 | blk.25.ffn_norm.weight | 0x276e8d120 | 0x2800 | | 320 | blk.25.attn_k_norm.weight | 0x276e8f920 | 0x400 | | 321 | blk.25.attn_k.weight | 0x276e8fd20 | 0x280000 | | 322 | blk.25.attn_output.weight | 0x27710fd20 | 0xa00000 | | 323 | blk.25.attn_q_norm.weight | 0x277b0fd20 | 0x400 | | 324 | blk.25.attn_q.weight | 0x277b10120 | 0xa00000 | | 325 | blk.25.attn_v.weight | 0x278510120 | 0x280000 | | 326 | blk.26.attn_norm.weight | 0x278790120 | 0x2800 | | 327 | blk.26.layer_output_scale.weight | 0x278792920 | 0x4 | | 328 | blk.26.ffn_down.weight | 0x278792940 | 0x3200000 | | 329 | blk.26.ffn_gate.weight | 0x27b992940 | 0x3200000 | | 330 | blk.26.ffn_up.weight | 0x27eb92940 | 0x3200000 | | 331 | blk.26.inp_gate.weight | 0x281d92940 | 0x140000 | | 332 | blk.26.proj.weight | 0x281ed2940 | 0x140000 | | 333 | blk.26.post_attention_norm.weight | 0x282012940 | 0x2800 | | 334 | blk.26.post_ffw_norm.weight | 0x282015140 | 0x2800 | | 335 | blk.26.post_norm.weight | 0x282017940 | 0x2800 | | 336 | blk.26.ffn_norm.weight | 0x28201a140 | 0x2800 | | 337 | blk.26.attn_k_norm.weight | 0x28201c940 | 0x400 | | 338 | blk.26.attn_k.weight | 0x28201cd40 | 0x280000 | | 339 | blk.26.attn_output.weight | 0x28229cd40 | 0xa00000 | | 340 | blk.26.attn_q_norm.weight | 0x282c9cd40 | 0x400 | | 341 | blk.26.attn_q.weight | 0x282c9d140 | 0xa00000 | | 342 | blk.26.attn_v.weight | 0x28369d140 | 0x280000 | | 343 | blk.27.attn_norm.weight | 0x28391d140 | 0x2800 | | 344 | blk.27.layer_output_scale.weight | 0x28391f940 | 0x4 | | 345 | blk.27.ffn_down.weight | 0x28391f960 | 0x3200000 | | 346 | blk.27.ffn_gate.weight | 0x286b1f960 | 0x3200000 | | 347 | blk.27.ffn_up.weight | 0x289d1f960 | 0x3200000 | | 348 | blk.27.inp_gate.weight | 0x28cf1f960 | 0x140000 | | 349 | blk.27.proj.weight | 0x28d05f960 | 0x140000 | | 350 | blk.27.post_attention_norm.weight | 0x28d19f960 | 0x2800 | | 351 | blk.27.post_ffw_norm.weight | 0x28d1a2160 | 0x2800 | | 352 | blk.27.post_norm.weight | 0x28d1a4960 | 0x2800 | | 353 | blk.27.ffn_norm.weight | 0x28d1a7160 | 0x2800 | | 354 | blk.27.attn_k_norm.weight | 0x28d1a9960 | 0x400 | | 355 | blk.27.attn_k.weight | 0x28d1a9d60 | 0x280000 | | 356 | blk.27.attn_output.weight | 0x28d429d60 | 0xa00000 | | 357 | blk.27.attn_q_norm.weight | 0x28de29d60 | 0x400 | | 358 | blk.27.attn_q.weight | 0x28de2a160 | 0xa00000 | | 359 | blk.27.attn_v.weight | 0x28e82a160 | 0x280000 | | 360 | blk.28.attn_norm.weight | 0x28eaaa160 | 0x2800 | | 361 | blk.28.layer_output_scale.weight | 0x28eaac960 | 0x4 | | 362 | blk.28.ffn_down.weight | 0x28eaac980 | 0x3200000 | | 363 | blk.28.ffn_gate.weight | 0x291cac980 | 0x3200000 | | 364 | blk.28.ffn_up.weight | 0x294eac980 | 0x3200000 | | 365 | blk.28.inp_gate.weight | 0x2980ac980 | 0x140000 | | 366 | blk.28.proj.weight | 0x2981ec980 | 0x140000 | | 367 | blk.28.post_attention_norm.weight | 0x29832c980 | 0x2800 | | 368 | blk.28.post_ffw_norm.weight | 0x29832f180 | 0x2800 | | 369 | blk.28.post_norm.weight | 0x298331980 | 0x2800 | | 370 | blk.28.ffn_norm.weight | 0x298334180 | 0x2800 | | 371 | blk.28.attn_k_norm.weight | 0x298336980 | 0x400 | | 372 | blk.28.attn_k.weight | 0x298336d80 | 0x280000 | | 373 | blk.28.attn_output.weight | 0x2985b6d80 | 0xa00000 | | 374 | blk.28.attn_q_norm.weight | 0x298fb6d80 | 0x400 | | 375 | blk.28.attn_q.weight | 0x298fb7180 | 0xa00000 | | 376 | blk.28.attn_v.weight | 0x2999b7180 | 0x280000 | | 377 | blk.29.attn_norm.weight | 0x299c37180 | 0x2800 | | 378 | blk.29.layer_output_scale.weight | 0x299c39980 | 0x4 | | 379 | blk.29.ffn_down.weight | 0x299c399a0 | 0x3200000 | | 380 | blk.29.ffn_gate.weight | 0x29ce399a0 | 0x3200000 | | 381 | blk.29.ffn_up.weight | 0x2a00399a0 | 0x3200000 | | 382 | blk.29.inp_gate.weight | 0x2a32399a0 | 0x140000 | | 383 | blk.29.proj.weight | 0x2a33799a0 | 0x140000 | | 384 | blk.29.post_attention_norm.weight | 0x2a34b99a0 | 0x2800 | | 385 | blk.29.post_ffw_norm.weight | 0x2a34bc1a0 | 0x2800 | | 386 | blk.29.post_norm.weight | 0x2a34be9a0 | 0x2800 | | 387 | blk.29.ffn_norm.weight | 0x2a34c11a0 | 0x2800 | | 388 | blk.29.attn_k_norm.weight | 0x2a34c39a0 | 0x800 | | 389 | blk.29.attn_k.weight | 0x2a34c41a0 | 0x500000 | | 390 | blk.29.attn_output.weight | 0x2a39c41a0 | 0x1400000 | | 391 | blk.29.attn_q_norm.weight | 0x2a4dc41a0 | 0x800 | | 392 | blk.29.attn_q.weight | 0x2a4dc49a0 | 0x1400000 | | 393 | blk.29.attn_v.weight | 0x2a61c49a0 | 0x500000 | | 394 | blk.3.attn_norm.weight | 0x2a66c49a0 | 0x2800 | | 395 | blk.3.layer_output_scale.weight | 0x2a66c71a0 | 0x4 | | 396 | blk.3.ffn_down.weight | 0x2a66c71c0 | 0x3200000 | | 397 | blk.3.ffn_gate.weight | 0x2a98c71c0 | 0x3200000 | | 398 | blk.3.ffn_up.weight | 0x2acac71c0 | 0x3200000 | | 399 | blk.3.inp_gate.weight | 0x2afcc71c0 | 0x140000 | | 400 | blk.3.proj.weight | 0x2afe071c0 | 0x140000 | | 401 | blk.3.post_attention_norm.weight | 0x2aff471c0 | 0x2800 | | 402 | blk.3.post_ffw_norm.weight | 0x2aff499c0 | 0x2800 | | 403 | blk.3.post_norm.weight | 0x2aff4c1c0 | 0x2800 | | 404 | blk.3.ffn_norm.weight | 0x2aff4e9c0 | 0x2800 | | 405 | blk.3.attn_k_norm.weight | 0x2aff511c0 | 0x400 | | 406 | blk.3.attn_k.weight | 0x2aff515c0 | 0x280000 | | 407 | blk.3.attn_output.weight | 0x2b01d15c0 | 0xa00000 | | 408 | blk.3.attn_q_norm.weight | 0x2b0bd15c0 | 0x400 | | 409 | blk.3.attn_q.weight | 0x2b0bd19c0 | 0xa00000 | | 410 | blk.3.attn_v.weight | 0x2b15d19c0 | 0x280000 | | 411 | blk.30.attn_norm.weight | 0x2b18519c0 | 0x2800 | | 412 | blk.30.layer_output_scale.weight | 0x2b18541c0 | 0x4 | | 413 | blk.30.ffn_down.weight | 0x2b18541e0 | 0x3200000 | | 414 | blk.30.ffn_gate.weight | 0x2b4a541e0 | 0x3200000 | | 415 | blk.30.ffn_up.weight | 0x2b7c541e0 | 0x3200000 | | 416 | blk.30.inp_gate.weight | 0x2bae541e0 | 0x140000 | | 417 | blk.30.proj.weight | 0x2baf941e0 | 0x140000 | | 418 | blk.30.post_attention_norm.weight | 0x2bb0d41e0 | 0x2800 | | 419 | blk.30.post_ffw_norm.weight | 0x2bb0d69e0 | 0x2800 | | 420 | blk.30.post_norm.weight | 0x2bb0d91e0 | 0x2800 | | 421 | blk.30.ffn_norm.weight | 0x2bb0db9e0 | 0x2800 | | 422 | blk.30.attn_k_norm.weight | 0x2bb0de1e0 | 0x400 | | 423 | blk.30.attn_k.weight | 0x2bb0de5e0 | 0x280000 | | 424 | blk.30.attn_output.weight | 0x2bb35e5e0 | 0xa00000 | | 425 | blk.30.attn_q_norm.weight | 0x2bbd5e5e0 | 0x400 | | 426 | blk.30.attn_q.weight | 0x2bbd5e9e0 | 0xa00000 | | 427 | blk.30.attn_v.weight | 0x2bc75e9e0 | 0x280000 | | 428 | blk.31.attn_norm.weight | 0x2bc9de9e0 | 0x2800 | | 429 | blk.31.layer_output_scale.weight | 0x2bc9e11e0 | 0x4 | | 430 | blk.31.ffn_down.weight | 0x2bc9e1200 | 0x3200000 | | 431 | blk.31.ffn_gate.weight | 0x2bfbe1200 | 0x3200000 | | 432 | blk.31.ffn_up.weight | 0x2c2de1200 | 0x3200000 | | 433 | blk.31.inp_gate.weight | 0x2c5fe1200 | 0x140000 | | 434 | blk.31.proj.weight | 0x2c6121200 | 0x140000 | | 435 | blk.31.post_attention_norm.weight | 0x2c6261200 | 0x2800 | | 436 | blk.31.post_ffw_norm.weight | 0x2c6263a00 | 0x2800 | | 437 | blk.31.post_norm.weight | 0x2c6266200 | 0x2800 | | 438 | blk.31.ffn_norm.weight | 0x2c6268a00 | 0x2800 | | 439 | blk.31.attn_k_norm.weight | 0x2c626b200 | 0x400 | | 440 | blk.31.attn_k.weight | 0x2c626b600 | 0x280000 | | 441 | blk.31.attn_output.weight | 0x2c64eb600 | 0xa00000 | | 442 | blk.31.attn_q_norm.weight | 0x2c6eeb600 | 0x400 | | 443 | blk.31.attn_q.weight | 0x2c6eeba00 | 0xa00000 | | 444 | blk.31.attn_v.weight | 0x2c78eba00 | 0x280000 | | 445 | blk.32.attn_norm.weight | 0x2c7b6ba00 | 0x2800 | | 446 | blk.32.layer_output_scale.weight | 0x2c7b6e200 | 0x4 | | 447 | blk.32.ffn_down.weight | 0x2c7b6e220 | 0x3200000 | | 448 | blk.32.ffn_gate.weight | 0x2cad6e220 | 0x3200000 | | 449 | blk.32.ffn_up.weight | 0x2cdf6e220 | 0x3200000 | | 450 | blk.32.inp_gate.weight | 0x2d116e220 | 0x140000 | | 451 | blk.32.proj.weight | 0x2d12ae220 | 0x140000 | | 452 | blk.32.post_attention_norm.weight | 0x2d13ee220 | 0x2800 | | 453 | blk.32.post_ffw_norm.weight | 0x2d13f0a20 | 0x2800 | | 454 | blk.32.post_norm.weight | 0x2d13f3220 | 0x2800 | | 455 | blk.32.ffn_norm.weight | 0x2d13f5a20 | 0x2800 | | 456 | blk.32.attn_k_norm.weight | 0x2d13f8220 | 0x400 | | 457 | blk.32.attn_k.weight | 0x2d13f8620 | 0x280000 | | 458 | blk.32.attn_output.weight | 0x2d1678620 | 0xa00000 | | 459 | blk.32.attn_q_norm.weight | 0x2d2078620 | 0x400 | | 460 | blk.32.attn_q.weight | 0x2d2078a20 | 0xa00000 | | 461 | blk.32.attn_v.weight | 0x2d2a78a20 | 0x280000 | | 462 | blk.33.attn_norm.weight | 0x2d2cf8a20 | 0x2800 | | 463 | blk.33.layer_output_scale.weight | 0x2d2cfb220 | 0x4 | | 464 | blk.33.ffn_down.weight | 0x2d2cfb240 | 0x3200000 | | 465 | blk.33.ffn_gate.weight | 0x2d5efb240 | 0x3200000 | | 466 | blk.33.ffn_up.weight | 0x2d90fb240 | 0x3200000 | | 467 | blk.33.inp_gate.weight | 0x2dc2fb240 | 0x140000 | | 468 | blk.33.proj.weight | 0x2dc43b240 | 0x140000 | | 469 | blk.33.post_attention_norm.weight | 0x2dc57b240 | 0x2800 | | 470 | blk.33.post_ffw_norm.weight | 0x2dc57da40 | 0x2800 | | 471 | blk.33.post_norm.weight | 0x2dc580240 | 0x2800 | | 472 | blk.33.ffn_norm.weight | 0x2dc582a40 | 0x2800 | | 473 | blk.33.attn_k_norm.weight | 0x2dc585240 | 0x400 | | 474 | blk.33.attn_k.weight | 0x2dc585640 | 0x280000 | | 475 | blk.33.attn_output.weight | 0x2dc805640 | 0xa00000 | | 476 | blk.33.attn_q_norm.weight | 0x2dd205640 | 0x400 | | 477 | blk.33.attn_q.weight | 0x2dd205a40 | 0xa00000 | | 478 | blk.33.attn_v.weight | 0x2ddc05a40 | 0x280000 | | 479 | blk.34.attn_norm.weight | 0x2dde85a40 | 0x2800 | | 480 | blk.34.layer_output_scale.weight | 0x2dde88240 | 0x4 | | 481 | blk.34.ffn_down.weight | 0x2dde88260 | 0x3200000 | | 482 | blk.34.ffn_gate.weight | 0x2e1088260 | 0x3200000 | | 483 | blk.34.ffn_up.weight | 0x2e4288260 | 0x3200000 | | 484 | blk.34.inp_gate.weight | 0x2e7488260 | 0x140000 | | 485 | blk.34.proj.weight | 0x2e75c8260 | 0x140000 | | 486 | blk.34.post_attention_norm.weight | 0x2e7708260 | 0x2800 | | 487 | blk.34.post_ffw_norm.weight | 0x2e770aa60 | 0x2800 | | 488 | blk.34.post_norm.weight | 0x2e770d260 | 0x2800 | | 489 | blk.34.ffn_norm.weight | 0x2e770fa60 | 0x2800 | | 490 | blk.34.attn_k_norm.weight | 0x2e7712260 | 0x400 | | 491 | blk.34.attn_k.weight | 0x2e7712660 | 0x280000 | | 492 | blk.34.attn_output.weight | 0x2e7992660 | 0xa00000 | | 493 | blk.34.attn_q_norm.weight | 0x2e8392660 | 0x400 | | 494 | blk.34.attn_q.weight | 0x2e8392a60 | 0xa00000 | | 495 | blk.34.attn_v.weight | 0x2e8d92a60 | 0x280000 | | 496 | blk.35.attn_norm.weight | 0x2e9012a60 | 0x2800 | | 497 | blk.35.layer_output_scale.weight | 0x2e9015260 | 0x4 | | 498 | blk.35.ffn_down.weight | 0x2e9015280 | 0x3200000 | | 499 | blk.35.ffn_gate.weight | 0x2ec215280 | 0x3200000 | | 500 | blk.35.ffn_up.weight | 0x2ef415280 | 0x3200000 | | 501 | blk.35.inp_gate.weight | 0x2f2615280 | 0x140000 | | 502 | blk.35.proj.weight | 0x2f2755280 | 0x140000 | | 503 | blk.35.post_attention_norm.weight | 0x2f2895280 | 0x2800 | | 504 | blk.35.post_ffw_norm.weight | 0x2f2897a80 | 0x2800 | | 505 | blk.35.post_norm.weight | 0x2f289a280 | 0x2800 | | 506 | blk.35.ffn_norm.weight | 0x2f289ca80 | 0x2800 | | 507 | blk.35.attn_k_norm.weight | 0x2f289f280 | 0x800 | | 508 | blk.35.attn_k.weight | 0x2f289fa80 | 0x500000 | | 509 | blk.35.attn_output.weight | 0x2f2d9fa80 | 0x1400000 | | 510 | blk.35.attn_q_norm.weight | 0x2f419fa80 | 0x800 | | 511 | blk.35.attn_q.weight | 0x2f41a0280 | 0x1400000 | | 512 | blk.35.attn_v.weight | 0x2f55a0280 | 0x500000 | | 513 | blk.36.attn_norm.weight | 0x2f5aa0280 | 0x2800 | | 514 | blk.36.layer_output_scale.weight | 0x2f5aa2a80 | 0x4 | | 515 | blk.36.ffn_down.weight | 0x2f5aa2aa0 | 0x3200000 | | 516 | blk.36.ffn_gate.weight | 0x2f8ca2aa0 | 0x3200000 | | 517 | blk.36.ffn_up.weight | 0x2fbea2aa0 | 0x3200000 | | 518 | blk.36.inp_gate.weight | 0x2ff0a2aa0 | 0x140000 | | 519 | blk.36.proj.weight | 0x2ff1e2aa0 | 0x140000 | | 520 | blk.36.post_attention_norm.weight | 0x2ff322aa0 | 0x2800 | | 521 | blk.36.post_ffw_norm.weight | 0x2ff3252a0 | 0x2800 | | 522 | blk.36.post_norm.weight | 0x2ff327aa0 | 0x2800 | | 523 | blk.36.ffn_norm.weight | 0x2ff32a2a0 | 0x2800 | | 524 | blk.36.attn_k_norm.weight | 0x2ff32caa0 | 0x400 | | 525 | blk.36.attn_k.weight | 0x2ff32cea0 | 0x280000 | | 526 | blk.36.attn_output.weight | 0x2ff5acea0 | 0xa00000 | | 527 | blk.36.attn_q_norm.weight | 0x2fffacea0 | 0x400 | | 528 | blk.36.attn_q.weight | 0x2fffad2a0 | 0xa00000 | | 529 | blk.36.attn_v.weight | 0x3009ad2a0 | 0x280000 | | 530 | blk.37.attn_norm.weight | 0x300c2d2a0 | 0x2800 | | 531 | blk.37.layer_output_scale.weight | 0x300c2faa0 | 0x4 | | 532 | blk.37.ffn_down.weight | 0x300c2fac0 | 0x3200000 | | 533 | blk.37.ffn_gate.weight | 0x303e2fac0 | 0x3200000 | | 534 | blk.37.ffn_up.weight | 0x30702fac0 | 0x3200000 | | 535 | blk.37.inp_gate.weight | 0x30a22fac0 | 0x140000 | | 536 | blk.37.proj.weight | 0x30a36fac0 | 0x140000 | | 537 | blk.37.post_attention_norm.weight | 0x30a4afac0 | 0x2800 | | 538 | blk.37.post_ffw_norm.weight | 0x30a4b22c0 | 0x2800 | | 539 | blk.37.post_norm.weight | 0x30a4b4ac0 | 0x2800 | | 540 | blk.37.ffn_norm.weight | 0x30a4b72c0 | 0x2800 | | 541 | blk.37.attn_k_norm.weight | 0x30a4b9ac0 | 0x400 | | 542 | blk.37.attn_k.weight | 0x30a4b9ec0 | 0x280000 | | 543 | blk.37.attn_output.weight | 0x30a739ec0 | 0xa00000 | | 544 | blk.37.attn_q_norm.weight | 0x30b139ec0 | 0x400 | | 545 | blk.37.attn_q.weight | 0x30b13a2c0 | 0xa00000 | | 546 | blk.37.attn_v.weight | 0x30bb3a2c0 | 0x280000 | | 547 | blk.38.attn_norm.weight | 0x30bdba2c0 | 0x2800 | | 548 | blk.38.layer_output_scale.weight | 0x30bdbcac0 | 0x4 | | 549 | blk.38.ffn_down.weight | 0x30bdbcae0 | 0x3200000 | | 550 | blk.38.ffn_gate.weight | 0x30efbcae0 | 0x3200000 | | 551 | blk.38.ffn_up.weight | 0x3121bcae0 | 0x3200000 | | 552 | blk.38.inp_gate.weight | 0x3153bcae0 | 0x140000 | | 553 | blk.38.proj.weight | 0x3154fcae0 | 0x140000 | | 554 | blk.38.post_attention_norm.weight | 0x31563cae0 | 0x2800 | | 555 | blk.38.post_ffw_norm.weight | 0x31563f2e0 | 0x2800 | | 556 | blk.38.post_norm.weight | 0x315641ae0 | 0x2800 | | 557 | blk.38.ffn_norm.weight | 0x3156442e0 | 0x2800 | | 558 | blk.38.attn_k_norm.weight | 0x315646ae0 | 0x400 | | 559 | blk.38.attn_k.weight | 0x315646ee0 | 0x280000 | | 560 | blk.38.attn_output.weight | 0x3158c6ee0 | 0xa00000 | | 561 | blk.38.attn_q_norm.weight | 0x3162c6ee0 | 0x400 | | 562 | blk.38.attn_q.weight | 0x3162c72e0 | 0xa00000 | | 563 | blk.38.attn_v.weight | 0x316cc72e0 | 0x280000 | | 564 | blk.39.attn_norm.weight | 0x316f472e0 | 0x2800 | | 565 | blk.39.layer_output_scale.weight | 0x316f49ae0 | 0x4 | | 566 | blk.39.ffn_down.weight | 0x316f49b00 | 0x3200000 | | 567 | blk.39.ffn_gate.weight | 0x31a149b00 | 0x3200000 | | 568 | blk.39.ffn_up.weight | 0x31d349b00 | 0x3200000 | | 569 | blk.39.inp_gate.weight | 0x320549b00 | 0x140000 | | 570 | blk.39.proj.weight | 0x320689b00 | 0x140000 | | 571 | blk.39.post_attention_norm.weight | 0x3207c9b00 | 0x2800 | | 572 | blk.39.post_ffw_norm.weight | 0x3207cc300 | 0x2800 | | 573 | blk.39.post_norm.weight | 0x3207ceb00 | 0x2800 | | 574 | blk.39.ffn_norm.weight | 0x3207d1300 | 0x2800 | | 575 | blk.39.attn_k_norm.weight | 0x3207d3b00 | 0x400 | | 576 | blk.39.attn_k.weight | 0x3207d3f00 | 0x280000 | | 577 | blk.39.attn_output.weight | 0x320a53f00 | 0xa00000 | | 578 | blk.39.attn_q_norm.weight | 0x321453f00 | 0x400 | | 579 | blk.39.attn_q.weight | 0x321454300 | 0xa00000 | | 580 | blk.39.attn_v.weight | 0x321e54300 | 0x280000 | | 581 | blk.4.attn_norm.weight | 0x3220d4300 | 0x2800 | | 582 | blk.4.layer_output_scale.weight | 0x3220d6b00 | 0x4 | | 583 | blk.4.ffn_down.weight | 0x3220d6b20 | 0x3200000 | | 584 | blk.4.ffn_gate.weight | 0x3252d6b20 | 0x3200000 | | 585 | blk.4.ffn_up.weight | 0x3284d6b20 | 0x3200000 | | 586 | blk.4.inp_gate.weight | 0x32b6d6b20 | 0x140000 | | 587 | blk.4.proj.weight | 0x32b816b20 | 0x140000 | | 588 | blk.4.post_attention_norm.weight | 0x32b956b20 | 0x2800 | | 589 | blk.4.post_ffw_norm.weight | 0x32b959320 | 0x2800 | | 590 | blk.4.post_norm.weight | 0x32b95bb20 | 0x2800 | | 591 | blk.4.ffn_norm.weight | 0x32b95e320 | 0x2800 | | 592 | blk.4.attn_k_norm.weight | 0x32b960b20 | 0x400 | | 593 | blk.4.attn_k.weight | 0x32b960f20 | 0x280000 | | 594 | blk.4.attn_output.weight | 0x32bbe0f20 | 0xa00000 | | 595 | blk.4.attn_q_norm.weight | 0x32c5e0f20 | 0x400 | | 596 | blk.4.attn_q.weight | 0x32c5e1320 | 0xa00000 | | 597 | blk.4.attn_v.weight | 0x32cfe1320 | 0x280000 | | 598 | blk.40.attn_norm.weight | 0x32d261320 | 0x2800 | | 599 | blk.40.layer_output_scale.weight | 0x32d263b20 | 0x4 | | 600 | blk.40.ffn_down.weight | 0x32d263b40 | 0x3200000 | | 601 | blk.40.ffn_gate.weight | 0x330463b40 | 0x3200000 | | 602 | blk.40.ffn_up.weight | 0x333663b40 | 0x3200000 | | 603 | blk.40.inp_gate.weight | 0x336863b40 | 0x140000 | | 604 | blk.40.proj.weight | 0x3369a3b40 | 0x140000 | | 605 | blk.40.post_attention_norm.weight | 0x336ae3b40 | 0x2800 | | 606 | blk.40.post_ffw_norm.weight | 0x336ae6340 | 0x2800 | | 607 | blk.40.post_norm.weight | 0x336ae8b40 | 0x2800 | | 608 | blk.40.ffn_norm.weight | 0x336aeb340 | 0x2800 | | 609 | blk.40.attn_k_norm.weight | 0x336aedb40 | 0x400 | | 610 | blk.40.attn_k.weight | 0x336aedf40 | 0x280000 | | 611 | blk.40.attn_output.weight | 0x336d6df40 | 0xa00000 | | 612 | blk.40.attn_q_norm.weight | 0x33776df40 | 0x400 | | 613 | blk.40.attn_q.weight | 0x33776e340 | 0xa00000 | | 614 | blk.40.attn_v.weight | 0x33816e340 | 0x280000 | | 615 | blk.41.attn_norm.weight | 0x3383ee340 | 0x2800 | | 616 | blk.41.layer_output_scale.weight | 0x3383f0b40 | 0x4 | | 617 | blk.41.ffn_down.weight | 0x3383f0b60 | 0x3200000 | | 618 | blk.41.ffn_gate.weight | 0x33b5f0b60 | 0x3200000 | | 619 | blk.41.ffn_up.weight | 0x33e7f0b60 | 0x3200000 | | 620 | blk.41.inp_gate.weight | 0x3419f0b60 | 0x140000 | | 621 | blk.41.proj.weight | 0x341b30b60 | 0x140000 | | 622 | blk.41.post_attention_norm.weight | 0x341c70b60 | 0x2800 | | 623 | blk.41.post_ffw_norm.weight | 0x341c73360 | 0x2800 | | 624 | blk.41.post_norm.weight | 0x341c75b60 | 0x2800 | | 625 | blk.41.ffn_norm.weight | 0x341c78360 | 0x2800 | | 626 | blk.41.attn_k_norm.weight | 0x341c7ab60 | 0x800 | | 627 | blk.41.attn_k.weight | 0x341c7b360 | 0x500000 | | 628 | blk.41.attn_output.weight | 0x34217b360 | 0x1400000 | | 629 | blk.41.attn_q_norm.weight | 0x34357b360 | 0x800 | | 630 | blk.41.attn_q.weight | 0x34357bb60 | 0x1400000 | | 631 | blk.41.attn_v.weight | 0x34497bb60 | 0x500000 | | 632 | blk.5.attn_norm.weight | 0x344e7bb60 | 0x2800 | | 633 | blk.5.layer_output_scale.weight | 0x344e7e360 | 0x4 | | 634 | blk.5.ffn_down.weight | 0x344e7e380 | 0x3200000 | | 635 | blk.5.ffn_gate.weight | 0x34807e380 | 0x3200000 | | 636 | blk.5.ffn_up.weight | 0x34b27e380 | 0x3200000 | | 637 | blk.5.inp_gate.weight | 0x34e47e380 | 0x140000 | | 638 | blk.5.proj.weight | 0x34e5be380 | 0x140000 | | 639 | blk.5.post_attention_norm.weight | 0x34e6fe380 | 0x2800 | | 640 | blk.5.post_ffw_norm.weight | 0x34e700b80 | 0x2800 | | 641 | blk.5.post_norm.weight | 0x34e703380 | 0x2800 | | 642 | blk.5.ffn_norm.weight | 0x34e705b80 | 0x2800 | | 643 | blk.5.attn_k_norm.weight | 0x34e708380 | 0x800 | | 644 | blk.5.attn_k.weight | 0x34e708b80 | 0x500000 | | 645 | blk.5.attn_output.weight | 0x34ec08b80 | 0x1400000 | | 646 | blk.5.attn_q_norm.weight | 0x350008b80 | 0x800 | | 647 | blk.5.attn_q.weight | 0x350009380 | 0x1400000 | | 648 | blk.5.attn_v.weight | 0x351409380 | 0x500000 | | 649 | blk.6.attn_norm.weight | 0x351909380 | 0x2800 | | 650 | blk.6.layer_output_scale.weight | 0x35190bb80 | 0x4 | | 651 | blk.6.ffn_down.weight | 0x35190bba0 | 0x3200000 | | 652 | blk.6.ffn_gate.weight | 0x354b0bba0 | 0x3200000 | | 653 | blk.6.ffn_up.weight | 0x357d0bba0 | 0x3200000 | | 654 | blk.6.inp_gate.weight | 0x35af0bba0 | 0x140000 | | 655 | blk.6.proj.weight | 0x35b04bba0 | 0x140000 | | 656 | blk.6.post_attention_norm.weight | 0x35b18bba0 | 0x2800 | | 657 | blk.6.post_ffw_norm.weight | 0x35b18e3a0 | 0x2800 | | 658 | blk.6.post_norm.weight | 0x35b190ba0 | 0x2800 | | 659 | blk.6.ffn_norm.weight | 0x35b1933a0 | 0x2800 | | 660 | blk.6.attn_k_norm.weight | 0x35b195ba0 | 0x400 | | 661 | blk.6.attn_k.weight | 0x35b195fa0 | 0x280000 | | 662 | blk.6.attn_output.weight | 0x35b415fa0 | 0xa00000 | | 663 | blk.6.attn_q_norm.weight | 0x35be15fa0 | 0x400 | | 664 | blk.6.attn_q.weight | 0x35be163a0 | 0xa00000 | | 665 | blk.6.attn_v.weight | 0x35c8163a0 | 0x280000 | | 666 | blk.7.attn_norm.weight | 0x35ca963a0 | 0x2800 | | 667 | blk.7.layer_output_scale.weight | 0x35ca98ba0 | 0x4 | | 668 | blk.7.ffn_down.weight | 0x35ca98bc0 | 0x3200000 | | 669 | blk.7.ffn_gate.weight | 0x35fc98bc0 | 0x3200000 | | 670 | blk.7.ffn_up.weight | 0x362e98bc0 | 0x3200000 | | 671 | blk.7.inp_gate.weight | 0x366098bc0 | 0x140000 | | 672 | blk.7.proj.weight | 0x3661d8bc0 | 0x140000 | | 673 | blk.7.post_attention_norm.weight | 0x366318bc0 | 0x2800 | | 674 | blk.7.post_ffw_norm.weight | 0x36631b3c0 | 0x2800 | | 675 | blk.7.post_norm.weight | 0x36631dbc0 | 0x2800 | | 676 | blk.7.ffn_norm.weight | 0x3663203c0 | 0x2800 | | 677 | blk.7.attn_k_norm.weight | 0x366322bc0 | 0x400 | | 678 | blk.7.attn_k.weight | 0x366322fc0 | 0x280000 | | 679 | blk.7.attn_output.weight | 0x3665a2fc0 | 0xa00000 | | 680 | blk.7.attn_q_norm.weight | 0x366fa2fc0 | 0x400 | | 681 | blk.7.attn_q.weight | 0x366fa33c0 | 0xa00000 | | 682 | blk.7.attn_v.weight | 0x3679a33c0 | 0x280000 | | 683 | blk.8.attn_norm.weight | 0x367c233c0 | 0x2800 | | 684 | blk.8.layer_output_scale.weight | 0x367c25bc0 | 0x4 | | 685 | blk.8.ffn_down.weight | 0x367c25be0 | 0x3200000 | | 686 | blk.8.ffn_gate.weight | 0x36ae25be0 | 0x3200000 | | 687 | blk.8.ffn_up.weight | 0x36e025be0 | 0x3200000 | | 688 | blk.8.inp_gate.weight | 0x371225be0 | 0x140000 | | 689 | blk.8.proj.weight | 0x371365be0 | 0x140000 | | 690 | blk.8.post_attention_norm.weight | 0x3714a5be0 | 0x2800 | | 691 | blk.8.post_ffw_norm.weight | 0x3714a83e0 | 0x2800 | | 692 | blk.8.post_norm.weight | 0x3714aabe0 | 0x2800 | | 693 | blk.8.ffn_norm.weight | 0x3714ad3e0 | 0x2800 | | 694 | blk.8.attn_k_norm.weight | 0x3714afbe0 | 0x400 | | 695 | blk.8.attn_k.weight | 0x3714affe0 | 0x280000 | | 696 | blk.8.attn_output.weight | 0x37172ffe0 | 0xa00000 | | 697 | blk.8.attn_q_norm.weight | 0x37212ffe0 | 0x400 | | 698 | blk.8.attn_q.weight | 0x3721303e0 | 0xa00000 | | 699 | blk.8.attn_v.weight | 0x372b303e0 | 0x280000 | | 700 | blk.9.attn_norm.weight | 0x372db03e0 | 0x2800 | | 701 | blk.9.layer_output_scale.weight | 0x372db2be0 | 0x4 | | 702 | blk.9.ffn_down.weight | 0x372db2c00 | 0x3200000 | | 703 | blk.9.ffn_gate.weight | 0x375fb2c00 | 0x3200000 | | 704 | blk.9.ffn_up.weight | 0x3791b2c00 | 0x3200000 | | 705 | blk.9.inp_gate.weight | 0x37c3b2c00 | 0x140000 | | 706 | blk.9.proj.weight | 0x37c4f2c00 | 0x140000 | | 707 | blk.9.post_attention_norm.weight | 0x37c632c00 | 0x2800 | | 708 | blk.9.post_ffw_norm.weight | 0x37c635400 | 0x2800 | | 709 | blk.9.post_norm.weight | 0x37c637c00 | 0x2800 | | 710 | blk.9.ffn_norm.weight | 0x37c63a400 | 0x2800 | | 711 | blk.9.attn_k_norm.weight | 0x37c63cc00 | 0x400 | | 712 | blk.9.attn_k.weight | 0x37c63d000 | 0x280000 | | 713 | blk.9.attn_output.weight | 0x37c8bd000 | 0xa00000 | | 714 | blk.9.attn_q_norm.weight | 0x37d2bd000 | 0x400 | | 715 | blk.9.attn_q.weight | 0x37d2bd400 | 0xa00000 | | 716 | blk.9.attn_v.weight | 0x37dcbd400 | 0x280000 | | 717 | output_norm.weight | 0x37df3d400 | 0x2800 | | 718 | per_layer_model_proj.weight | 0x37df3fc00 | 0x3480000 | | 719 | per_layer_proj_norm.weight | 0x3813bfc00 | 0x400 | ### Base Tensor Group : ~4B 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) | (~671M) 671088640 | 2560 x 262144 x 1 x 1 | F16 | 16.0000 | | 2 | per_layer_token_embd.weight | Per_Layer_Token_Embd (W) | ( ~3B) 2818572288 | 10752 x 262144 x 1 x 1 | F16 | 16.0000 | | 717 | output_norm.weight | Output Normalization (W) | ( ~3K) 2560 | 2560 x 1 x 1 x 1 | F32 | 32.0000 | | 718 | per_layer_model_proj.weight | Per_Layer_Model_Proj (W) | ( ~28M) 27525120 | 2560 x 10752 x 1 x 1 | F16 | 16.0000 | | 719 | per_layer_proj_norm.weight | Per_Layer_Proj_Norm (W) | ( 256) 256 | 256 x 1 x 1 x 1 | F32 | 32.0000 | - Total elements in base: ( ~4B) 3517189120 - Percentage of total elements: 46.78% - Bits per Weight (BPW) for base: 16.0000 bits ### Block 0 Tensor Group : ~93M Elements | T_ID | Tensor Layer Name | Human Friendly Tensor Layer Name | Elements | Shape | Type | BPW | | ---: | :------------------------------- | :--------------------------------------------- | :--------------- | :-------------------- | :--- | ------: | | 3 | blk.0.attn_norm.weight | Block 0 Attention Normalization (W) | ( ~3K) 2560 | 2560 x 1 x 1 x 1 | F32 | 32.0000 | | 4 | blk.0.layer_output_scale.weight | Block 0 Layer_Output_Scale (W) | ( 1) 1 | 1 x 1 x 1 x 1 | F32 | 32.0000 | | 5 | blk.0.ffn_down.weight | Block 0 Feed-Forward Network "Down" (W) | ( ~26M) 26214400 | 10240 x 2560 x 1 x 1 | F16 | 16.0000 | | 6 | blk.0.ffn_gate.weight | Block 0 Feed-Forward Network "Gate" (W) | ( ~26M) 26214400 | 2560 x 10240 x 1 x 1 | F16 | 16.0000 | | 7 | blk.0.ffn_up.weight | Block 0 Feed-Forward Network "Up" (W) | ( ~26M) 26214400 | 2560 x 10240 x 1 x 1 | F16 | 16.0000 | | 8 | blk.0.inp_gate.weight | Block 0 Inp_Gate (W) | (~655K) 655360 | 2560 x 256 x 1 x 1 | F16 | 16.0000 | | 9 | blk.0.proj.weight | Block 0 Proj (W) | (~655K) 655360 | 256 x 2560 x 1 x 1 | F16 | 16.0000 | | 10 | blk.0.post_attention_norm.weight | Block 0 Post_Attention_Norm (W) | ( ~3K) 2560 | 2560 x 1 x 1 x 1 | F32 | 32.0000 | | 11 | blk.0.post_ffw_norm.weight | Block 0 Post_Ffw_Norm (W) | ( ~3K) 2560 | 2560 x 1 x 1 x 1 | F32 | 32.0000 | | 12 | blk.0.post_norm.weight | Block 0 Post_Norm (W) | ( ~3K) 2560 | 2560 x 1 x 1 x 1 | F32 | 32.0000 | | 13 | blk.0.ffn_norm.weight | Block 0 Feed-Forward Network Normalization (W) | ( ~3K) 2560 | 2560 x 1 x 1 x 1 | F32 | 32.0000 | | 14 | blk.0.attn_k_norm.weight | Block 0 Attn_K_Norm (W) | ( 256) 256 | 256 x 1 x 1 x 1 | F32 | 32.0000 | | 15 | blk.0.attn_k.weight | Block 0 Attention Key (W) | ( ~1M) 1310720 | 2560 x 512 x 1 x 1 | F16 | 16.0000 | | 16 | blk.0.attn_output.weight | Block 0 Attention Output (W) | ( ~5M) 5242880 | 2048 x 2560 x 1 x 1 | F16 | 16.0000 | | 17 | blk.0.attn_q_norm.weight | Block 0 Attn_Q_Norm (W) | ( 256) 256 | 256 x 1 x 1 x 1 | F32 | 32.0000 | | 18 | blk.0.attn_q.weight | Block 0 Attention Query (W) | ( ~5M) 5242880 | 2560 x 2048 x 1 x 1 | F16 | 16.0000 | | 19 | blk.0.attn_v.weight | Block 0 Attention Value (W) | ( ~1M) 1310720 | 2560 x 512 x 1 x 1 | F16 | 16.0000 | - Total elements in blk.0: (~93M) 93074433 - Percentage of total elements: 1.24% - Bits per Weight (BPW) for blk.0: 16.0023 bits ### Block 1 Tensor Group : ~93M Elements | T_ID | Tensor Layer Name | Human Friendly Tensor Layer Name | Elements | Shape | Type | BPW | | ---: | :------------------------------- | :--------------------------------------------- | :--------------- | :-------------------- | :--- | ------: | | 20 | blk.1.attn_norm.weight | Block 1 Attention Normalization (W) | ( ~3K) 2560 | 2560 x 1 x 1 x 1 | F32 | 32.0000 | | 21 | blk.1.layer_output_scale.weight | Block 1 Layer_Output_Scale (W) | ( 1) 1 | 1 x 1 x 1 x 1 | F32 | 32.0000 | | 22 | blk.1.ffn_down.weight | Block 1 Feed-Forward Network "Down" (W) | ( ~26M) 26214400 | 10240 x 2560 x 1 x 1 | F16 | 16.0000 | | 23 | blk.1.ffn_gate.weight | Block 1 Feed-Forward Network "Gate" (W) | ( ~26M) 26214400 | 2560 x 10240 x 1 x 1 | F16 | 16.0000 | | 24 | blk.1.ffn_up.weight | Block 1 Feed-Forward Network "Up" (W) | ( ~26M) 26214400 | 2560 x 10240 x 1 x 1 | F16 | 16.0000 | | 25 | blk.1.inp_gate.weight | Block 1 Inp_Gate (W) | (~655K) 655360 | 2560 x 256 x 1 x 1 | F16 | 16.0000 | | 26 | blk.1.proj.weight | Block 1 Proj (W) | (~655K) 655360 | 256 x 2560 x 1 x 1 | F16 | 16.0000 | | 27 | blk.1.post_attention_norm.weight | Block 1 Post_Attention_Norm (W) | ( ~3K) 2560 | 2560 x 1 x 1 x 1 | F32 | 32.0000 | | 28 | blk.1.post_ffw_norm.weight | Block 1 Post_Ffw_Norm (W) | ( ~3K) 2560 | 2560 x 1 x 1 x 1 | F32 | 32.0000 | | 29 | blk.1.post_norm.weight | Block 1 Post_Norm (W) | ( ~3K) 2560 | 2560 x 1 x 1 x 1 | F32 | 32.0000 | | 30 | blk.1.ffn_norm.weight | Block 1 Feed-Forward Network Normalization (W) | ( ~3K) 2560 | 2560 x 1 x 1 x 1 | F32 | 32.0000 | | 31 | blk.1.attn_k_norm.weight | Block 1 Attn_K_Norm (W) | ( 256) 256 | 256 x 1 x 1 x 1 | F32 | 32.0000 | | 32 | blk.1.attn_k.weight | Block 1 Attention Key (W) | ( ~1M) 1310720 | 2560 x 512 x 1 x 1 | F16 | 16.0000 | | 33 | blk.1.attn_output.weight | Block 1 Attention Output (W) | ( ~5M) 5242880 | 2048 x 2560 x 1 x 1 | F16 | 16.0000 | | 34 | blk.1.attn_q_norm.weight | Block 1 Attn_Q_Norm (W) | ( 256) 256 | 256 x 1 x 1 x 1 | F32 | 32.0000 | | 35 | blk.1.attn_q.weight | Block 1 Attention Query (W) | ( ~5M) 5242880 | 2560 x 2048 x 1 x 1 | F16 | 16.0000 | | 36 | blk.1.attn_v.weight | Block 1 Attention Value (W) | ( ~1M) 1310720 | 2560 x 512 x 1 x 1 | F16 | 16.0000 | - Total elements in blk.1: (~93M) 93074433 - Percentage of total elements: 1.24% - Bits per Weight (BPW) for blk.1: 16.0023 bits ### Block 10 Tensor Group : ~93M Elements | T_ID | Tensor Layer Name | Human Friendly Tensor Layer Name | Elements | Shape | Type | BPW | | ---: | :-------------------------------- | :---------------------------------------------- | :--------------- | :-------------------- | :--- | ------: | | 37 | blk.10.attn_norm.weight | Block 10 Attention Normalization (W) | ( ~3K) 2560 | 2560 x 1 x 1 x 1 | F32 | 32.0000 | | 38 | blk.10.layer_output_scale.weight | Block 10 Layer_Output_Scale (W) | ( 1) 1 | 1 x 1 x 1 x 1 | F32 | 32.0000 | | 39 | blk.10.ffn_down.weight | Block 10 Feed-Forward Network "Down" (W) | ( ~26M) 26214400 | 10240 x 2560 x 1 x 1 | F16 | 16.0000 | | 40 | blk.10.ffn_gate.weight | Block 10 Feed-Forward Network "Gate" (W) | ( ~26M) 26214400 | 2560 x 10240 x 1 x 1 | F16 | 16.0000 | | 41 | blk.10.ffn_up.weight | Block 10 Feed-Forward Network "Up" (W) | ( ~26M) 26214400 | 2560 x 10240 x 1 x 1 | F16 | 16.0000 | | 42 | blk.10.inp_gate.weight | Block 10 Inp_Gate (W) | (~655K) 655360 | 2560 x 256 x 1 x 1 | F16 | 16.0000 | | 43 | blk.10.proj.weight | Block 10 Proj (W) | (~655K) 655360 | 256 x 2560 x 1 x 1 | F16 | 16.0000 | | 44 | blk.10.post_attention_norm.weight | Block 10 Post_Attention_Norm (W) | ( ~3K) 2560 | 2560 x 1 x 1 x 1 | F32 | 32.0000 | | 45 | blk.10.post_ffw_norm.weight | Block 10 Post_Ffw_Norm (W) | ( ~3K) 2560 | 2560 x 1 x 1 x 1 | F32 | 32.0000 | | 46 | blk.10.post_norm.weight | Block 10 Post_Norm (W) | ( ~3K) 2560 | 2560 x 1 x 1 x 1 | F32 | 32.0000 | | 47 | blk.10.ffn_norm.weight | Block 10 Feed-Forward Network Normalization (W) | ( ~3K) 2560 | 2560 x 1 x 1 x 1 | F32 | 32.0000 | | 48 | blk.10.attn_k_norm.weight | Block 10 Attn_K_Norm (W) | ( 256) 256 | 256 x 1 x 1 x 1 | F32 | 32.0000 | | 49 | blk.10.attn_k.weight | Block 10 Attention Key (W) | ( ~1M) 1310720 | 2560 x 512 x 1 x 1 | F16 | 16.0000 | | 50 | blk.10.attn_output.weight | Block 10 Attention Output (W) | ( ~5M) 5242880 | 2048 x 2560 x 1 x 1 | F16 | 16.0000 | | 51 | blk.10.attn_q_norm.weight | Block 10 Attn_Q_Norm (W) | ( 256) 256 | 256 x 1 x 1 x 1 | F32 | 32.0000 | | 52 | blk.10.attn_q.weight | Block 10 Attention Query (W) | ( ~5M) 5242880 | 2560 x 2048 x 1 x 1 | F16 | 16.0000 | | 53 | blk.10.attn_v.weight | Block 10 Attention Value (W) | ( ~1M) 1310720 | 2560 x 512 x 1 x 1 | F16 | 16.0000 | - Total elements in blk.10: (~93M) 93074433 - Percentage of total elements: 1.24% - Bits per Weight (BPW) for blk.10: 16.0023 bits ### Block 11 Tensor Group : ~106M Elements | T_ID | Tensor Layer Name | Human Friendly Tensor Layer Name | Elements | Shape | Type | BPW | | ---: | :-------------------------------- | :---------------------------------------------- | :--------------- | :-------------------- | :--- | ------: | | 54 | blk.11.attn_norm.weight | Block 11 Attention Normalization (W) | ( ~3K) 2560 | 2560 x 1 x 1 x 1 | F32 | 32.0000 | | 55 | blk.11.layer_output_scale.weight | Block 11 Layer_Output_Scale (W) | ( 1) 1 | 1 x 1 x 1 x 1 | F32 | 32.0000 | | 56 | blk.11.ffn_down.weight | Block 11 Feed-Forward Network "Down" (W) | ( ~26M) 26214400 | 10240 x 2560 x 1 x 1 | F16 | 16.0000 | | 57 | blk.11.ffn_gate.weight | Block 11 Feed-Forward Network "Gate" (W) | ( ~26M) 26214400 | 2560 x 10240 x 1 x 1 | F16 | 16.0000 | | 58 | blk.11.ffn_up.weight | Block 11 Feed-Forward Network "Up" (W) | ( ~26M) 26214400 | 2560 x 10240 x 1 x 1 | F16 | 16.0000 | | 59 | blk.11.inp_gate.weight | Block 11 Inp_Gate (W) | (~655K) 655360 | 2560 x 256 x 1 x 1 | F16 | 16.0000 | | 60 | blk.11.proj.weight | Block 11 Proj (W) | (~655K) 655360 | 256 x 2560 x 1 x 1 | F16 | 16.0000 | | 61 | blk.11.post_attention_norm.weight | Block 11 Post_Attention_Norm (W) | ( ~3K) 2560 | 2560 x 1 x 1 x 1 | F32 | 32.0000 | | 62 | blk.11.post_ffw_norm.weight | Block 11 Post_Ffw_Norm (W) | ( ~3K) 2560 | 2560 x 1 x 1 x 1 | F32 | 32.0000 | | 63 | blk.11.post_norm.weight | Block 11 Post_Norm (W) | ( ~3K) 2560 | 2560 x 1 x 1 x 1 | F32 | 32.0000 | | 64 | blk.11.ffn_norm.weight | Block 11 Feed-Forward Network Normalization (W) | ( ~3K) 2560 | 2560 x 1 x 1 x 1 | F32 | 32.0000 | | 65 | blk.11.attn_k_norm.weight | Block 11 Attn_K_Norm (W) | ( 512) 512 | 512 x 1 x 1 x 1 | F32 | 32.0000 | | 66 | blk.11.attn_k.weight | Block 11 Attention Key (W) | ( ~3M) 2621440 | 2560 x 1024 x 1 x 1 | F16 | 16.0000 | | 67 | blk.11.attn_output.weight | Block 11 Attention Output (W) | ( ~10M) 10485760 | 4096 x 2560 x 1 x 1 | F16 | 16.0000 | | 68 | blk.11.attn_q_norm.weight | Block 11 Attn_Q_Norm (W) | ( 512) 512 | 512 x 1 x 1 x 1 | F32 | 32.0000 | | 69 | blk.11.attn_q.weight | Block 11 Attention Query (W) | ( ~10M) 10485760 | 2560 x 4096 x 1 x 1 | F16 | 16.0000 | | 70 | blk.11.attn_v.weight | Block 11 Attention Value (W) | ( ~3M) 2621440 | 2560 x 1024 x 1 x 1 | F16 | 16.0000 | - Total elements in blk.11: (~106M) 106182145 - Percentage of total elements: 1.41% - Bits per Weight (BPW) for blk.11: 16.0021 bits ### Block 12 Tensor Group : ~93M Elements | T_ID | Tensor Layer Name | Human Friendly Tensor Layer Name | Elements | Shape | Type | BPW | | ---: | :-------------------------------- | :---------------------------------------------- | :--------------- | :-------------------- | :--- | ------: | | 71 | blk.12.attn_norm.weight | Block 12 Attention Normalization (W) | ( ~3K) 2560 | 2560 x 1 x 1 x 1 | F32 | 32.0000 | | 72 | blk.12.layer_output_scale.weight | Block 12 Layer_Output_Scale (W) | ( 1) 1 | 1 x 1 x 1 x 1 | F32 | 32.0000 | | 73 | blk.12.ffn_down.weight | Block 12 Feed-Forward Network "Down" (W) | ( ~26M) 26214400 | 10240 x 2560 x 1 x 1 | F16 | 16.0000 | | 74 | blk.12.ffn_gate.weight | Block 12 Feed-Forward Network "Gate" (W) | ( ~26M) 26214400 | 2560 x 10240 x 1 x 1 | F16 | 16.0000 | | 75 | blk.12.ffn_up.weight | Block 12 Feed-Forward Network "Up" (W) | ( ~26M) 26214400 | 2560 x 10240 x 1 x 1 | F16 | 16.0000 | | 76 | blk.12.inp_gate.weight | Block 12 Inp_Gate (W) | (~655K) 655360 | 2560 x 256 x 1 x 1 | F16 | 16.0000 | | 77 | blk.12.proj.weight | Block 12 Proj (W) | (~655K) 655360 | 256 x 2560 x 1 x 1 | F16 | 16.0000 | | 78 | blk.12.post_attention_norm.weight | Block 12 Post_Attention_Norm (W) | ( ~3K) 2560 | 2560 x 1 x 1 x 1 | F32 | 32.0000 | | 79 | blk.12.post_ffw_norm.weight | Block 12 Post_Ffw_Norm (W) | ( ~3K) 2560 | 2560 x 1 x 1 x 1 | F32 | 32.0000 | | 80 | blk.12.post_norm.weight | Block 12 Post_Norm (W) | ( ~3K) 2560 | 2560 x 1 x 1 x 1 | F32 | 32.0000 | | 81 | blk.12.ffn_norm.weight | Block 12 Feed-Forward Network Normalization (W) | ( ~3K) 2560 | 2560 x 1 x 1 x 1 | F32 | 32.0000 | | 82 | blk.12.attn_k_norm.weight | Block 12 Attn_K_Norm (W) | ( 256) 256 | 256 x 1 x 1 x 1 | F32 | 32.0000 | | 83 | blk.12.attn_k.weight | Block 12 Attention Key (W) | ( ~1M) 1310720 | 2560 x 512 x 1 x 1 | F16 | 16.0000 | | 84 | blk.12.attn_output.weight | Block 12 Attention Output (W) | ( ~5M) 5242880 | 2048 x 2560 x 1 x 1 | F16 | 16.0000 | | 85 | blk.12.attn_q_norm.weight | Block 12 Attn_Q_Norm (W) | ( 256) 256 | 256 x 1 x 1 x 1 | F32 | 32.0000 | | 86 | blk.12.attn_q.weight | Block 12 Attention Query (W) | ( ~5M) 5242880 | 2560 x 2048 x 1 x 1 | F16 | 16.0000 | | 87 | blk.12.attn_v.weight | Block 12 Attention Value (W) | ( ~1M) 1310720 | 2560 x 512 x 1 x 1 | F16 | 16.0000 | - Total elements in blk.12: (~93M) 93074433 - Percentage of total elements: 1.24% - Bits per Weight (BPW) for blk.12: 16.0023 bits ### Block 13 Tensor Group : ~93M Elements | T_ID | Tensor Layer Name | Human Friendly Tensor Layer Name | Elements | Shape | Type | BPW | | ---: | :-------------------------------- | :---------------------------------------------- | :--------------- | :-------------------- | :--- | ------: | | 88 | blk.13.attn_norm.weight | Block 13 Attention Normalization (W) | ( ~3K) 2560 | 2560 x 1 x 1 x 1 | F32 | 32.0000 | | 89 | blk.13.layer_output_scale.weight | Block 13 Layer_Output_Scale (W) | ( 1) 1 | 1 x 1 x 1 x 1 | F32 | 32.0000 | | 90 | blk.13.ffn_down.weight | Block 13 Feed-Forward Network "Down" (W) | ( ~26M) 26214400 | 10240 x 2560 x 1 x 1 | F16 | 16.0000 | | 91 | blk.13.ffn_gate.weight | Block 13 Feed-Forward Network "Gate" (W) | ( ~26M) 26214400 | 2560 x 10240 x 1 x 1 | F16 | 16.0000 | | 92 | blk.13.ffn_up.weight | Block 13 Feed-Forward Network "Up" (W) | ( ~26M) 26214400 | 2560 x 10240 x 1 x 1 | F16 | 16.0000 | | 93 | blk.13.inp_gate.weight | Block 13 Inp_Gate (W) | (~655K) 655360 | 2560 x 256 x 1 x 1 | F16 | 16.0000 | | 94 | blk.13.proj.weight | Block 13 Proj (W) | (~655K) 655360 | 256 x 2560 x 1 x 1 | F16 | 16.0000 | | 95 | blk.13.post_attention_norm.weight | Block 13 Post_Attention_Norm (W) | ( ~3K) 2560 | 2560 x 1 x 1 x 1 | F32 | 32.0000 | | 96 | blk.13.post_ffw_norm.weight | Block 13 Post_Ffw_Norm (W) | ( ~3K) 2560 | 2560 x 1 x 1 x 1 | F32 | 32.0000 | | 97 | blk.13.post_norm.weight | Block 13 Post_Norm (W) | ( ~3K) 2560 | 2560 x 1 x 1 x 1 | F32 | 32.0000 | | 98 | blk.13.ffn_norm.weight | Block 13 Feed-Forward Network Normalization (W) | ( ~3K) 2560 | 2560 x 1 x 1 x 1 | F32 | 32.0000 | | 99 | blk.13.attn_k_norm.weight | Block 13 Attn_K_Norm (W) | ( 256) 256 | 256 x 1 x 1 x 1 | F32 | 32.0000 | | 100 | blk.13.attn_k.weight | Block 13 Attention Key (W) | ( ~1M) 1310720 | 2560 x 512 x 1 x 1 | F16 | 16.0000 | | 101 | blk.13.attn_output.weight | Block 13 Attention Output (W) | ( ~5M) 5242880 | 2048 x 2560 x 1 x 1 | F16 | 16.0000 | | 102 | blk.13.attn_q_norm.weight | Block 13 Attn_Q_Norm (W) | ( 256) 256 | 256 x 1 x 1 x 1 | F32 | 32.0000 | | 103 | blk.13.attn_q.weight | Block 13 Attention Query (W) | ( ~5M) 5242880 | 2560 x 2048 x 1 x 1 | F16 | 16.0000 | | 104 | blk.13.attn_v.weight | Block 13 Attention Value (W) | ( ~1M) 1310720 | 2560 x 512 x 1 x 1 | F16 | 16.0000 | - Total elements in blk.13: (~93M) 93074433 - Percentage of total elements: 1.24% - Bits per Weight (BPW) for blk.13: 16.0023 bits ### Block 14 Tensor Group : ~93M Elements | T_ID | Tensor Layer Name | Human Friendly Tensor Layer Name | Elements | Shape | Type | BPW | | ---: | :-------------------------------- | :---------------------------------------------- | :--------------- | :-------------------- | :--- | ------: | | 105 | blk.14.attn_norm.weight | Block 14 Attention Normalization (W) | ( ~3K) 2560 | 2560 x 1 x 1 x 1 | F32 | 32.0000 | | 106 | blk.14.layer_output_scale.weight | Block 14 Layer_Output_Scale (W) | ( 1) 1 | 1 x 1 x 1 x 1 | F32 | 32.0000 | | 107 | blk.14.ffn_down.weight | Block 14 Feed-Forward Network "Down" (W) | ( ~26M) 26214400 | 10240 x 2560 x 1 x 1 | F16 | 16.0000 | | 108 | blk.14.ffn_gate.weight | Block 14 Feed-Forward Network "Gate" (W) | ( ~26M) 26214400 | 2560 x 10240 x 1 x 1 | F16 | 16.0000 | | 109 | blk.14.ffn_up.weight | Block 14 Feed-Forward Network "Up" (W) | ( ~26M) 26214400 | 2560 x 10240 x 1 x 1 | F16 | 16.0000 | | 110 | blk.14.inp_gate.weight | Block 14 Inp_Gate (W) | (~655K) 655360 | 2560 x 256 x 1 x 1 | F16 | 16.0000 | | 111 | blk.14.proj.weight | Block 14 Proj (W) | (~655K) 655360 | 256 x 2560 x 1 x 1 | F16 | 16.0000 | | 112 | blk.14.post_attention_norm.weight | Block 14 Post_Attention_Norm (W) | ( ~3K) 2560 | 2560 x 1 x 1 x 1 | F32 | 32.0000 | | 113 | blk.14.post_ffw_norm.weight | Block 14 Post_Ffw_Norm (W) | ( ~3K) 2560 | 2560 x 1 x 1 x 1 | F32 | 32.0000 | | 114 | blk.14.post_norm.weight | Block 14 Post_Norm (W) | ( ~3K) 2560 | 2560 x 1 x 1 x 1 | F32 | 32.0000 | | 115 | blk.14.ffn_norm.weight | Block 14 Feed-Forward Network Normalization (W) | ( ~3K) 2560 | 2560 x 1 x 1 x 1 | F32 | 32.0000 | | 116 | blk.14.attn_k_norm.weight | Block 14 Attn_K_Norm (W) | ( 256) 256 | 256 x 1 x 1 x 1 | F32 | 32.0000 | | 117 | blk.14.attn_k.weight | Block 14 Attention Key (W) | ( ~1M) 1310720 | 2560 x 512 x 1 x 1 | F16 | 16.0000 | | 118 | blk.14.attn_output.weight | Block 14 Attention Output (W) | ( ~5M) 5242880 | 2048 x 2560 x 1 x 1 | F16 | 16.0000 | | 119 | blk.14.attn_q_norm.weight | Block 14 Attn_Q_Norm (W) | ( 256) 256 | 256 x 1 x 1 x 1 | F32 | 32.0000 | | 120 | blk.14.attn_q.weight | Block 14 Attention Query (W) | ( ~5M) 5242880 | 2560 x 2048 x 1 x 1 | F16 | 16.0000 | | 121 | blk.14.attn_v.weight | Block 14 Attention Value (W) | ( ~1M) 1310720 | 2560 x 512 x 1 x 1 | F16 | 16.0000 | - Total elements in blk.14: (~93M) 93074433 - Percentage of total elements: 1.24% - Bits per Weight (BPW) for blk.14: 16.0023 bits ### Block 15 Tensor Group : ~93M Elements | T_ID | Tensor Layer Name | Human Friendly Tensor Layer Name | Elements | Shape | Type | BPW | | ---: | :-------------------------------- | :---------------------------------------------- | :--------------- | :-------------------- | :--- | ------: | | 122 | blk.15.attn_norm.weight | Block 15 Attention Normalization (W) | ( ~3K) 2560 | 2560 x 1 x 1 x 1 | F32 | 32.0000 | | 123 | blk.15.layer_output_scale.weight | Block 15 Layer_Output_Scale (W) | ( 1) 1 | 1 x 1 x 1 x 1 | F32 | 32.0000 | | 124 | blk.15.ffn_down.weight | Block 15 Feed-Forward Network "Down" (W) | ( ~26M) 26214400 | 10240 x 2560 x 1 x 1 | F16 | 16.0000 | | 125 | blk.15.ffn_gate.weight | Block 15 Feed-Forward Network "Gate" (W) | ( ~26M) 26214400 | 2560 x 10240 x 1 x 1 | F16 | 16.0000 | | 126 | blk.15.ffn_up.weight | Block 15 Feed-Forward Network "Up" (W) | ( ~26M) 26214400 | 2560 x 10240 x 1 x 1 | F16 | 16.0000 | | 127 | blk.15.inp_gate.weight | Block 15 Inp_Gate (W) | (~655K) 655360 | 2560 x 256 x 1 x 1 | F16 | 16.0000 | | 128 | blk.15.proj.weight | Block 15 Proj (W) | (~655K) 655360 | 256 x 2560 x 1 x 1 | F16 | 16.0000 | | 129 | blk.15.post_attention_norm.weight | Block 15 Post_Attention_Norm (W) | ( ~3K) 2560 | 2560 x 1 x 1 x 1 | F32 | 32.0000 | | 130 | blk.15.post_ffw_norm.weight | Block 15 Post_Ffw_Norm (W) | ( ~3K) 2560 | 2560 x 1 x 1 x 1 | F32 | 32.0000 | | 131 | blk.15.post_norm.weight | Block 15 Post_Norm (W) | ( ~3K) 2560 | 2560 x 1 x 1 x 1 | F32 | 32.0000 | | 132 | blk.15.ffn_norm.weight | Block 15 Feed-Forward Network Normalization (W) | ( ~3K) 2560 | 2560 x 1 x 1 x 1 | F32 | 32.0000 | | 133 | blk.15.attn_k_norm.weight | Block 15 Attn_K_Norm (W) | ( 256) 256 | 256 x 1 x 1 x 1 | F32 | 32.0000 | | 134 | blk.15.attn_k.weight | Block 15 Attention Key (W) | ( ~1M) 1310720 | 2560 x 512 x 1 x 1 | F16 | 16.0000 | | 135 | blk.15.attn_output.weight | Block 15 Attention Output (W) | ( ~5M) 5242880 | 2048 x 2560 x 1 x 1 | F16 | 16.0000 | | 136 | blk.15.attn_q_norm.weight | Block 15 Attn_Q_Norm (W) | ( 256) 256 | 256 x 1 x 1 x 1 | F32 | 32.0000 | | 137 | blk.15.attn_q.weight | Block 15 Attention Query (W) | ( ~5M) 5242880 | 2560 x 2048 x 1 x 1 | F16 | 16.0000 | | 138 | blk.15.attn_v.weight | Block 15 Attention Value (W) | ( ~1M) 1310720 | 2560 x 512 x 1 x 1 | F16 | 16.0000 | - Total elements in blk.15: (~93M) 93074433 - Percentage of total elements: 1.24% - Bits per Weight (BPW) for blk.15: 16.0023 bits ### Block 16 Tensor Group : ~93M Elements | T_ID | Tensor Layer Name | Human Friendly Tensor Layer Name | Elements | Shape | Type | BPW | | ---: | :-------------------------------- | :---------------------------------------------- | :--------------- | :-------------------- | :--- | ------: | | 139 | blk.16.attn_norm.weight | Block 16 Attention Normalization (W) | ( ~3K) 2560 | 2560 x 1 x 1 x 1 | F32 | 32.0000 | | 140 | blk.16.layer_output_scale.weight | Block 16 Layer_Output_Scale (W) | ( 1) 1 | 1 x 1 x 1 x 1 | F32 | 32.0000 | | 141 | blk.16.ffn_down.weight | Block 16 Feed-Forward Network "Down" (W) | ( ~26M) 26214400 | 10240 x 2560 x 1 x 1 | F16 | 16.0000 | | 142 | blk.16.ffn_gate.weight | Block 16 Feed-Forward Network "Gate" (W) | ( ~26M) 26214400 | 2560 x 10240 x 1 x 1 | F16 | 16.0000 | | 143 | blk.16.ffn_up.weight | Block 16 Feed-Forward Network "Up" (W) | ( ~26M) 26214400 | 2560 x 10240 x 1 x 1 | F16 | 16.0000 | | 144 | blk.16.inp_gate.weight | Block 16 Inp_Gate (W) | (~655K) 655360 | 2560 x 256 x 1 x 1 | F16 | 16.0000 | | 145 | blk.16.proj.weight | Block 16 Proj (W) | (~655K) 655360 | 256 x 2560 x 1 x 1 | F16 | 16.0000 | | 146 | blk.16.post_attention_norm.weight | Block 16 Post_Attention_Norm (W) | ( ~3K) 2560 | 2560 x 1 x 1 x 1 | F32 | 32.0000 | | 147 | blk.16.post_ffw_norm.weight | Block 16 Post_Ffw_Norm (W) | ( ~3K) 2560 | 2560 x 1 x 1 x 1 | F32 | 32.0000 | | 148 | blk.16.post_norm.weight | Block 16 Post_Norm (W) | ( ~3K) 2560 | 2560 x 1 x 1 x 1 | F32 | 32.0000 | | 149 | blk.16.ffn_norm.weight | Block 16 Feed-Forward Network Normalization (W) | ( ~3K) 2560 | 2560 x 1 x 1 x 1 | F32 | 32.0000 | | 150 | blk.16.attn_k_norm.weight | Block 16 Attn_K_Norm (W) | ( 256) 256 | 256 x 1 x 1 x 1 | F32 | 32.0000 | | 151 | blk.16.attn_k.weight | Block 16 Attention Key (W) | ( ~1M) 1310720 | 2560 x 512 x 1 x 1 | F16 | 16.0000 | | 152 | blk.16.attn_output.weight | Block 16 Attention Output (W) | ( ~5M) 5242880 | 2048 x 2560 x 1 x 1 | F16 | 16.0000 | | 153 | blk.16.attn_q_norm.weight | Block 16 Attn_Q_Norm (W) | ( 256) 256 | 256 x 1 x 1 x 1 | F32 | 32.0000 | | 154 | blk.16.attn_q.weight | Block 16 Attention Query (W) | ( ~5M) 5242880 | 2560 x 2048 x 1 x 1 | F16 | 16.0000 | | 155 | blk.16.attn_v.weight | Block 16 Attention Value (W) | ( ~1M) 1310720 | 2560 x 512 x 1 x 1 | F16 | 16.0000 | - Total elements in blk.16: (~93M) 93074433 - Percentage of total elements: 1.24% - Bits per Weight (BPW) for blk.16: 16.0023 bits ### Block 17 Tensor Group : ~106M Elements | T_ID | Tensor Layer Name | Human Friendly Tensor Layer Name | Elements | Shape | Type | BPW | | ---: | :-------------------------------- | :---------------------------------------------- | :--------------- | :-------------------- | :--- | ------: | | 156 | blk.17.attn_norm.weight | Block 17 Attention Normalization (W) | ( ~3K) 2560 | 2560 x 1 x 1 x 1 | F32 | 32.0000 | | 157 | blk.17.layer_output_scale.weight | Block 17 Layer_Output_Scale (W) | ( 1) 1 | 1 x 1 x 1 x 1 | F32 | 32.0000 | | 158 | blk.17.ffn_down.weight | Block 17 Feed-Forward Network "Down" (W) | ( ~26M) 26214400 | 10240 x 2560 x 1 x 1 | F16 | 16.0000 | | 159 | blk.17.ffn_gate.weight | Block 17 Feed-Forward Network "Gate" (W) | ( ~26M) 26214400 | 2560 x 10240 x 1 x 1 | F16 | 16.0000 | | 160 | blk.17.ffn_up.weight | Block 17 Feed-Forward Network "Up" (W) | ( ~26M) 26214400 | 2560 x 10240 x 1 x 1 | F16 | 16.0000 | | 161 | blk.17.inp_gate.weight | Block 17 Inp_Gate (W) | (~655K) 655360 | 2560 x 256 x 1 x 1 | F16 | 16.0000 | | 162 | blk.17.proj.weight | Block 17 Proj (W) | (~655K) 655360 | 256 x 2560 x 1 x 1 | F16 | 16.0000 | | 163 | blk.17.post_attention_norm.weight | Block 17 Post_Attention_Norm (W) | ( ~3K) 2560 | 2560 x 1 x 1 x 1 | F32 | 32.0000 | | 164 | blk.17.post_ffw_norm.weight | Block 17 Post_Ffw_Norm (W) | ( ~3K) 2560 | 2560 x 1 x 1 x 1 | F32 | 32.0000 | | 165 | blk.17.post_norm.weight | Block 17 Post_Norm (W) | ( ~3K) 2560 | 2560 x 1 x 1 x 1 | F32 | 32.0000 | | 166 | blk.17.ffn_norm.weight | Block 17 Feed-Forward Network Normalization (W) | ( ~3K) 2560 | 2560 x 1 x 1 x 1 | F32 | 32.0000 | | 167 | blk.17.attn_k_norm.weight | Block 17 Attn_K_Norm (W) | ( 512) 512 | 512 x 1 x 1 x 1 | F32 | 32.0000 | | 168 | blk.17.attn_k.weight | Block 17 Attention Key (W) | ( ~3M) 2621440 | 2560 x 1024 x 1 x 1 | F16 | 16.0000 | | 169 | blk.17.attn_output.weight | Block 17 Attention Output (W) | ( ~10M) 10485760 | 4096 x 2560 x 1 x 1 | F16 | 16.0000 | | 170 | blk.17.attn_q_norm.weight | Block 17 Attn_Q_Norm (W) | ( 512) 512 | 512 x 1 x 1 x 1 | F32 | 32.0000 | | 171 | blk.17.attn_q.weight | Block 17 Attention Query (W) | ( ~10M) 10485760 | 2560 x 4096 x 1 x 1 | F16 | 16.0000 | | 172 | blk.17.attn_v.weight | Block 17 Attention Value (W) | ( ~3M) 2621440 | 2560 x 1024 x 1 x 1 | F16 | 16.0000 | - Total elements in blk.17: (~106M) 106182145 - Percentage of total elements: 1.41% - Bits per Weight (BPW) for blk.17: 16.0021 bits ### Block 18 Tensor Group : ~93M Elements | T_ID | Tensor Layer Name | Human Friendly Tensor Layer Name | Elements | Shape | Type | BPW | | ---: | :-------------------------------- | :---------------------------------------------- | :--------------- | :-------------------- | :--- | ------: | | 173 | blk.18.attn_norm.weight | Block 18 Attention Normalization (W) | ( ~3K) 2560 | 2560 x 1 x 1 x 1 | F32 | 32.0000 | | 174 | blk.18.layer_output_scale.weight | Block 18 Layer_Output_Scale (W) | ( 1) 1 | 1 x 1 x 1 x 1 | F32 | 32.0000 | | 175 | blk.18.ffn_down.weight | Block 18 Feed-Forward Network "Down" (W) | ( ~26M) 26214400 | 10240 x 2560 x 1 x 1 | F16 | 16.0000 | | 176 | blk.18.ffn_gate.weight | Block 18 Feed-Forward Network "Gate" (W) | ( ~26M) 26214400 | 2560 x 10240 x 1 x 1 | F16 | 16.0000 | | 177 | blk.18.ffn_up.weight | Block 18 Feed-Forward Network "Up" (W) | ( ~26M) 26214400 | 2560 x 10240 x 1 x 1 | F16 | 16.0000 | | 178 | blk.18.inp_gate.weight | Block 18 Inp_Gate (W) | (~655K) 655360 | 2560 x 256 x 1 x 1 | F16 | 16.0000 | | 179 | blk.18.proj.weight | Block 18 Proj (W) | (~655K) 655360 | 256 x 2560 x 1 x 1 | F16 | 16.0000 | | 180 | blk.18.post_attention_norm.weight | Block 18 Post_Attention_Norm (W) | ( ~3K) 2560 | 2560 x 1 x 1 x 1 | F32 | 32.0000 | | 181 | blk.18.post_ffw_norm.weight | Block 18 Post_Ffw_Norm (W) | ( ~3K) 2560 | 2560 x 1 x 1 x 1 | F32 | 32.0000 | | 182 | blk.18.post_norm.weight | Block 18 Post_Norm (W) | ( ~3K) 2560 | 2560 x 1 x 1 x 1 | F32 | 32.0000 | | 183 | blk.18.ffn_norm.weight | Block 18 Feed-Forward Network Normalization (W) | ( ~3K) 2560 | 2560 x 1 x 1 x 1 | F32 | 32.0000 | | 184 | blk.18.attn_k_norm.weight | Block 18 Attn_K_Norm (W) | ( 256) 256 | 256 x 1 x 1 x 1 | F32 | 32.0000 | | 185 | blk.18.attn_k.weight | Block 18 Attention Key (W) | ( ~1M) 1310720 | 2560 x 512 x 1 x 1 | F16 | 16.0000 | | 186 | blk.18.attn_output.weight | Block 18 Attention Output (W) | ( ~5M) 5242880 | 2048 x 2560 x 1 x 1 | F16 | 16.0000 | | 187 | blk.18.attn_q_norm.weight | Block 18 Attn_Q_Norm (W) | ( 256) 256 | 256 x 1 x 1 x 1 | F32 | 32.0000 | | 188 | blk.18.attn_q.weight | Block 18 Attention Query (W) | ( ~5M) 5242880 | 2560 x 2048 x 1 x 1 | F16 | 16.0000 | | 189 | blk.18.attn_v.weight | Block 18 Attention Value (W) | ( ~1M) 1310720 | 2560 x 512 x 1 x 1 | F16 | 16.0000 | - Total elements in blk.18: (~93M) 93074433 - Percentage of total elements: 1.24% - Bits per Weight (BPW) for blk.18: 16.0023 bits ### Block 19 Tensor Group : ~93M Elements | T_ID | Tensor Layer Name | Human Friendly Tensor Layer Name | Elements | Shape | Type | BPW | | ---: | :-------------------------------- | :---------------------------------------------- | :--------------- | :-------------------- | :--- | ------: | | 190 | blk.19.attn_norm.weight | Block 19 Attention Normalization (W) | ( ~3K) 2560 | 2560 x 1 x 1 x 1 | F32 | 32.0000 | | 191 | blk.19.layer_output_scale.weight | Block 19 Layer_Output_Scale (W) | ( 1) 1 | 1 x 1 x 1 x 1 | F32 | 32.0000 | | 192 | blk.19.ffn_down.weight | Block 19 Feed-Forward Network "Down" (W) | ( ~26M) 26214400 | 10240 x 2560 x 1 x 1 | F16 | 16.0000 | | 193 | blk.19.ffn_gate.weight | Block 19 Feed-Forward Network "Gate" (W) | ( ~26M) 26214400 | 2560 x 10240 x 1 x 1 | F16 | 16.0000 | | 194 | blk.19.ffn_up.weight | Block 19 Feed-Forward Network "Up" (W) | ( ~26M) 26214400 | 2560 x 10240 x 1 x 1 | F16 | 16.0000 | | 195 | blk.19.inp_gate.weight | Block 19 Inp_Gate (W) | (~655K) 655360 | 2560 x 256 x 1 x 1 | F16 | 16.0000 | | 196 | blk.19.proj.weight | Block 19 Proj (W) | (~655K) 655360 | 256 x 2560 x 1 x 1 | F16 | 16.0000 | | 197 | blk.19.post_attention_norm.weight | Block 19 Post_Attention_Norm (W) | ( ~3K) 2560 | 2560 x 1 x 1 x 1 | F32 | 32.0000 | | 198 | blk.19.post_ffw_norm.weight | Block 19 Post_Ffw_Norm (W) | ( ~3K) 2560 | 2560 x 1 x 1 x 1 | F32 | 32.0000 | | 199 | blk.19.post_norm.weight | Block 19 Post_Norm (W) | ( ~3K) 2560 | 2560 x 1 x 1 x 1 | F32 | 32.0000 | | 200 | blk.19.ffn_norm.weight | Block 19 Feed-Forward Network Normalization (W) | ( ~3K) 2560 | 2560 x 1 x 1 x 1 | F32 | 32.0000 | | 201 | blk.19.attn_k_norm.weight | Block 19 Attn_K_Norm (W) | ( 256) 256 | 256 x 1 x 1 x 1 | F32 | 32.0000 | | 202 | blk.19.attn_k.weight | Block 19 Attention Key (W) | ( ~1M) 1310720 | 2560 x 512 x 1 x 1 | F16 | 16.0000 | | 203 | blk.19.attn_output.weight | Block 19 Attention Output (W) | ( ~5M) 5242880 | 2048 x 2560 x 1 x 1 | F16 | 16.0000 | | 204 | blk.19.attn_q_norm.weight | Block 19 Attn_Q_Norm (W) | ( 256) 256 | 256 x 1 x 1 x 1 | F32 | 32.0000 | | 205 | blk.19.attn_q.weight | Block 19 Attention Query (W) | ( ~5M) 5242880 | 2560 x 2048 x 1 x 1 | F16 | 16.0000 | | 206 | blk.19.attn_v.weight | Block 19 Attention Value (W) | ( ~1M) 1310720 | 2560 x 512 x 1 x 1 | F16 | 16.0000 | - Total elements in blk.19: (~93M) 93074433 - Percentage of total elements: 1.24% - Bits per Weight (BPW) for blk.19: 16.0023 bits ### Block 2 Tensor Group : ~93M Elements | T_ID | Tensor Layer Name | Human Friendly Tensor Layer Name | Elements | Shape | Type | BPW | | ---: | :------------------------------- | :--------------------------------------------- | :--------------- | :-------------------- | :--- | ------: | | 207 | blk.2.attn_norm.weight | Block 2 Attention Normalization (W) | ( ~3K) 2560 | 2560 x 1 x 1 x 1 | F32 | 32.0000 | | 208 | blk.2.layer_output_scale.weight | Block 2 Layer_Output_Scale (W) | ( 1) 1 | 1 x 1 x 1 x 1 | F32 | 32.0000 | | 209 | blk.2.ffn_down.weight | Block 2 Feed-Forward Network "Down" (W) | ( ~26M) 26214400 | 10240 x 2560 x 1 x 1 | F16 | 16.0000 | | 210 | blk.2.ffn_gate.weight | Block 2 Feed-Forward Network "Gate" (W) | ( ~26M) 26214400 | 2560 x 10240 x 1 x 1 | F16 | 16.0000 | | 211 | blk.2.ffn_up.weight | Block 2 Feed-Forward Network "Up" (W) | ( ~26M) 26214400 | 2560 x 10240 x 1 x 1 | F16 | 16.0000 | | 212 | blk.2.inp_gate.weight | Block 2 Inp_Gate (W) | (~655K) 655360 | 2560 x 256 x 1 x 1 | F16 | 16.0000 | | 213 | blk.2.proj.weight | Block 2 Proj (W) | (~655K) 655360 | 256 x 2560 x 1 x 1 | F16 | 16.0000 | | 214 | blk.2.post_attention_norm.weight | Block 2 Post_Attention_Norm (W) | ( ~3K) 2560 | 2560 x 1 x 1 x 1 | F32 | 32.0000 | | 215 | blk.2.post_ffw_norm.weight | Block 2 Post_Ffw_Norm (W) | ( ~3K) 2560 | 2560 x 1 x 1 x 1 | F32 | 32.0000 | | 216 | blk.2.post_norm.weight | Block 2 Post_Norm (W) | ( ~3K) 2560 | 2560 x 1 x 1 x 1 | F32 | 32.0000 | | 217 | blk.2.ffn_norm.weight | Block 2 Feed-Forward Network Normalization (W) | ( ~3K) 2560 | 2560 x 1 x 1 x 1 | F32 | 32.0000 | | 218 | blk.2.attn_k_norm.weight | Block 2 Attn_K_Norm (W) | ( 256) 256 | 256 x 1 x 1 x 1 | F32 | 32.0000 | | 219 | blk.2.attn_k.weight | Block 2 Attention Key (W) | ( ~1M) 1310720 | 2560 x 512 x 1 x 1 | F16 | 16.0000 | | 220 | blk.2.attn_output.weight | Block 2 Attention Output (W) | ( ~5M) 5242880 | 2048 x 2560 x 1 x 1 | F16 | 16.0000 | | 221 | blk.2.attn_q_norm.weight | Block 2 Attn_Q_Norm (W) | ( 256) 256 | 256 x 1 x 1 x 1 | F32 | 32.0000 | | 222 | blk.2.attn_q.weight | Block 2 Attention Query (W) | ( ~5M) 5242880 | 2560 x 2048 x 1 x 1 | F16 | 16.0000 | | 223 | blk.2.attn_v.weight | Block 2 Attention Value (W) | ( ~1M) 1310720 | 2560 x 512 x 1 x 1 | F16 | 16.0000 | - Total elements in blk.2: (~93M) 93074433 - Percentage of total elements: 1.24% - Bits per Weight (BPW) for blk.2: 16.0023 bits ### Block 20 Tensor Group : ~93M Elements | T_ID | Tensor Layer Name | Human Friendly Tensor Layer Name | Elements | Shape | Type | BPW | | ---: | :-------------------------------- | :---------------------------------------------- | :--------------- | :-------------------- | :--- | ------: | | 224 | blk.20.attn_norm.weight | Block 20 Attention Normalization (W) | ( ~3K) 2560 | 2560 x 1 x 1 x 1 | F32 | 32.0000 | | 225 | blk.20.layer_output_scale.weight | Block 20 Layer_Output_Scale (W) | ( 1) 1 | 1 x 1 x 1 x 1 | F32 | 32.0000 | | 226 | blk.20.ffn_down.weight | Block 20 Feed-Forward Network "Down" (W) | ( ~26M) 26214400 | 10240 x 2560 x 1 x 1 | F16 | 16.0000 | | 227 | blk.20.ffn_gate.weight | Block 20 Feed-Forward Network "Gate" (W) | ( ~26M) 26214400 | 2560 x 10240 x 1 x 1 | F16 | 16.0000 | | 228 | blk.20.ffn_up.weight | Block 20 Feed-Forward Network "Up" (W) | ( ~26M) 26214400 | 2560 x 10240 x 1 x 1 | F16 | 16.0000 | | 229 | blk.20.inp_gate.weight | Block 20 Inp_Gate (W) | (~655K) 655360 | 2560 x 256 x 1 x 1 | F16 | 16.0000 | | 230 | blk.20.proj.weight | Block 20 Proj (W) | (~655K) 655360 | 256 x 2560 x 1 x 1 | F16 | 16.0000 | | 231 | blk.20.post_attention_norm.weight | Block 20 Post_Attention_Norm (W) | ( ~3K) 2560 | 2560 x 1 x 1 x 1 | F32 | 32.0000 | | 232 | blk.20.post_ffw_norm.weight | Block 20 Post_Ffw_Norm (W) | ( ~3K) 2560 | 2560 x 1 x 1 x 1 | F32 | 32.0000 | | 233 | blk.20.post_norm.weight | Block 20 Post_Norm (W) | ( ~3K) 2560 | 2560 x 1 x 1 x 1 | F32 | 32.0000 | | 234 | blk.20.ffn_norm.weight | Block 20 Feed-Forward Network Normalization (W) | ( ~3K) 2560 | 2560 x 1 x 1 x 1 | F32 | 32.0000 | | 235 | blk.20.attn_k_norm.weight | Block 20 Attn_K_Norm (W) | ( 256) 256 | 256 x 1 x 1 x 1 | F32 | 32.0000 | | 236 | blk.20.attn_k.weight | Block 20 Attention Key (W) | ( ~1M) 1310720 | 2560 x 512 x 1 x 1 | F16 | 16.0000 | | 237 | blk.20.attn_output.weight | Block 20 Attention Output (W) | ( ~5M) 5242880 | 2048 x 2560 x 1 x 1 | F16 | 16.0000 | | 238 | blk.20.attn_q_norm.weight | Block 20 Attn_Q_Norm (W) | ( 256) 256 | 256 x 1 x 1 x 1 | F32 | 32.0000 | | 239 | blk.20.attn_q.weight | Block 20 Attention Query (W) | ( ~5M) 5242880 | 2560 x 2048 x 1 x 1 | F16 | 16.0000 | | 240 | blk.20.attn_v.weight | Block 20 Attention Value (W) | ( ~1M) 1310720 | 2560 x 512 x 1 x 1 | F16 | 16.0000 | - Total elements in blk.20: (~93M) 93074433 - Percentage of total elements: 1.24% - Bits per Weight (BPW) for blk.20: 16.0023 bits ### Block 21 Tensor Group : ~93M Elements | T_ID | Tensor Layer Name | Human Friendly Tensor Layer Name | Elements | Shape | Type | BPW | | ---: | :-------------------------------- | :---------------------------------------------- | :--------------- | :-------------------- | :--- | ------: | | 241 | blk.21.attn_norm.weight | Block 21 Attention Normalization (W) | ( ~3K) 2560 | 2560 x 1 x 1 x 1 | F32 | 32.0000 | | 242 | blk.21.layer_output_scale.weight | Block 21 Layer_Output_Scale (W) | ( 1) 1 | 1 x 1 x 1 x 1 | F32 | 32.0000 | | 243 | blk.21.ffn_down.weight | Block 21 Feed-Forward Network "Down" (W) | ( ~26M) 26214400 | 10240 x 2560 x 1 x 1 | F16 | 16.0000 | | 244 | blk.21.ffn_gate.weight | Block 21 Feed-Forward Network "Gate" (W) | ( ~26M) 26214400 | 2560 x 10240 x 1 x 1 | F16 | 16.0000 | | 245 | blk.21.ffn_up.weight | Block 21 Feed-Forward Network "Up" (W) | ( ~26M) 26214400 | 2560 x 10240 x 1 x 1 | F16 | 16.0000 | | 246 | blk.21.inp_gate.weight | Block 21 Inp_Gate (W) | (~655K) 655360 | 2560 x 256 x 1 x 1 | F16 | 16.0000 | | 247 | blk.21.proj.weight | Block 21 Proj (W) | (~655K) 655360 | 256 x 2560 x 1 x 1 | F16 | 16.0000 | | 248 | blk.21.post_attention_norm.weight | Block 21 Post_Attention_Norm (W) | ( ~3K) 2560 | 2560 x 1 x 1 x 1 | F32 | 32.0000 | | 249 | blk.21.post_ffw_norm.weight | Block 21 Post_Ffw_Norm (W) | ( ~3K) 2560 | 2560 x 1 x 1 x 1 | F32 | 32.0000 | | 250 | blk.21.post_norm.weight | Block 21 Post_Norm (W) | ( ~3K) 2560 | 2560 x 1 x 1 x 1 | F32 | 32.0000 | | 251 | blk.21.ffn_norm.weight | Block 21 Feed-Forward Network Normalization (W) | ( ~3K) 2560 | 2560 x 1 x 1 x 1 | F32 | 32.0000 | | 252 | blk.21.attn_k_norm.weight | Block 21 Attn_K_Norm (W) | ( 256) 256 | 256 x 1 x 1 x 1 | F32 | 32.0000 | | 253 | blk.21.attn_k.weight | Block 21 Attention Key (W) | ( ~1M) 1310720 | 2560 x 512 x 1 x 1 | F16 | 16.0000 | | 254 | blk.21.attn_output.weight | Block 21 Attention Output (W) | ( ~5M) 5242880 | 2048 x 2560 x 1 x 1 | F16 | 16.0000 | | 255 | blk.21.attn_q_norm.weight | Block 21 Attn_Q_Norm (W) | ( 256) 256 | 256 x 1 x 1 x 1 | F32 | 32.0000 | | 256 | blk.21.attn_q.weight | Block 21 Attention Query (W) | ( ~5M) 5242880 | 2560 x 2048 x 1 x 1 | F16 | 16.0000 | | 257 | blk.21.attn_v.weight | Block 21 Attention Value (W) | ( ~1M) 1310720 | 2560 x 512 x 1 x 1 | F16 | 16.0000 | - Total elements in blk.21: (~93M) 93074433 - Percentage of total elements: 1.24% - Bits per Weight (BPW) for blk.21: 16.0023 bits ### Block 22 Tensor Group : ~93M Elements | T_ID | Tensor Layer Name | Human Friendly Tensor Layer Name | Elements | Shape | Type | BPW | | ---: | :-------------------------------- | :---------------------------------------------- | :--------------- | :-------------------- | :--- | ------: | | 258 | blk.22.attn_norm.weight | Block 22 Attention Normalization (W) | ( ~3K) 2560 | 2560 x 1 x 1 x 1 | F32 | 32.0000 | | 259 | blk.22.layer_output_scale.weight | Block 22 Layer_Output_Scale (W) | ( 1) 1 | 1 x 1 x 1 x 1 | F32 | 32.0000 | | 260 | blk.22.ffn_down.weight | Block 22 Feed-Forward Network "Down" (W) | ( ~26M) 26214400 | 10240 x 2560 x 1 x 1 | F16 | 16.0000 | | 261 | blk.22.ffn_gate.weight | Block 22 Feed-Forward Network "Gate" (W) | ( ~26M) 26214400 | 2560 x 10240 x 1 x 1 | F16 | 16.0000 | | 262 | blk.22.ffn_up.weight | Block 22 Feed-Forward Network "Up" (W) | ( ~26M) 26214400 | 2560 x 10240 x 1 x 1 | F16 | 16.0000 | | 263 | blk.22.inp_gate.weight | Block 22 Inp_Gate (W) | (~655K) 655360 | 2560 x 256 x 1 x 1 | F16 | 16.0000 | | 264 | blk.22.proj.weight | Block 22 Proj (W) | (~655K) 655360 | 256 x 2560 x 1 x 1 | F16 | 16.0000 | | 265 | blk.22.post_attention_norm.weight | Block 22 Post_Attention_Norm (W) | ( ~3K) 2560 | 2560 x 1 x 1 x 1 | F32 | 32.0000 | | 266 | blk.22.post_ffw_norm.weight | Block 22 Post_Ffw_Norm (W) | ( ~3K) 2560 | 2560 x 1 x 1 x 1 | F32 | 32.0000 | | 267 | blk.22.post_norm.weight | Block 22 Post_Norm (W) | ( ~3K) 2560 | 2560 x 1 x 1 x 1 | F32 | 32.0000 | | 268 | blk.22.ffn_norm.weight | Block 22 Feed-Forward Network Normalization (W) | ( ~3K) 2560 | 2560 x 1 x 1 x 1 | F32 | 32.0000 | | 269 | blk.22.attn_k_norm.weight | Block 22 Attn_K_Norm (W) | ( 256) 256 | 256 x 1 x 1 x 1 | F32 | 32.0000 | | 270 | blk.22.attn_k.weight | Block 22 Attention Key (W) | ( ~1M) 1310720 | 2560 x 512 x 1 x 1 | F16 | 16.0000 | | 271 | blk.22.attn_output.weight | Block 22 Attention Output (W) | ( ~5M) 5242880 | 2048 x 2560 x 1 x 1 | F16 | 16.0000 | | 272 | blk.22.attn_q_norm.weight | Block 22 Attn_Q_Norm (W) | ( 256) 256 | 256 x 1 x 1 x 1 | F32 | 32.0000 | | 273 | blk.22.attn_q.weight | Block 22 Attention Query (W) | ( ~5M) 5242880 | 2560 x 2048 x 1 x 1 | F16 | 16.0000 | | 274 | blk.22.attn_v.weight | Block 22 Attention Value (W) | ( ~1M) 1310720 | 2560 x 512 x 1 x 1 | F16 | 16.0000 | - Total elements in blk.22: (~93M) 93074433 - Percentage of total elements: 1.24% - Bits per Weight (BPW) for blk.22: 16.0023 bits ### Block 23 Tensor Group : ~106M Elements | T_ID | Tensor Layer Name | Human Friendly Tensor Layer Name | Elements | Shape | Type | BPW | | ---: | :-------------------------------- | :---------------------------------------------- | :--------------- | :-------------------- | :--- | ------: | | 275 | blk.23.attn_norm.weight | Block 23 Attention Normalization (W) | ( ~3K) 2560 | 2560 x 1 x 1 x 1 | F32 | 32.0000 | | 276 | blk.23.layer_output_scale.weight | Block 23 Layer_Output_Scale (W) | ( 1) 1 | 1 x 1 x 1 x 1 | F32 | 32.0000 | | 277 | blk.23.ffn_down.weight | Block 23 Feed-Forward Network "Down" (W) | ( ~26M) 26214400 | 10240 x 2560 x 1 x 1 | F16 | 16.0000 | | 278 | blk.23.ffn_gate.weight | Block 23 Feed-Forward Network "Gate" (W) | ( ~26M) 26214400 | 2560 x 10240 x 1 x 1 | F16 | 16.0000 | | 279 | blk.23.ffn_up.weight | Block 23 Feed-Forward Network "Up" (W) | ( ~26M) 26214400 | 2560 x 10240 x 1 x 1 | F16 | 16.0000 | | 280 | blk.23.inp_gate.weight | Block 23 Inp_Gate (W) | (~655K) 655360 | 2560 x 256 x 1 x 1 | F16 | 16.0000 | | 281 | blk.23.proj.weight | Block 23 Proj (W) | (~655K) 655360 | 256 x 2560 x 1 x 1 | F16 | 16.0000 | | 282 | blk.23.post_attention_norm.weight | Block 23 Post_Attention_Norm (W) | ( ~3K) 2560 | 2560 x 1 x 1 x 1 | F32 | 32.0000 | | 283 | blk.23.post_ffw_norm.weight | Block 23 Post_Ffw_Norm (W) | ( ~3K) 2560 | 2560 x 1 x 1 x 1 | F32 | 32.0000 | | 284 | blk.23.post_norm.weight | Block 23 Post_Norm (W) | ( ~3K) 2560 | 2560 x 1 x 1 x 1 | F32 | 32.0000 | | 285 | blk.23.ffn_norm.weight | Block 23 Feed-Forward Network Normalization (W) | ( ~3K) 2560 | 2560 x 1 x 1 x 1 | F32 | 32.0000 | | 286 | blk.23.attn_k_norm.weight | Block 23 Attn_K_Norm (W) | ( 512) 512 | 512 x 1 x 1 x 1 | F32 | 32.0000 | | 287 | blk.23.attn_k.weight | Block 23 Attention Key (W) | ( ~3M) 2621440 | 2560 x 1024 x 1 x 1 | F16 | 16.0000 | | 288 | blk.23.attn_output.weight | Block 23 Attention Output (W) | ( ~10M) 10485760 | 4096 x 2560 x 1 x 1 | F16 | 16.0000 | | 289 | blk.23.attn_q_norm.weight | Block 23 Attn_Q_Norm (W) | ( 512) 512 | 512 x 1 x 1 x 1 | F32 | 32.0000 | | 290 | blk.23.attn_q.weight | Block 23 Attention Query (W) | ( ~10M) 10485760 | 2560 x 4096 x 1 x 1 | F16 | 16.0000 | | 291 | blk.23.attn_v.weight | Block 23 Attention Value (W) | ( ~3M) 2621440 | 2560 x 1024 x 1 x 1 | F16 | 16.0000 | - Total elements in blk.23: (~106M) 106182145 - Percentage of total elements: 1.41% - Bits per Weight (BPW) for blk.23: 16.0021 bits ### Block 24 Tensor Group : ~93M Elements | T_ID | Tensor Layer Name | Human Friendly Tensor Layer Name | Elements | Shape | Type | BPW | | ---: | :-------------------------------- | :---------------------------------------------- | :--------------- | :-------------------- | :--- | ------: | | 292 | blk.24.attn_norm.weight | Block 24 Attention Normalization (W) | ( ~3K) 2560 | 2560 x 1 x 1 x 1 | F32 | 32.0000 | | 293 | blk.24.layer_output_scale.weight | Block 24 Layer_Output_Scale (W) | ( 1) 1 | 1 x 1 x 1 x 1 | F32 | 32.0000 | | 294 | blk.24.ffn_down.weight | Block 24 Feed-Forward Network "Down" (W) | ( ~26M) 26214400 | 10240 x 2560 x 1 x 1 | F16 | 16.0000 | | 295 | blk.24.ffn_gate.weight | Block 24 Feed-Forward Network "Gate" (W) | ( ~26M) 26214400 | 2560 x 10240 x 1 x 1 | F16 | 16.0000 | | 296 | blk.24.ffn_up.weight | Block 24 Feed-Forward Network "Up" (W) | ( ~26M) 26214400 | 2560 x 10240 x 1 x 1 | F16 | 16.0000 | | 297 | blk.24.inp_gate.weight | Block 24 Inp_Gate (W) | (~655K) 655360 | 2560 x 256 x 1 x 1 | F16 | 16.0000 | | 298 | blk.24.proj.weight | Block 24 Proj (W) | (~655K) 655360 | 256 x 2560 x 1 x 1 | F16 | 16.0000 | | 299 | blk.24.post_attention_norm.weight | Block 24 Post_Attention_Norm (W) | ( ~3K) 2560 | 2560 x 1 x 1 x 1 | F32 | 32.0000 | | 300 | blk.24.post_ffw_norm.weight | Block 24 Post_Ffw_Norm (W) | ( ~3K) 2560 | 2560 x 1 x 1 x 1 | F32 | 32.0000 | | 301 | blk.24.post_norm.weight | Block 24 Post_Norm (W) | ( ~3K) 2560 | 2560 x 1 x 1 x 1 | F32 | 32.0000 | | 302 | blk.24.ffn_norm.weight | Block 24 Feed-Forward Network Normalization (W) | ( ~3K) 2560 | 2560 x 1 x 1 x 1 | F32 | 32.0000 | | 303 | blk.24.attn_k_norm.weight | Block 24 Attn_K_Norm (W) | ( 256) 256 | 256 x 1 x 1 x 1 | F32 | 32.0000 | | 304 | blk.24.attn_k.weight | Block 24 Attention Key (W) | ( ~1M) 1310720 | 2560 x 512 x 1 x 1 | F16 | 16.0000 | | 305 | blk.24.attn_output.weight | Block 24 Attention Output (W) | ( ~5M) 5242880 | 2048 x 2560 x 1 x 1 | F16 | 16.0000 | | 306 | blk.24.attn_q_norm.weight | Block 24 Attn_Q_Norm (W) | ( 256) 256 | 256 x 1 x 1 x 1 | F32 | 32.0000 | | 307 | blk.24.attn_q.weight | Block 24 Attention Query (W) | ( ~5M) 5242880 | 2560 x 2048 x 1 x 1 | F16 | 16.0000 | | 308 | blk.24.attn_v.weight | Block 24 Attention Value (W) | ( ~1M) 1310720 | 2560 x 512 x 1 x 1 | F16 | 16.0000 | - Total elements in blk.24: (~93M) 93074433 - Percentage of total elements: 1.24% - Bits per Weight (BPW) for blk.24: 16.0023 bits ### Block 25 Tensor Group : ~93M Elements | T_ID | Tensor Layer Name | Human Friendly Tensor Layer Name | Elements | Shape | Type | BPW | | ---: | :-------------------------------- | :---------------------------------------------- | :--------------- | :-------------------- | :--- | ------: | | 309 | blk.25.attn_norm.weight | Block 25 Attention Normalization (W) | ( ~3K) 2560 | 2560 x 1 x 1 x 1 | F32 | 32.0000 | | 310 | blk.25.layer_output_scale.weight | Block 25 Layer_Output_Scale (W) | ( 1) 1 | 1 x 1 x 1 x 1 | F32 | 32.0000 | | 311 | blk.25.ffn_down.weight | Block 25 Feed-Forward Network "Down" (W) | ( ~26M) 26214400 | 10240 x 2560 x 1 x 1 | F16 | 16.0000 | | 312 | blk.25.ffn_gate.weight | Block 25 Feed-Forward Network "Gate" (W) | ( ~26M) 26214400 | 2560 x 10240 x 1 x 1 | F16 | 16.0000 | | 313 | blk.25.ffn_up.weight | Block 25 Feed-Forward Network "Up" (W) | ( ~26M) 26214400 | 2560 x 10240 x 1 x 1 | F16 | 16.0000 | | 314 | blk.25.inp_gate.weight | Block 25 Inp_Gate (W) | (~655K) 655360 | 2560 x 256 x 1 x 1 | F16 | 16.0000 | | 315 | blk.25.proj.weight | Block 25 Proj (W) | (~655K) 655360 | 256 x 2560 x 1 x 1 | F16 | 16.0000 | | 316 | blk.25.post_attention_norm.weight | Block 25 Post_Attention_Norm (W) | ( ~3K) 2560 | 2560 x 1 x 1 x 1 | F32 | 32.0000 | | 317 | blk.25.post_ffw_norm.weight | Block 25 Post_Ffw_Norm (W) | ( ~3K) 2560 | 2560 x 1 x 1 x 1 | F32 | 32.0000 | | 318 | blk.25.post_norm.weight | Block 25 Post_Norm (W) | ( ~3K) 2560 | 2560 x 1 x 1 x 1 | F32 | 32.0000 | | 319 | blk.25.ffn_norm.weight | Block 25 Feed-Forward Network Normalization (W) | ( ~3K) 2560 | 2560 x 1 x 1 x 1 | F32 | 32.0000 | | 320 | blk.25.attn_k_norm.weight | Block 25 Attn_K_Norm (W) | ( 256) 256 | 256 x 1 x 1 x 1 | F32 | 32.0000 | | 321 | blk.25.attn_k.weight | Block 25 Attention Key (W) | ( ~1M) 1310720 | 2560 x 512 x 1 x 1 | F16 | 16.0000 | | 322 | blk.25.attn_output.weight | Block 25 Attention Output (W) | ( ~5M) 5242880 | 2048 x 2560 x 1 x 1 | F16 | 16.0000 | | 323 | blk.25.attn_q_norm.weight | Block 25 Attn_Q_Norm (W) | ( 256) 256 | 256 x 1 x 1 x 1 | F32 | 32.0000 | | 324 | blk.25.attn_q.weight | Block 25 Attention Query (W) | ( ~5M) 5242880 | 2560 x 2048 x 1 x 1 | F16 | 16.0000 | | 325 | blk.25.attn_v.weight | Block 25 Attention Value (W) | ( ~1M) 1310720 | 2560 x 512 x 1 x 1 | F16 | 16.0000 | - Total elements in blk.25: (~93M) 93074433 - Percentage of total elements: 1.24% - Bits per Weight (BPW) for blk.25: 16.0023 bits ### Block 26 Tensor Group : ~93M Elements | T_ID | Tensor Layer Name | Human Friendly Tensor Layer Name | Elements | Shape | Type | BPW | | ---: | :-------------------------------- | :---------------------------------------------- | :--------------- | :-------------------- | :--- | ------: | | 326 | blk.26.attn_norm.weight | Block 26 Attention Normalization (W) | ( ~3K) 2560 | 2560 x 1 x 1 x 1 | F32 | 32.0000 | | 327 | blk.26.layer_output_scale.weight | Block 26 Layer_Output_Scale (W) | ( 1) 1 | 1 x 1 x 1 x 1 | F32 | 32.0000 | | 328 | blk.26.ffn_down.weight | Block 26 Feed-Forward Network "Down" (W) | ( ~26M) 26214400 | 10240 x 2560 x 1 x 1 | F16 | 16.0000 | | 329 | blk.26.ffn_gate.weight | Block 26 Feed-Forward Network "Gate" (W) | ( ~26M) 26214400 | 2560 x 10240 x 1 x 1 | F16 | 16.0000 | | 330 | blk.26.ffn_up.weight | Block 26 Feed-Forward Network "Up" (W) | ( ~26M) 26214400 | 2560 x 10240 x 1 x 1 | F16 | 16.0000 | | 331 | blk.26.inp_gate.weight | Block 26 Inp_Gate (W) | (~655K) 655360 | 2560 x 256 x 1 x 1 | F16 | 16.0000 | | 332 | blk.26.proj.weight | Block 26 Proj (W) | (~655K) 655360 | 256 x 2560 x 1 x 1 | F16 | 16.0000 | | 333 | blk.26.post_attention_norm.weight | Block 26 Post_Attention_Norm (W) | ( ~3K) 2560 | 2560 x 1 x 1 x 1 | F32 | 32.0000 | | 334 | blk.26.post_ffw_norm.weight | Block 26 Post_Ffw_Norm (W) | ( ~3K) 2560 | 2560 x 1 x 1 x 1 | F32 | 32.0000 | | 335 | blk.26.post_norm.weight | Block 26 Post_Norm (W) | ( ~3K) 2560 | 2560 x 1 x 1 x 1 | F32 | 32.0000 | | 336 | blk.26.ffn_norm.weight | Block 26 Feed-Forward Network Normalization (W) | ( ~3K) 2560 | 2560 x 1 x 1 x 1 | F32 | 32.0000 | | 337 | blk.26.attn_k_norm.weight | Block 26 Attn_K_Norm (W) | ( 256) 256 | 256 x 1 x 1 x 1 | F32 | 32.0000 | | 338 | blk.26.attn_k.weight | Block 26 Attention Key (W) | ( ~1M) 1310720 | 2560 x 512 x 1 x 1 | F16 | 16.0000 | | 339 | blk.26.attn_output.weight | Block 26 Attention Output (W) | ( ~5M) 5242880 | 2048 x 2560 x 1 x 1 | F16 | 16.0000 | | 340 | blk.26.attn_q_norm.weight | Block 26 Attn_Q_Norm (W) | ( 256) 256 | 256 x 1 x 1 x 1 | F32 | 32.0000 | | 341 | blk.26.attn_q.weight | Block 26 Attention Query (W) | ( ~5M) 5242880 | 2560 x 2048 x 1 x 1 | F16 | 16.0000 | | 342 | blk.26.attn_v.weight | Block 26 Attention Value (W) | ( ~1M) 1310720 | 2560 x 512 x 1 x 1 | F16 | 16.0000 | - Total elements in blk.26: (~93M) 93074433 - Percentage of total elements: 1.24% - Bits per Weight (BPW) for blk.26: 16.0023 bits ### Block 27 Tensor Group : ~93M Elements | T_ID | Tensor Layer Name | Human Friendly Tensor Layer Name | Elements | Shape | Type | BPW | | ---: | :-------------------------------- | :---------------------------------------------- | :--------------- | :-------------------- | :--- | ------: | | 343 | blk.27.attn_norm.weight | Block 27 Attention Normalization (W) | ( ~3K) 2560 | 2560 x 1 x 1 x 1 | F32 | 32.0000 | | 344 | blk.27.layer_output_scale.weight | Block 27 Layer_Output_Scale (W) | ( 1) 1 | 1 x 1 x 1 x 1 | F32 | 32.0000 | | 345 | blk.27.ffn_down.weight | Block 27 Feed-Forward Network "Down" (W) | ( ~26M) 26214400 | 10240 x 2560 x 1 x 1 | F16 | 16.0000 | | 346 | blk.27.ffn_gate.weight | Block 27 Feed-Forward Network "Gate" (W) | ( ~26M) 26214400 | 2560 x 10240 x 1 x 1 | F16 | 16.0000 | | 347 | blk.27.ffn_up.weight | Block 27 Feed-Forward Network "Up" (W) | ( ~26M) 26214400 | 2560 x 10240 x 1 x 1 | F16 | 16.0000 | | 348 | blk.27.inp_gate.weight | Block 27 Inp_Gate (W) | (~655K) 655360 | 2560 x 256 x 1 x 1 | F16 | 16.0000 | | 349 | blk.27.proj.weight | Block 27 Proj (W) | (~655K) 655360 | 256 x 2560 x 1 x 1 | F16 | 16.0000 | | 350 | blk.27.post_attention_norm.weight | Block 27 Post_Attention_Norm (W) | ( ~3K) 2560 | 2560 x 1 x 1 x 1 | F32 | 32.0000 | | 351 | blk.27.post_ffw_norm.weight | Block 27 Post_Ffw_Norm (W) | ( ~3K) 2560 | 2560 x 1 x 1 x 1 | F32 | 32.0000 | | 352 | blk.27.post_norm.weight | Block 27 Post_Norm (W) | ( ~3K) 2560 | 2560 x 1 x 1 x 1 | F32 | 32.0000 | | 353 | blk.27.ffn_norm.weight | Block 27 Feed-Forward Network Normalization (W) | ( ~3K) 2560 | 2560 x 1 x 1 x 1 | F32 | 32.0000 | | 354 | blk.27.attn_k_norm.weight | Block 27 Attn_K_Norm (W) | ( 256) 256 | 256 x 1 x 1 x 1 | F32 | 32.0000 | | 355 | blk.27.attn_k.weight | Block 27 Attention Key (W) | ( ~1M) 1310720 | 2560 x 512 x 1 x 1 | F16 | 16.0000 | | 356 | blk.27.attn_output.weight | Block 27 Attention Output (W) | ( ~5M) 5242880 | 2048 x 2560 x 1 x 1 | F16 | 16.0000 | | 357 | blk.27.attn_q_norm.weight | Block 27 Attn_Q_Norm (W) | ( 256) 256 | 256 x 1 x 1 x 1 | F32 | 32.0000 | | 358 | blk.27.attn_q.weight | Block 27 Attention Query (W) | ( ~5M) 5242880 | 2560 x 2048 x 1 x 1 | F16 | 16.0000 | | 359 | blk.27.attn_v.weight | Block 27 Attention Value (W) | ( ~1M) 1310720 | 2560 x 512 x 1 x 1 | F16 | 16.0000 | - Total elements in blk.27: (~93M) 93074433 - Percentage of total elements: 1.24% - Bits per Weight (BPW) for blk.27: 16.0023 bits ### Block 28 Tensor Group : ~93M Elements | T_ID | Tensor Layer Name | Human Friendly Tensor Layer Name | Elements | Shape | Type | BPW | | ---: | :-------------------------------- | :---------------------------------------------- | :--------------- | :-------------------- | :--- | ------: | | 360 | blk.28.attn_norm.weight | Block 28 Attention Normalization (W) | ( ~3K) 2560 | 2560 x 1 x 1 x 1 | F32 | 32.0000 | | 361 | blk.28.layer_output_scale.weight | Block 28 Layer_Output_Scale (W) | ( 1) 1 | 1 x 1 x 1 x 1 | F32 | 32.0000 | | 362 | blk.28.ffn_down.weight | Block 28 Feed-Forward Network "Down" (W) | ( ~26M) 26214400 | 10240 x 2560 x 1 x 1 | F16 | 16.0000 | | 363 | blk.28.ffn_gate.weight | Block 28 Feed-Forward Network "Gate" (W) | ( ~26M) 26214400 | 2560 x 10240 x 1 x 1 | F16 | 16.0000 | | 364 | blk.28.ffn_up.weight | Block 28 Feed-Forward Network "Up" (W) | ( ~26M) 26214400 | 2560 x 10240 x 1 x 1 | F16 | 16.0000 | | 365 | blk.28.inp_gate.weight | Block 28 Inp_Gate (W) | (~655K) 655360 | 2560 x 256 x 1 x 1 | F16 | 16.0000 | | 366 | blk.28.proj.weight | Block 28 Proj (W) | (~655K) 655360 | 256 x 2560 x 1 x 1 | F16 | 16.0000 | | 367 | blk.28.post_attention_norm.weight | Block 28 Post_Attention_Norm (W) | ( ~3K) 2560 | 2560 x 1 x 1 x 1 | F32 | 32.0000 | | 368 | blk.28.post_ffw_norm.weight | Block 28 Post_Ffw_Norm (W) | ( ~3K) 2560 | 2560 x 1 x 1 x 1 | F32 | 32.0000 | | 369 | blk.28.post_norm.weight | Block 28 Post_Norm (W) | ( ~3K) 2560 | 2560 x 1 x 1 x 1 | F32 | 32.0000 | | 370 | blk.28.ffn_norm.weight | Block 28 Feed-Forward Network Normalization (W) | ( ~3K) 2560 | 2560 x 1 x 1 x 1 | F32 | 32.0000 | | 371 | blk.28.attn_k_norm.weight | Block 28 Attn_K_Norm (W) | ( 256) 256 | 256 x 1 x 1 x 1 | F32 | 32.0000 | | 372 | blk.28.attn_k.weight | Block 28 Attention Key (W) | ( ~1M) 1310720 | 2560 x 512 x 1 x 1 | F16 | 16.0000 | | 373 | blk.28.attn_output.weight | Block 28 Attention Output (W) | ( ~5M) 5242880 | 2048 x 2560 x 1 x 1 | F16 | 16.0000 | | 374 | blk.28.attn_q_norm.weight | Block 28 Attn_Q_Norm (W) | ( 256) 256 | 256 x 1 x 1 x 1 | F32 | 32.0000 | | 375 | blk.28.attn_q.weight | Block 28 Attention Query (W) | ( ~5M) 5242880 | 2560 x 2048 x 1 x 1 | F16 | 16.0000 | | 376 | blk.28.attn_v.weight | Block 28 Attention Value (W) | ( ~1M) 1310720 | 2560 x 512 x 1 x 1 | F16 | 16.0000 | - Total elements in blk.28: (~93M) 93074433 - Percentage of total elements: 1.24% - Bits per Weight (BPW) for blk.28: 16.0023 bits ### Block 29 Tensor Group : ~106M Elements | T_ID | Tensor Layer Name | Human Friendly Tensor Layer Name | Elements | Shape | Type | BPW | | ---: | :-------------------------------- | :---------------------------------------------- | :--------------- | :-------------------- | :--- | ------: | | 377 | blk.29.attn_norm.weight | Block 29 Attention Normalization (W) | ( ~3K) 2560 | 2560 x 1 x 1 x 1 | F32 | 32.0000 | | 378 | blk.29.layer_output_scale.weight | Block 29 Layer_Output_Scale (W) | ( 1) 1 | 1 x 1 x 1 x 1 | F32 | 32.0000 | | 379 | blk.29.ffn_down.weight | Block 29 Feed-Forward Network "Down" (W) | ( ~26M) 26214400 | 10240 x 2560 x 1 x 1 | F16 | 16.0000 | | 380 | blk.29.ffn_gate.weight | Block 29 Feed-Forward Network "Gate" (W) | ( ~26M) 26214400 | 2560 x 10240 x 1 x 1 | F16 | 16.0000 | | 381 | blk.29.ffn_up.weight | Block 29 Feed-Forward Network "Up" (W) | ( ~26M) 26214400 | 2560 x 10240 x 1 x 1 | F16 | 16.0000 | | 382 | blk.29.inp_gate.weight | Block 29 Inp_Gate (W) | (~655K) 655360 | 2560 x 256 x 1 x 1 | F16 | 16.0000 | | 383 | blk.29.proj.weight | Block 29 Proj (W) | (~655K) 655360 | 256 x 2560 x 1 x 1 | F16 | 16.0000 | | 384 | blk.29.post_attention_norm.weight | Block 29 Post_Attention_Norm (W) | ( ~3K) 2560 | 2560 x 1 x 1 x 1 | F32 | 32.0000 | | 385 | blk.29.post_ffw_norm.weight | Block 29 Post_Ffw_Norm (W) | ( ~3K) 2560 | 2560 x 1 x 1 x 1 | F32 | 32.0000 | | 386 | blk.29.post_norm.weight | Block 29 Post_Norm (W) | ( ~3K) 2560 | 2560 x 1 x 1 x 1 | F32 | 32.0000 | | 387 | blk.29.ffn_norm.weight | Block 29 Feed-Forward Network Normalization (W) | ( ~3K) 2560 | 2560 x 1 x 1 x 1 | F32 | 32.0000 | | 388 | blk.29.attn_k_norm.weight | Block 29 Attn_K_Norm (W) | ( 512) 512 | 512 x 1 x 1 x 1 | F32 | 32.0000 | | 389 | blk.29.attn_k.weight | Block 29 Attention Key (W) | ( ~3M) 2621440 | 2560 x 1024 x 1 x 1 | F16 | 16.0000 | | 390 | blk.29.attn_output.weight | Block 29 Attention Output (W) | ( ~10M) 10485760 | 4096 x 2560 x 1 x 1 | F16 | 16.0000 | | 391 | blk.29.attn_q_norm.weight | Block 29 Attn_Q_Norm (W) | ( 512) 512 | 512 x 1 x 1 x 1 | F32 | 32.0000 | | 392 | blk.29.attn_q.weight | Block 29 Attention Query (W) | ( ~10M) 10485760 | 2560 x 4096 x 1 x 1 | F16 | 16.0000 | | 393 | blk.29.attn_v.weight | Block 29 Attention Value (W) | ( ~3M) 2621440 | 2560 x 1024 x 1 x 1 | F16 | 16.0000 | - Total elements in blk.29: (~106M) 106182145 - Percentage of total elements: 1.41% - Bits per Weight (BPW) for blk.29: 16.0021 bits ### Block 3 Tensor Group : ~93M Elements | T_ID | Tensor Layer Name | Human Friendly Tensor Layer Name | Elements | Shape | Type | BPW | | ---: | :------------------------------- | :--------------------------------------------- | :--------------- | :-------------------- | :--- | ------: | | 394 | blk.3.attn_norm.weight | Block 3 Attention Normalization (W) | ( ~3K) 2560 | 2560 x 1 x 1 x 1 | F32 | 32.0000 | | 395 | blk.3.layer_output_scale.weight | Block 3 Layer_Output_Scale (W) | ( 1) 1 | 1 x 1 x 1 x 1 | F32 | 32.0000 | | 396 | blk.3.ffn_down.weight | Block 3 Feed-Forward Network "Down" (W) | ( ~26M) 26214400 | 10240 x 2560 x 1 x 1 | F16 | 16.0000 | | 397 | blk.3.ffn_gate.weight | Block 3 Feed-Forward Network "Gate" (W) | ( ~26M) 26214400 | 2560 x 10240 x 1 x 1 | F16 | 16.0000 | | 398 | blk.3.ffn_up.weight | Block 3 Feed-Forward Network "Up" (W) | ( ~26M) 26214400 | 2560 x 10240 x 1 x 1 | F16 | 16.0000 | | 399 | blk.3.inp_gate.weight | Block 3 Inp_Gate (W) | (~655K) 655360 | 2560 x 256 x 1 x 1 | F16 | 16.0000 | | 400 | blk.3.proj.weight | Block 3 Proj (W) | (~655K) 655360 | 256 x 2560 x 1 x 1 | F16 | 16.0000 | | 401 | blk.3.post_attention_norm.weight | Block 3 Post_Attention_Norm (W) | ( ~3K) 2560 | 2560 x 1 x 1 x 1 | F32 | 32.0000 | | 402 | blk.3.post_ffw_norm.weight | Block 3 Post_Ffw_Norm (W) | ( ~3K) 2560 | 2560 x 1 x 1 x 1 | F32 | 32.0000 | | 403 | blk.3.post_norm.weight | Block 3 Post_Norm (W) | ( ~3K) 2560 | 2560 x 1 x 1 x 1 | F32 | 32.0000 | | 404 | blk.3.ffn_norm.weight | Block 3 Feed-Forward Network Normalization (W) | ( ~3K) 2560 | 2560 x 1 x 1 x 1 | F32 | 32.0000 | | 405 | blk.3.attn_k_norm.weight | Block 3 Attn_K_Norm (W) | ( 256) 256 | 256 x 1 x 1 x 1 | F32 | 32.0000 | | 406 | blk.3.attn_k.weight | Block 3 Attention Key (W) | ( ~1M) 1310720 | 2560 x 512 x 1 x 1 | F16 | 16.0000 | | 407 | blk.3.attn_output.weight | Block 3 Attention Output (W) | ( ~5M) 5242880 | 2048 x 2560 x 1 x 1 | F16 | 16.0000 | | 408 | blk.3.attn_q_norm.weight | Block 3 Attn_Q_Norm (W) | ( 256) 256 | 256 x 1 x 1 x 1 | F32 | 32.0000 | | 409 | blk.3.attn_q.weight | Block 3 Attention Query (W) | ( ~5M) 5242880 | 2560 x 2048 x 1 x 1 | F16 | 16.0000 | | 410 | blk.3.attn_v.weight | Block 3 Attention Value (W) | ( ~1M) 1310720 | 2560 x 512 x 1 x 1 | F16 | 16.0000 | - Total elements in blk.3: (~93M) 93074433 - Percentage of total elements: 1.24% - Bits per Weight (BPW) for blk.3: 16.0023 bits ### Block 30 Tensor Group : ~93M Elements | T_ID | Tensor Layer Name | Human Friendly Tensor Layer Name | Elements | Shape | Type | BPW | | ---: | :-------------------------------- | :---------------------------------------------- | :--------------- | :-------------------- | :--- | ------: | | 411 | blk.30.attn_norm.weight | Block 30 Attention Normalization (W) | ( ~3K) 2560 | 2560 x 1 x 1 x 1 | F32 | 32.0000 | | 412 | blk.30.layer_output_scale.weight | Block 30 Layer_Output_Scale (W) | ( 1) 1 | 1 x 1 x 1 x 1 | F32 | 32.0000 | | 413 | blk.30.ffn_down.weight | Block 30 Feed-Forward Network "Down" (W) | ( ~26M) 26214400 | 10240 x 2560 x 1 x 1 | F16 | 16.0000 | | 414 | blk.30.ffn_gate.weight | Block 30 Feed-Forward Network "Gate" (W) | ( ~26M) 26214400 | 2560 x 10240 x 1 x 1 | F16 | 16.0000 | | 415 | blk.30.ffn_up.weight | Block 30 Feed-Forward Network "Up" (W) | ( ~26M) 26214400 | 2560 x 10240 x 1 x 1 | F16 | 16.0000 | | 416 | blk.30.inp_gate.weight | Block 30 Inp_Gate (W) | (~655K) 655360 | 2560 x 256 x 1 x 1 | F16 | 16.0000 | | 417 | blk.30.proj.weight | Block 30 Proj (W) | (~655K) 655360 | 256 x 2560 x 1 x 1 | F16 | 16.0000 | | 418 | blk.30.post_attention_norm.weight | Block 30 Post_Attention_Norm (W) | ( ~3K) 2560 | 2560 x 1 x 1 x 1 | F32 | 32.0000 | | 419 | blk.30.post_ffw_norm.weight | Block 30 Post_Ffw_Norm (W) | ( ~3K) 2560 | 2560 x 1 x 1 x 1 | F32 | 32.0000 | | 420 | blk.30.post_norm.weight | Block 30 Post_Norm (W) | ( ~3K) 2560 | 2560 x 1 x 1 x 1 | F32 | 32.0000 | | 421 | blk.30.ffn_norm.weight | Block 30 Feed-Forward Network Normalization (W) | ( ~3K) 2560 | 2560 x 1 x 1 x 1 | F32 | 32.0000 | | 422 | blk.30.attn_k_norm.weight | Block 30 Attn_K_Norm (W) | ( 256) 256 | 256 x 1 x 1 x 1 | F32 | 32.0000 | | 423 | blk.30.attn_k.weight | Block 30 Attention Key (W) | ( ~1M) 1310720 | 2560 x 512 x 1 x 1 | F16 | 16.0000 | | 424 | blk.30.attn_output.weight | Block 30 Attention Output (W) | ( ~5M) 5242880 | 2048 x 2560 x 1 x 1 | F16 | 16.0000 | | 425 | blk.30.attn_q_norm.weight | Block 30 Attn_Q_Norm (W) | ( 256) 256 | 256 x 1 x 1 x 1 | F32 | 32.0000 | | 426 | blk.30.attn_q.weight | Block 30 Attention Query (W) | ( ~5M) 5242880 | 2560 x 2048 x 1 x 1 | F16 | 16.0000 | | 427 | blk.30.attn_v.weight | Block 30 Attention Value (W) | ( ~1M) 1310720 | 2560 x 512 x 1 x 1 | F16 | 16.0000 | - Total elements in blk.30: (~93M) 93074433 - Percentage of total elements: 1.24% - Bits per Weight (BPW) for blk.30: 16.0023 bits ### Block 31 Tensor Group : ~93M Elements | T_ID | Tensor Layer Name | Human Friendly Tensor Layer Name | Elements | Shape | Type | BPW | | ---: | :-------------------------------- | :---------------------------------------------- | :--------------- | :-------------------- | :--- | ------: | | 428 | blk.31.attn_norm.weight | Block 31 Attention Normalization (W) | ( ~3K) 2560 | 2560 x 1 x 1 x 1 | F32 | 32.0000 | | 429 | blk.31.layer_output_scale.weight | Block 31 Layer_Output_Scale (W) | ( 1) 1 | 1 x 1 x 1 x 1 | F32 | 32.0000 | | 430 | blk.31.ffn_down.weight | Block 31 Feed-Forward Network "Down" (W) | ( ~26M) 26214400 | 10240 x 2560 x 1 x 1 | F16 | 16.0000 | | 431 | blk.31.ffn_gate.weight | Block 31 Feed-Forward Network "Gate" (W) | ( ~26M) 26214400 | 2560 x 10240 x 1 x 1 | F16 | 16.0000 | | 432 | blk.31.ffn_up.weight | Block 31 Feed-Forward Network "Up" (W) | ( ~26M) 26214400 | 2560 x 10240 x 1 x 1 | F16 | 16.0000 | | 433 | blk.31.inp_gate.weight | Block 31 Inp_Gate (W) | (~655K) 655360 | 2560 x 256 x 1 x 1 | F16 | 16.0000 | | 434 | blk.31.proj.weight | Block 31 Proj (W) | (~655K) 655360 | 256 x 2560 x 1 x 1 | F16 | 16.0000 | | 435 | blk.31.post_attention_norm.weight | Block 31 Post_Attention_Norm (W) | ( ~3K) 2560 | 2560 x 1 x 1 x 1 | F32 | 32.0000 | | 436 | blk.31.post_ffw_norm.weight | Block 31 Post_Ffw_Norm (W) | ( ~3K) 2560 | 2560 x 1 x 1 x 1 | F32 | 32.0000 | | 437 | blk.31.post_norm.weight | Block 31 Post_Norm (W) | ( ~3K) 2560 | 2560 x 1 x 1 x 1 | F32 | 32.0000 | | 438 | blk.31.ffn_norm.weight | Block 31 Feed-Forward Network Normalization (W) | ( ~3K) 2560 | 2560 x 1 x 1 x 1 | F32 | 32.0000 | | 439 | blk.31.attn_k_norm.weight | Block 31 Attn_K_Norm (W) | ( 256) 256 | 256 x 1 x 1 x 1 | F32 | 32.0000 | | 440 | blk.31.attn_k.weight | Block 31 Attention Key (W) | ( ~1M) 1310720 | 2560 x 512 x 1 x 1 | F16 | 16.0000 | | 441 | blk.31.attn_output.weight | Block 31 Attention Output (W) | ( ~5M) 5242880 | 2048 x 2560 x 1 x 1 | F16 | 16.0000 | | 442 | blk.31.attn_q_norm.weight | Block 31 Attn_Q_Norm (W) | ( 256) 256 | 256 x 1 x 1 x 1 | F32 | 32.0000 | | 443 | blk.31.attn_q.weight | Block 31 Attention Query (W) | ( ~5M) 5242880 | 2560 x 2048 x 1 x 1 | F16 | 16.0000 | | 444 | blk.31.attn_v.weight | Block 31 Attention Value (W) | ( ~1M) 1310720 | 2560 x 512 x 1 x 1 | F16 | 16.0000 | - Total elements in blk.31: (~93M) 93074433 - Percentage of total elements: 1.24% - Bits per Weight (BPW) for blk.31: 16.0023 bits ### Block 32 Tensor Group : ~93M Elements | T_ID | Tensor Layer Name | Human Friendly Tensor Layer Name | Elements | Shape | Type | BPW | | ---: | :-------------------------------- | :---------------------------------------------- | :--------------- | :-------------------- | :--- | ------: | | 445 | blk.32.attn_norm.weight | Block 32 Attention Normalization (W) | ( ~3K) 2560 | 2560 x 1 x 1 x 1 | F32 | 32.0000 | | 446 | blk.32.layer_output_scale.weight | Block 32 Layer_Output_Scale (W) | ( 1) 1 | 1 x 1 x 1 x 1 | F32 | 32.0000 | | 447 | blk.32.ffn_down.weight | Block 32 Feed-Forward Network "Down" (W) | ( ~26M) 26214400 | 10240 x 2560 x 1 x 1 | F16 | 16.0000 | | 448 | blk.32.ffn_gate.weight | Block 32 Feed-Forward Network "Gate" (W) | ( ~26M) 26214400 | 2560 x 10240 x 1 x 1 | F16 | 16.0000 | | 449 | blk.32.ffn_up.weight | Block 32 Feed-Forward Network "Up" (W) | ( ~26M) 26214400 | 2560 x 10240 x 1 x 1 | F16 | 16.0000 | | 450 | blk.32.inp_gate.weight | Block 32 Inp_Gate (W) | (~655K) 655360 | 2560 x 256 x 1 x 1 | F16 | 16.0000 | | 451 | blk.32.proj.weight | Block 32 Proj (W) | (~655K) 655360 | 256 x 2560 x 1 x 1 | F16 | 16.0000 | | 452 | blk.32.post_attention_norm.weight | Block 32 Post_Attention_Norm (W) | ( ~3K) 2560 | 2560 x 1 x 1 x 1 | F32 | 32.0000 | | 453 | blk.32.post_ffw_norm.weight | Block 32 Post_Ffw_Norm (W) | ( ~3K) 2560 | 2560 x 1 x 1 x 1 | F32 | 32.0000 | | 454 | blk.32.post_norm.weight | Block 32 Post_Norm (W) | ( ~3K) 2560 | 2560 x 1 x 1 x 1 | F32 | 32.0000 | | 455 | blk.32.ffn_norm.weight | Block 32 Feed-Forward Network Normalization (W) | ( ~3K) 2560 | 2560 x 1 x 1 x 1 | F32 | 32.0000 | | 456 | blk.32.attn_k_norm.weight | Block 32 Attn_K_Norm (W) | ( 256) 256 | 256 x 1 x 1 x 1 | F32 | 32.0000 | | 457 | blk.32.attn_k.weight | Block 32 Attention Key (W) | ( ~1M) 1310720 | 2560 x 512 x 1 x 1 | F16 | 16.0000 | | 458 | blk.32.attn_output.weight | Block 32 Attention Output (W) | ( ~5M) 5242880 | 2048 x 2560 x 1 x 1 | F16 | 16.0000 | | 459 | blk.32.attn_q_norm.weight | Block 32 Attn_Q_Norm (W) | ( 256) 256 | 256 x 1 x 1 x 1 | F32 | 32.0000 | | 460 | blk.32.attn_q.weight | Block 32 Attention Query (W) | ( ~5M) 5242880 | 2560 x 2048 x 1 x 1 | F16 | 16.0000 | | 461 | blk.32.attn_v.weight | Block 32 Attention Value (W) | ( ~1M) 1310720 | 2560 x 512 x 1 x 1 | F16 | 16.0000 | - Total elements in blk.32: (~93M) 93074433 - Percentage of total elements: 1.24% - Bits per Weight (BPW) for blk.32: 16.0023 bits ### Block 33 Tensor Group : ~93M Elements | T_ID | Tensor Layer Name | Human Friendly Tensor Layer Name | Elements | Shape | Type | BPW | | ---: | :-------------------------------- | :---------------------------------------------- | :--------------- | :-------------------- | :--- | ------: | | 462 | blk.33.attn_norm.weight | Block 33 Attention Normalization (W) | ( ~3K) 2560 | 2560 x 1 x 1 x 1 | F32 | 32.0000 | | 463 | blk.33.layer_output_scale.weight | Block 33 Layer_Output_Scale (W) | ( 1) 1 | 1 x 1 x 1 x 1 | F32 | 32.0000 | | 464 | blk.33.ffn_down.weight | Block 33 Feed-Forward Network "Down" (W) | ( ~26M) 26214400 | 10240 x 2560 x 1 x 1 | F16 | 16.0000 | | 465 | blk.33.ffn_gate.weight | Block 33 Feed-Forward Network "Gate" (W) | ( ~26M) 26214400 | 2560 x 10240 x 1 x 1 | F16 | 16.0000 | | 466 | blk.33.ffn_up.weight | Block 33 Feed-Forward Network "Up" (W) | ( ~26M) 26214400 | 2560 x 10240 x 1 x 1 | F16 | 16.0000 | | 467 | blk.33.inp_gate.weight | Block 33 Inp_Gate (W) | (~655K) 655360 | 2560 x 256 x 1 x 1 | F16 | 16.0000 | | 468 | blk.33.proj.weight | Block 33 Proj (W) | (~655K) 655360 | 256 x 2560 x 1 x 1 | F16 | 16.0000 | | 469 | blk.33.post_attention_norm.weight | Block 33 Post_Attention_Norm (W) | ( ~3K) 2560 | 2560 x 1 x 1 x 1 | F32 | 32.0000 | | 470 | blk.33.post_ffw_norm.weight | Block 33 Post_Ffw_Norm (W) | ( ~3K) 2560 | 2560 x 1 x 1 x 1 | F32 | 32.0000 | | 471 | blk.33.post_norm.weight | Block 33 Post_Norm (W) | ( ~3K) 2560 | 2560 x 1 x 1 x 1 | F32 | 32.0000 | | 472 | blk.33.ffn_norm.weight | Block 33 Feed-Forward Network Normalization (W) | ( ~3K) 2560 | 2560 x 1 x 1 x 1 | F32 | 32.0000 | | 473 | blk.33.attn_k_norm.weight | Block 33 Attn_K_Norm (W) | ( 256) 256 | 256 x 1 x 1 x 1 | F32 | 32.0000 | | 474 | blk.33.attn_k.weight | Block 33 Attention Key (W) | ( ~1M) 1310720 | 2560 x 512 x 1 x 1 | F16 | 16.0000 | | 475 | blk.33.attn_output.weight | Block 33 Attention Output (W) | ( ~5M) 5242880 | 2048 x 2560 x 1 x 1 | F16 | 16.0000 | | 476 | blk.33.attn_q_norm.weight | Block 33 Attn_Q_Norm (W) | ( 256) 256 | 256 x 1 x 1 x 1 | F32 | 32.0000 | | 477 | blk.33.attn_q.weight | Block 33 Attention Query (W) | ( ~5M) 5242880 | 2560 x 2048 x 1 x 1 | F16 | 16.0000 | | 478 | blk.33.attn_v.weight | Block 33 Attention Value (W) | ( ~1M) 1310720 | 2560 x 512 x 1 x 1 | F16 | 16.0000 | - Total elements in blk.33: (~93M) 93074433 - Percentage of total elements: 1.24% - Bits per Weight (BPW) for blk.33: 16.0023 bits ### Block 34 Tensor Group : ~93M Elements | T_ID | Tensor Layer Name | Human Friendly Tensor Layer Name | Elements | Shape | Type | BPW | | ---: | :-------------------------------- | :---------------------------------------------- | :--------------- | :-------------------- | :--- | ------: | | 479 | blk.34.attn_norm.weight | Block 34 Attention Normalization (W) | ( ~3K) 2560 | 2560 x 1 x 1 x 1 | F32 | 32.0000 | | 480 | blk.34.layer_output_scale.weight | Block 34 Layer_Output_Scale (W) | ( 1) 1 | 1 x 1 x 1 x 1 | F32 | 32.0000 | | 481 | blk.34.ffn_down.weight | Block 34 Feed-Forward Network "Down" (W) | ( ~26M) 26214400 | 10240 x 2560 x 1 x 1 | F16 | 16.0000 | | 482 | blk.34.ffn_gate.weight | Block 34 Feed-Forward Network "Gate" (W) | ( ~26M) 26214400 | 2560 x 10240 x 1 x 1 | F16 | 16.0000 | | 483 | blk.34.ffn_up.weight | Block 34 Feed-Forward Network "Up" (W) | ( ~26M) 26214400 | 2560 x 10240 x 1 x 1 | F16 | 16.0000 | | 484 | blk.34.inp_gate.weight | Block 34 Inp_Gate (W) | (~655K) 655360 | 2560 x 256 x 1 x 1 | F16 | 16.0000 | | 485 | blk.34.proj.weight | Block 34 Proj (W) | (~655K) 655360 | 256 x 2560 x 1 x 1 | F16 | 16.0000 | | 486 | blk.34.post_attention_norm.weight | Block 34 Post_Attention_Norm (W) | ( ~3K) 2560 | 2560 x 1 x 1 x 1 | F32 | 32.0000 | | 487 | blk.34.post_ffw_norm.weight | Block 34 Post_Ffw_Norm (W) | ( ~3K) 2560 | 2560 x 1 x 1 x 1 | F32 | 32.0000 | | 488 | blk.34.post_norm.weight | Block 34 Post_Norm (W) | ( ~3K) 2560 | 2560 x 1 x 1 x 1 | F32 | 32.0000 | | 489 | blk.34.ffn_norm.weight | Block 34 Feed-Forward Network Normalization (W) | ( ~3K) 2560 | 2560 x 1 x 1 x 1 | F32 | 32.0000 | | 490 | blk.34.attn_k_norm.weight | Block 34 Attn_K_Norm (W) | ( 256) 256 | 256 x 1 x 1 x 1 | F32 | 32.0000 | | 491 | blk.34.attn_k.weight | Block 34 Attention Key (W) | ( ~1M) 1310720 | 2560 x 512 x 1 x 1 | F16 | 16.0000 | | 492 | blk.34.attn_output.weight | Block 34 Attention Output (W) | ( ~5M) 5242880 | 2048 x 2560 x 1 x 1 | F16 | 16.0000 | | 493 | blk.34.attn_q_norm.weight | Block 34 Attn_Q_Norm (W) | ( 256) 256 | 256 x 1 x 1 x 1 | F32 | 32.0000 | | 494 | blk.34.attn_q.weight | Block 34 Attention Query (W) | ( ~5M) 5242880 | 2560 x 2048 x 1 x 1 | F16 | 16.0000 | | 495 | blk.34.attn_v.weight | Block 34 Attention Value (W) | ( ~1M) 1310720 | 2560 x 512 x 1 x 1 | F16 | 16.0000 | - Total elements in blk.34: (~93M) 93074433 - Percentage of total elements: 1.24% - Bits per Weight (BPW) for blk.34: 16.0023 bits ### Block 35 Tensor Group : ~106M Elements | T_ID | Tensor Layer Name | Human Friendly Tensor Layer Name | Elements | Shape | Type | BPW | | ---: | :-------------------------------- | :---------------------------------------------- | :--------------- | :-------------------- | :--- | ------: | | 496 | blk.35.attn_norm.weight | Block 35 Attention Normalization (W) | ( ~3K) 2560 | 2560 x 1 x 1 x 1 | F32 | 32.0000 | | 497 | blk.35.layer_output_scale.weight | Block 35 Layer_Output_Scale (W) | ( 1) 1 | 1 x 1 x 1 x 1 | F32 | 32.0000 | | 498 | blk.35.ffn_down.weight | Block 35 Feed-Forward Network "Down" (W) | ( ~26M) 26214400 | 10240 x 2560 x 1 x 1 | F16 | 16.0000 | | 499 | blk.35.ffn_gate.weight | Block 35 Feed-Forward Network "Gate" (W) | ( ~26M) 26214400 | 2560 x 10240 x 1 x 1 | F16 | 16.0000 | | 500 | blk.35.ffn_up.weight | Block 35 Feed-Forward Network "Up" (W) | ( ~26M) 26214400 | 2560 x 10240 x 1 x 1 | F16 | 16.0000 | | 501 | blk.35.inp_gate.weight | Block 35 Inp_Gate (W) | (~655K) 655360 | 2560 x 256 x 1 x 1 | F16 | 16.0000 | | 502 | blk.35.proj.weight | Block 35 Proj (W) | (~655K) 655360 | 256 x 2560 x 1 x 1 | F16 | 16.0000 | | 503 | blk.35.post_attention_norm.weight | Block 35 Post_Attention_Norm (W) | ( ~3K) 2560 | 2560 x 1 x 1 x 1 | F32 | 32.0000 | | 504 | blk.35.post_ffw_norm.weight | Block 35 Post_Ffw_Norm (W) | ( ~3K) 2560 | 2560 x 1 x 1 x 1 | F32 | 32.0000 | | 505 | blk.35.post_norm.weight | Block 35 Post_Norm (W) | ( ~3K) 2560 | 2560 x 1 x 1 x 1 | F32 | 32.0000 | | 506 | blk.35.ffn_norm.weight | Block 35 Feed-Forward Network Normalization (W) | ( ~3K) 2560 | 2560 x 1 x 1 x 1 | F32 | 32.0000 | | 507 | blk.35.attn_k_norm.weight | Block 35 Attn_K_Norm (W) | ( 512) 512 | 512 x 1 x 1 x 1 | F32 | 32.0000 | | 508 | blk.35.attn_k.weight | Block 35 Attention Key (W) | ( ~3M) 2621440 | 2560 x 1024 x 1 x 1 | F16 | 16.0000 | | 509 | blk.35.attn_output.weight | Block 35 Attention Output (W) | ( ~10M) 10485760 | 4096 x 2560 x 1 x 1 | F16 | 16.0000 | | 510 | blk.35.attn_q_norm.weight | Block 35 Attn_Q_Norm (W) | ( 512) 512 | 512 x 1 x 1 x 1 | F32 | 32.0000 | | 511 | blk.35.attn_q.weight | Block 35 Attention Query (W) | ( ~10M) 10485760 | 2560 x 4096 x 1 x 1 | F16 | 16.0000 | | 512 | blk.35.attn_v.weight | Block 35 Attention Value (W) | ( ~3M) 2621440 | 2560 x 1024 x 1 x 1 | F16 | 16.0000 | - Total elements in blk.35: (~106M) 106182145 - Percentage of total elements: 1.41% - Bits per Weight (BPW) for blk.35: 16.0021 bits ### Block 36 Tensor Group : ~93M Elements | T_ID | Tensor Layer Name | Human Friendly Tensor Layer Name | Elements | Shape | Type | BPW | | ---: | :-------------------------------- | :---------------------------------------------- | :--------------- | :-------------------- | :--- | ------: | | 513 | blk.36.attn_norm.weight | Block 36 Attention Normalization (W) | ( ~3K) 2560 | 2560 x 1 x 1 x 1 | F32 | 32.0000 | | 514 | blk.36.layer_output_scale.weight | Block 36 Layer_Output_Scale (W) | ( 1) 1 | 1 x 1 x 1 x 1 | F32 | 32.0000 | | 515 | blk.36.ffn_down.weight | Block 36 Feed-Forward Network "Down" (W) | ( ~26M) 26214400 | 10240 x 2560 x 1 x 1 | F16 | 16.0000 | | 516 | blk.36.ffn_gate.weight | Block 36 Feed-Forward Network "Gate" (W) | ( ~26M) 26214400 | 2560 x 10240 x 1 x 1 | F16 | 16.0000 | | 517 | blk.36.ffn_up.weight | Block 36 Feed-Forward Network "Up" (W) | ( ~26M) 26214400 | 2560 x 10240 x 1 x 1 | F16 | 16.0000 | | 518 | blk.36.inp_gate.weight | Block 36 Inp_Gate (W) | (~655K) 655360 | 2560 x 256 x 1 x 1 | F16 | 16.0000 | | 519 | blk.36.proj.weight | Block 36 Proj (W) | (~655K) 655360 | 256 x 2560 x 1 x 1 | F16 | 16.0000 | | 520 | blk.36.post_attention_norm.weight | Block 36 Post_Attention_Norm (W) | ( ~3K) 2560 | 2560 x 1 x 1 x 1 | F32 | 32.0000 | | 521 | blk.36.post_ffw_norm.weight | Block 36 Post_Ffw_Norm (W) | ( ~3K) 2560 | 2560 x 1 x 1 x 1 | F32 | 32.0000 | | 522 | blk.36.post_norm.weight | Block 36 Post_Norm (W) | ( ~3K) 2560 | 2560 x 1 x 1 x 1 | F32 | 32.0000 | | 523 | blk.36.ffn_norm.weight | Block 36 Feed-Forward Network Normalization (W) | ( ~3K) 2560 | 2560 x 1 x 1 x 1 | F32 | 32.0000 | | 524 | blk.36.attn_k_norm.weight | Block 36 Attn_K_Norm (W) | ( 256) 256 | 256 x 1 x 1 x 1 | F32 | 32.0000 | | 525 | blk.36.attn_k.weight | Block 36 Attention Key (W) | ( ~1M) 1310720 | 2560 x 512 x 1 x 1 | F16 | 16.0000 | | 526 | blk.36.attn_output.weight | Block 36 Attention Output (W) | ( ~5M) 5242880 | 2048 x 2560 x 1 x 1 | F16 | 16.0000 | | 527 | blk.36.attn_q_norm.weight | Block 36 Attn_Q_Norm (W) | ( 256) 256 | 256 x 1 x 1 x 1 | F32 | 32.0000 | | 528 | blk.36.attn_q.weight | Block 36 Attention Query (W) | ( ~5M) 5242880 | 2560 x 2048 x 1 x 1 | F16 | 16.0000 | | 529 | blk.36.attn_v.weight | Block 36 Attention Value (W) | ( ~1M) 1310720 | 2560 x 512 x 1 x 1 | F16 | 16.0000 | - Total elements in blk.36: (~93M) 93074433 - Percentage of total elements: 1.24% - Bits per Weight (BPW) for blk.36: 16.0023 bits ### Block 37 Tensor Group : ~93M Elements | T_ID | Tensor Layer Name | Human Friendly Tensor Layer Name | Elements | Shape | Type | BPW | | ---: | :-------------------------------- | :---------------------------------------------- | :--------------- | :-------------------- | :--- | ------: | | 530 | blk.37.attn_norm.weight | Block 37 Attention Normalization (W) | ( ~3K) 2560 | 2560 x 1 x 1 x 1 | F32 | 32.0000 | | 531 | blk.37.layer_output_scale.weight | Block 37 Layer_Output_Scale (W) | ( 1) 1 | 1 x 1 x 1 x 1 | F32 | 32.0000 | | 532 | blk.37.ffn_down.weight | Block 37 Feed-Forward Network "Down" (W) | ( ~26M) 26214400 | 10240 x 2560 x 1 x 1 | F16 | 16.0000 | | 533 | blk.37.ffn_gate.weight | Block 37 Feed-Forward Network "Gate" (W) | ( ~26M) 26214400 | 2560 x 10240 x 1 x 1 | F16 | 16.0000 | | 534 | blk.37.ffn_up.weight | Block 37 Feed-Forward Network "Up" (W) | ( ~26M) 26214400 | 2560 x 10240 x 1 x 1 | F16 | 16.0000 | | 535 | blk.37.inp_gate.weight | Block 37 Inp_Gate (W) | (~655K) 655360 | 2560 x 256 x 1 x 1 | F16 | 16.0000 | | 536 | blk.37.proj.weight | Block 37 Proj (W) | (~655K) 655360 | 256 x 2560 x 1 x 1 | F16 | 16.0000 | | 537 | blk.37.post_attention_norm.weight | Block 37 Post_Attention_Norm (W) | ( ~3K) 2560 | 2560 x 1 x 1 x 1 | F32 | 32.0000 | | 538 | blk.37.post_ffw_norm.weight | Block 37 Post_Ffw_Norm (W) | ( ~3K) 2560 | 2560 x 1 x 1 x 1 | F32 | 32.0000 | | 539 | blk.37.post_norm.weight | Block 37 Post_Norm (W) | ( ~3K) 2560 | 2560 x 1 x 1 x 1 | F32 | 32.0000 | | 540 | blk.37.ffn_norm.weight | Block 37 Feed-Forward Network Normalization (W) | ( ~3K) 2560 | 2560 x 1 x 1 x 1 | F32 | 32.0000 | | 541 | blk.37.attn_k_norm.weight | Block 37 Attn_K_Norm (W) | ( 256) 256 | 256 x 1 x 1 x 1 | F32 | 32.0000 | | 542 | blk.37.attn_k.weight | Block 37 Attention Key (W) | ( ~1M) 1310720 | 2560 x 512 x 1 x 1 | F16 | 16.0000 | | 543 | blk.37.attn_output.weight | Block 37 Attention Output (W) | ( ~5M) 5242880 | 2048 x 2560 x 1 x 1 | F16 | 16.0000 | | 544 | blk.37.attn_q_norm.weight | Block 37 Attn_Q_Norm (W) | ( 256) 256 | 256 x 1 x 1 x 1 | F32 | 32.0000 | | 545 | blk.37.attn_q.weight | Block 37 Attention Query (W) | ( ~5M) 5242880 | 2560 x 2048 x 1 x 1 | F16 | 16.0000 | | 546 | blk.37.attn_v.weight | Block 37 Attention Value (W) | ( ~1M) 1310720 | 2560 x 512 x 1 x 1 | F16 | 16.0000 | - Total elements in blk.37: (~93M) 93074433 - Percentage of total elements: 1.24% - Bits per Weight (BPW) for blk.37: 16.0023 bits ### Block 38 Tensor Group : ~93M Elements | T_ID | Tensor Layer Name | Human Friendly Tensor Layer Name | Elements | Shape | Type | BPW | | ---: | :-------------------------------- | :---------------------------------------------- | :--------------- | :-------------------- | :--- | ------: | | 547 | blk.38.attn_norm.weight | Block 38 Attention Normalization (W) | ( ~3K) 2560 | 2560 x 1 x 1 x 1 | F32 | 32.0000 | | 548 | blk.38.layer_output_scale.weight | Block 38 Layer_Output_Scale (W) | ( 1) 1 | 1 x 1 x 1 x 1 | F32 | 32.0000 | | 549 | blk.38.ffn_down.weight | Block 38 Feed-Forward Network "Down" (W) | ( ~26M) 26214400 | 10240 x 2560 x 1 x 1 | F16 | 16.0000 | | 550 | blk.38.ffn_gate.weight | Block 38 Feed-Forward Network "Gate" (W) | ( ~26M) 26214400 | 2560 x 10240 x 1 x 1 | F16 | 16.0000 | | 551 | blk.38.ffn_up.weight | Block 38 Feed-Forward Network "Up" (W) | ( ~26M) 26214400 | 2560 x 10240 x 1 x 1 | F16 | 16.0000 | | 552 | blk.38.inp_gate.weight | Block 38 Inp_Gate (W) | (~655K) 655360 | 2560 x 256 x 1 x 1 | F16 | 16.0000 | | 553 | blk.38.proj.weight | Block 38 Proj (W) | (~655K) 655360 | 256 x 2560 x 1 x 1 | F16 | 16.0000 | | 554 | blk.38.post_attention_norm.weight | Block 38 Post_Attention_Norm (W) | ( ~3K) 2560 | 2560 x 1 x 1 x 1 | F32 | 32.0000 | | 555 | blk.38.post_ffw_norm.weight | Block 38 Post_Ffw_Norm (W) | ( ~3K) 2560 | 2560 x 1 x 1 x 1 | F32 | 32.0000 | | 556 | blk.38.post_norm.weight | Block 38 Post_Norm (W) | ( ~3K) 2560 | 2560 x 1 x 1 x 1 | F32 | 32.0000 | | 557 | blk.38.ffn_norm.weight | Block 38 Feed-Forward Network Normalization (W) | ( ~3K) 2560 | 2560 x 1 x 1 x 1 | F32 | 32.0000 | | 558 | blk.38.attn_k_norm.weight | Block 38 Attn_K_Norm (W) | ( 256) 256 | 256 x 1 x 1 x 1 | F32 | 32.0000 | | 559 | blk.38.attn_k.weight | Block 38 Attention Key (W) | ( ~1M) 1310720 | 2560 x 512 x 1 x 1 | F16 | 16.0000 | | 560 | blk.38.attn_output.weight | Block 38 Attention Output (W) | ( ~5M) 5242880 | 2048 x 2560 x 1 x 1 | F16 | 16.0000 | | 561 | blk.38.attn_q_norm.weight | Block 38 Attn_Q_Norm (W) | ( 256) 256 | 256 x 1 x 1 x 1 | F32 | 32.0000 | | 562 | blk.38.attn_q.weight | Block 38 Attention Query (W) | ( ~5M) 5242880 | 2560 x 2048 x 1 x 1 | F16 | 16.0000 | | 563 | blk.38.attn_v.weight | Block 38 Attention Value (W) | ( ~1M) 1310720 | 2560 x 512 x 1 x 1 | F16 | 16.0000 | - Total elements in blk.38: (~93M) 93074433 - Percentage of total elements: 1.24% - Bits per Weight (BPW) for blk.38: 16.0023 bits ### Block 39 Tensor Group : ~93M Elements | T_ID | Tensor Layer Name | Human Friendly Tensor Layer Name | Elements | Shape | Type | BPW | | ---: | :-------------------------------- | :---------------------------------------------- | :--------------- | :-------------------- | :--- | ------: | | 564 | blk.39.attn_norm.weight | Block 39 Attention Normalization (W) | ( ~3K) 2560 | 2560 x 1 x 1 x 1 | F32 | 32.0000 | | 565 | blk.39.layer_output_scale.weight | Block 39 Layer_Output_Scale (W) | ( 1) 1 | 1 x 1 x 1 x 1 | F32 | 32.0000 | | 566 | blk.39.ffn_down.weight | Block 39 Feed-Forward Network "Down" (W) | ( ~26M) 26214400 | 10240 x 2560 x 1 x 1 | F16 | 16.0000 | | 567 | blk.39.ffn_gate.weight | Block 39 Feed-Forward Network "Gate" (W) | ( ~26M) 26214400 | 2560 x 10240 x 1 x 1 | F16 | 16.0000 | | 568 | blk.39.ffn_up.weight | Block 39 Feed-Forward Network "Up" (W) | ( ~26M) 26214400 | 2560 x 10240 x 1 x 1 | F16 | 16.0000 | | 569 | blk.39.inp_gate.weight | Block 39 Inp_Gate (W) | (~655K) 655360 | 2560 x 256 x 1 x 1 | F16 | 16.0000 | | 570 | blk.39.proj.weight | Block 39 Proj (W) | (~655K) 655360 | 256 x 2560 x 1 x 1 | F16 | 16.0000 | | 571 | blk.39.post_attention_norm.weight | Block 39 Post_Attention_Norm (W) | ( ~3K) 2560 | 2560 x 1 x 1 x 1 | F32 | 32.0000 | | 572 | blk.39.post_ffw_norm.weight | Block 39 Post_Ffw_Norm (W) | ( ~3K) 2560 | 2560 x 1 x 1 x 1 | F32 | 32.0000 | | 573 | blk.39.post_norm.weight | Block 39 Post_Norm (W) | ( ~3K) 2560 | 2560 x 1 x 1 x 1 | F32 | 32.0000 | | 574 | blk.39.ffn_norm.weight | Block 39 Feed-Forward Network Normalization (W) | ( ~3K) 2560 | 2560 x 1 x 1 x 1 | F32 | 32.0000 | | 575 | blk.39.attn_k_norm.weight | Block 39 Attn_K_Norm (W) | ( 256) 256 | 256 x 1 x 1 x 1 | F32 | 32.0000 | | 576 | blk.39.attn_k.weight | Block 39 Attention Key (W) | ( ~1M) 1310720 | 2560 x 512 x 1 x 1 | F16 | 16.0000 | | 577 | blk.39.attn_output.weight | Block 39 Attention Output (W) | ( ~5M) 5242880 | 2048 x 2560 x 1 x 1 | F16 | 16.0000 | | 578 | blk.39.attn_q_norm.weight | Block 39 Attn_Q_Norm (W) | ( 256) 256 | 256 x 1 x 1 x 1 | F32 | 32.0000 | | 579 | blk.39.attn_q.weight | Block 39 Attention Query (W) | ( ~5M) 5242880 | 2560 x 2048 x 1 x 1 | F16 | 16.0000 | | 580 | blk.39.attn_v.weight | Block 39 Attention Value (W) | ( ~1M) 1310720 | 2560 x 512 x 1 x 1 | F16 | 16.0000 | - Total elements in blk.39: (~93M) 93074433 - Percentage of total elements: 1.24% - Bits per Weight (BPW) for blk.39: 16.0023 bits ### Block 4 Tensor Group : ~93M Elements | T_ID | Tensor Layer Name | Human Friendly Tensor Layer Name | Elements | Shape | Type | BPW | | ---: | :------------------------------- | :--------------------------------------------- | :--------------- | :-------------------- | :--- | ------: | | 581 | blk.4.attn_norm.weight | Block 4 Attention Normalization (W) | ( ~3K) 2560 | 2560 x 1 x 1 x 1 | F32 | 32.0000 | | 582 | blk.4.layer_output_scale.weight | Block 4 Layer_Output_Scale (W) | ( 1) 1 | 1 x 1 x 1 x 1 | F32 | 32.0000 | | 583 | blk.4.ffn_down.weight | Block 4 Feed-Forward Network "Down" (W) | ( ~26M) 26214400 | 10240 x 2560 x 1 x 1 | F16 | 16.0000 | | 584 | blk.4.ffn_gate.weight | Block 4 Feed-Forward Network "Gate" (W) | ( ~26M) 26214400 | 2560 x 10240 x 1 x 1 | F16 | 16.0000 | | 585 | blk.4.ffn_up.weight | Block 4 Feed-Forward Network "Up" (W) | ( ~26M) 26214400 | 2560 x 10240 x 1 x 1 | F16 | 16.0000 | | 586 | blk.4.inp_gate.weight | Block 4 Inp_Gate (W) | (~655K) 655360 | 2560 x 256 x 1 x 1 | F16 | 16.0000 | | 587 | blk.4.proj.weight | Block 4 Proj (W) | (~655K) 655360 | 256 x 2560 x 1 x 1 | F16 | 16.0000 | | 588 | blk.4.post_attention_norm.weight | Block 4 Post_Attention_Norm (W) | ( ~3K) 2560 | 2560 x 1 x 1 x 1 | F32 | 32.0000 | | 589 | blk.4.post_ffw_norm.weight | Block 4 Post_Ffw_Norm (W) | ( ~3K) 2560 | 2560 x 1 x 1 x 1 | F32 | 32.0000 | | 590 | blk.4.post_norm.weight | Block 4 Post_Norm (W) | ( ~3K) 2560 | 2560 x 1 x 1 x 1 | F32 | 32.0000 | | 591 | blk.4.ffn_norm.weight | Block 4 Feed-Forward Network Normalization (W) | ( ~3K) 2560 | 2560 x 1 x 1 x 1 | F32 | 32.0000 | | 592 | blk.4.attn_k_norm.weight | Block 4 Attn_K_Norm (W) | ( 256) 256 | 256 x 1 x 1 x 1 | F32 | 32.0000 | | 593 | blk.4.attn_k.weight | Block 4 Attention Key (W) | ( ~1M) 1310720 | 2560 x 512 x 1 x 1 | F16 | 16.0000 | | 594 | blk.4.attn_output.weight | Block 4 Attention Output (W) | ( ~5M) 5242880 | 2048 x 2560 x 1 x 1 | F16 | 16.0000 | | 595 | blk.4.attn_q_norm.weight | Block 4 Attn_Q_Norm (W) | ( 256) 256 | 256 x 1 x 1 x 1 | F32 | 32.0000 | | 596 | blk.4.attn_q.weight | Block 4 Attention Query (W) | ( ~5M) 5242880 | 2560 x 2048 x 1 x 1 | F16 | 16.0000 | | 597 | blk.4.attn_v.weight | Block 4 Attention Value (W) | ( ~1M) 1310720 | 2560 x 512 x 1 x 1 | F16 | 16.0000 | - Total elements in blk.4: (~93M) 93074433 - Percentage of total elements: 1.24% - Bits per Weight (BPW) for blk.4: 16.0023 bits ### Block 40 Tensor Group : ~93M Elements | T_ID | Tensor Layer Name | Human Friendly Tensor Layer Name | Elements | Shape | Type | BPW | | ---: | :-------------------------------- | :---------------------------------------------- | :--------------- | :-------------------- | :--- | ------: | | 598 | blk.40.attn_norm.weight | Block 40 Attention Normalization (W) | ( ~3K) 2560 | 2560 x 1 x 1 x 1 | F32 | 32.0000 | | 599 | blk.40.layer_output_scale.weight | Block 40 Layer_Output_Scale (W) | ( 1) 1 | 1 x 1 x 1 x 1 | F32 | 32.0000 | | 600 | blk.40.ffn_down.weight | Block 40 Feed-Forward Network "Down" (W) | ( ~26M) 26214400 | 10240 x 2560 x 1 x 1 | F16 | 16.0000 | | 601 | blk.40.ffn_gate.weight | Block 40 Feed-Forward Network "Gate" (W) | ( ~26M) 26214400 | 2560 x 10240 x 1 x 1 | F16 | 16.0000 | | 602 | blk.40.ffn_up.weight | Block 40 Feed-Forward Network "Up" (W) | ( ~26M) 26214400 | 2560 x 10240 x 1 x 1 | F16 | 16.0000 | | 603 | blk.40.inp_gate.weight | Block 40 Inp_Gate (W) | (~655K) 655360 | 2560 x 256 x 1 x 1 | F16 | 16.0000 | | 604 | blk.40.proj.weight | Block 40 Proj (W) | (~655K) 655360 | 256 x 2560 x 1 x 1 | F16 | 16.0000 | | 605 | blk.40.post_attention_norm.weight | Block 40 Post_Attention_Norm (W) | ( ~3K) 2560 | 2560 x 1 x 1 x 1 | F32 | 32.0000 | | 606 | blk.40.post_ffw_norm.weight | Block 40 Post_Ffw_Norm (W) | ( ~3K) 2560 | 2560 x 1 x 1 x 1 | F32 | 32.0000 | | 607 | blk.40.post_norm.weight | Block 40 Post_Norm (W) | ( ~3K) 2560 | 2560 x 1 x 1 x 1 | F32 | 32.0000 | | 608 | blk.40.ffn_norm.weight | Block 40 Feed-Forward Network Normalization (W) | ( ~3K) 2560 | 2560 x 1 x 1 x 1 | F32 | 32.0000 | | 609 | blk.40.attn_k_norm.weight | Block 40 Attn_K_Norm (W) | ( 256) 256 | 256 x 1 x 1 x 1 | F32 | 32.0000 | | 610 | blk.40.attn_k.weight | Block 40 Attention Key (W) | ( ~1M) 1310720 | 2560 x 512 x 1 x 1 | F16 | 16.0000 | | 611 | blk.40.attn_output.weight | Block 40 Attention Output (W) | ( ~5M) 5242880 | 2048 x 2560 x 1 x 1 | F16 | 16.0000 | | 612 | blk.40.attn_q_norm.weight | Block 40 Attn_Q_Norm (W) | ( 256) 256 | 256 x 1 x 1 x 1 | F32 | 32.0000 | | 613 | blk.40.attn_q.weight | Block 40 Attention Query (W) | ( ~5M) 5242880 | 2560 x 2048 x 1 x 1 | F16 | 16.0000 | | 614 | blk.40.attn_v.weight | Block 40 Attention Value (W) | ( ~1M) 1310720 | 2560 x 512 x 1 x 1 | F16 | 16.0000 | - Total elements in blk.40: (~93M) 93074433 - Percentage of total elements: 1.24% - Bits per Weight (BPW) for blk.40: 16.0023 bits ### Block 41 Tensor Group : ~106M Elements | T_ID | Tensor Layer Name | Human Friendly Tensor Layer Name | Elements | Shape | Type | BPW | | ---: | :-------------------------------- | :---------------------------------------------- | :--------------- | :-------------------- | :--- | ------: | | 615 | blk.41.attn_norm.weight | Block 41 Attention Normalization (W) | ( ~3K) 2560 | 2560 x 1 x 1 x 1 | F32 | 32.0000 | | 616 | blk.41.layer_output_scale.weight | Block 41 Layer_Output_Scale (W) | ( 1) 1 | 1 x 1 x 1 x 1 | F32 | 32.0000 | | 617 | blk.41.ffn_down.weight | Block 41 Feed-Forward Network "Down" (W) | ( ~26M) 26214400 | 10240 x 2560 x 1 x 1 | F16 | 16.0000 | | 618 | blk.41.ffn_gate.weight | Block 41 Feed-Forward Network "Gate" (W) | ( ~26M) 26214400 | 2560 x 10240 x 1 x 1 | F16 | 16.0000 | | 619 | blk.41.ffn_up.weight | Block 41 Feed-Forward Network "Up" (W) | ( ~26M) 26214400 | 2560 x 10240 x 1 x 1 | F16 | 16.0000 | | 620 | blk.41.inp_gate.weight | Block 41 Inp_Gate (W) | (~655K) 655360 | 2560 x 256 x 1 x 1 | F16 | 16.0000 | | 621 | blk.41.proj.weight | Block 41 Proj (W) | (~655K) 655360 | 256 x 2560 x 1 x 1 | F16 | 16.0000 | | 622 | blk.41.post_attention_norm.weight | Block 41 Post_Attention_Norm (W) | ( ~3K) 2560 | 2560 x 1 x 1 x 1 | F32 | 32.0000 | | 623 | blk.41.post_ffw_norm.weight | Block 41 Post_Ffw_Norm (W) | ( ~3K) 2560 | 2560 x 1 x 1 x 1 | F32 | 32.0000 | | 624 | blk.41.post_norm.weight | Block 41 Post_Norm (W) | ( ~3K) 2560 | 2560 x 1 x 1 x 1 | F32 | 32.0000 | | 625 | blk.41.ffn_norm.weight | Block 41 Feed-Forward Network Normalization (W) | ( ~3K) 2560 | 2560 x 1 x 1 x 1 | F32 | 32.0000 | | 626 | blk.41.attn_k_norm.weight | Block 41 Attn_K_Norm (W) | ( 512) 512 | 512 x 1 x 1 x 1 | F32 | 32.0000 | | 627 | blk.41.attn_k.weight | Block 41 Attention Key (W) | ( ~3M) 2621440 | 2560 x 1024 x 1 x 1 | F16 | 16.0000 | | 628 | blk.41.attn_output.weight | Block 41 Attention Output (W) | ( ~10M) 10485760 | 4096 x 2560 x 1 x 1 | F16 | 16.0000 | | 629 | blk.41.attn_q_norm.weight | Block 41 Attn_Q_Norm (W) | ( 512) 512 | 512 x 1 x 1 x 1 | F32 | 32.0000 | | 630 | blk.41.attn_q.weight | Block 41 Attention Query (W) | ( ~10M) 10485760 | 2560 x 4096 x 1 x 1 | F16 | 16.0000 | | 631 | blk.41.attn_v.weight | Block 41 Attention Value (W) | ( ~3M) 2621440 | 2560 x 1024 x 1 x 1 | F16 | 16.0000 | - Total elements in blk.41: (~106M) 106182145 - Percentage of total elements: 1.41% - Bits per Weight (BPW) for blk.41: 16.0021 bits ### Block 5 Tensor Group : ~106M Elements | T_ID | Tensor Layer Name | Human Friendly Tensor Layer Name | Elements | Shape | Type | BPW | | ---: | :------------------------------- | :--------------------------------------------- | :--------------- | :-------------------- | :--- | ------: | | 632 | blk.5.attn_norm.weight | Block 5 Attention Normalization (W) | ( ~3K) 2560 | 2560 x 1 x 1 x 1 | F32 | 32.0000 | | 633 | blk.5.layer_output_scale.weight | Block 5 Layer_Output_Scale (W) | ( 1) 1 | 1 x 1 x 1 x 1 | F32 | 32.0000 | | 634 | blk.5.ffn_down.weight | Block 5 Feed-Forward Network "Down" (W) | ( ~26M) 26214400 | 10240 x 2560 x 1 x 1 | F16 | 16.0000 | | 635 | blk.5.ffn_gate.weight | Block 5 Feed-Forward Network "Gate" (W) | ( ~26M) 26214400 | 2560 x 10240 x 1 x 1 | F16 | 16.0000 | | 636 | blk.5.ffn_up.weight | Block 5 Feed-Forward Network "Up" (W) | ( ~26M) 26214400 | 2560 x 10240 x 1 x 1 | F16 | 16.0000 | | 637 | blk.5.inp_gate.weight | Block 5 Inp_Gate (W) | (~655K) 655360 | 2560 x 256 x 1 x 1 | F16 | 16.0000 | | 638 | blk.5.proj.weight | Block 5 Proj (W) | (~655K) 655360 | 256 x 2560 x 1 x 1 | F16 | 16.0000 | | 639 | blk.5.post_attention_norm.weight | Block 5 Post_Attention_Norm (W) | ( ~3K) 2560 | 2560 x 1 x 1 x 1 | F32 | 32.0000 | | 640 | blk.5.post_ffw_norm.weight | Block 5 Post_Ffw_Norm (W) | ( ~3K) 2560 | 2560 x 1 x 1 x 1 | F32 | 32.0000 | | 641 | blk.5.post_norm.weight | Block 5 Post_Norm (W) | ( ~3K) 2560 | 2560 x 1 x 1 x 1 | F32 | 32.0000 | | 642 | blk.5.ffn_norm.weight | Block 5 Feed-Forward Network Normalization (W) | ( ~3K) 2560 | 2560 x 1 x 1 x 1 | F32 | 32.0000 | | 643 | blk.5.attn_k_norm.weight | Block 5 Attn_K_Norm (W) | ( 512) 512 | 512 x 1 x 1 x 1 | F32 | 32.0000 | | 644 | blk.5.attn_k.weight | Block 5 Attention Key (W) | ( ~3M) 2621440 | 2560 x 1024 x 1 x 1 | F16 | 16.0000 | | 645 | blk.5.attn_output.weight | Block 5 Attention Output (W) | ( ~10M) 10485760 | 4096 x 2560 x 1 x 1 | F16 | 16.0000 | | 646 | blk.5.attn_q_norm.weight | Block 5 Attn_Q_Norm (W) | ( 512) 512 | 512 x 1 x 1 x 1 | F32 | 32.0000 | | 647 | blk.5.attn_q.weight | Block 5 Attention Query (W) | ( ~10M) 10485760 | 2560 x 4096 x 1 x 1 | F16 | 16.0000 | | 648 | blk.5.attn_v.weight | Block 5 Attention Value (W) | ( ~3M) 2621440 | 2560 x 1024 x 1 x 1 | F16 | 16.0000 | - Total elements in blk.5: (~106M) 106182145 - Percentage of total elements: 1.41% - Bits per Weight (BPW) for blk.5: 16.0021 bits ### Block 6 Tensor Group : ~93M Elements | T_ID | Tensor Layer Name | Human Friendly Tensor Layer Name | Elements | Shape | Type | BPW | | ---: | :------------------------------- | :--------------------------------------------- | :--------------- | :-------------------- | :--- | ------: | | 649 | blk.6.attn_norm.weight | Block 6 Attention Normalization (W) | ( ~3K) 2560 | 2560 x 1 x 1 x 1 | F32 | 32.0000 | | 650 | blk.6.layer_output_scale.weight | Block 6 Layer_Output_Scale (W) | ( 1) 1 | 1 x 1 x 1 x 1 | F32 | 32.0000 | | 651 | blk.6.ffn_down.weight | Block 6 Feed-Forward Network "Down" (W) | ( ~26M) 26214400 | 10240 x 2560 x 1 x 1 | F16 | 16.0000 | | 652 | blk.6.ffn_gate.weight | Block 6 Feed-Forward Network "Gate" (W) | ( ~26M) 26214400 | 2560 x 10240 x 1 x 1 | F16 | 16.0000 | | 653 | blk.6.ffn_up.weight | Block 6 Feed-Forward Network "Up" (W) | ( ~26M) 26214400 | 2560 x 10240 x 1 x 1 | F16 | 16.0000 | | 654 | blk.6.inp_gate.weight | Block 6 Inp_Gate (W) | (~655K) 655360 | 2560 x 256 x 1 x 1 | F16 | 16.0000 | | 655 | blk.6.proj.weight | Block 6 Proj (W) | (~655K) 655360 | 256 x 2560 x 1 x 1 | F16 | 16.0000 | | 656 | blk.6.post_attention_norm.weight | Block 6 Post_Attention_Norm (W) | ( ~3K) 2560 | 2560 x 1 x 1 x 1 | F32 | 32.0000 | | 657 | blk.6.post_ffw_norm.weight | Block 6 Post_Ffw_Norm (W) | ( ~3K) 2560 | 2560 x 1 x 1 x 1 | F32 | 32.0000 | | 658 | blk.6.post_norm.weight | Block 6 Post_Norm (W) | ( ~3K) 2560 | 2560 x 1 x 1 x 1 | F32 | 32.0000 | | 659 | blk.6.ffn_norm.weight | Block 6 Feed-Forward Network Normalization (W) | ( ~3K) 2560 | 2560 x 1 x 1 x 1 | F32 | 32.0000 | | 660 | blk.6.attn_k_norm.weight | Block 6 Attn_K_Norm (W) | ( 256) 256 | 256 x 1 x 1 x 1 | F32 | 32.0000 | | 661 | blk.6.attn_k.weight | Block 6 Attention Key (W) | ( ~1M) 1310720 | 2560 x 512 x 1 x 1 | F16 | 16.0000 | | 662 | blk.6.attn_output.weight | Block 6 Attention Output (W) | ( ~5M) 5242880 | 2048 x 2560 x 1 x 1 | F16 | 16.0000 | | 663 | blk.6.attn_q_norm.weight | Block 6 Attn_Q_Norm (W) | ( 256) 256 | 256 x 1 x 1 x 1 | F32 | 32.0000 | | 664 | blk.6.attn_q.weight | Block 6 Attention Query (W) | ( ~5M) 5242880 | 2560 x 2048 x 1 x 1 | F16 | 16.0000 | | 665 | blk.6.attn_v.weight | Block 6 Attention Value (W) | ( ~1M) 1310720 | 2560 x 512 x 1 x 1 | F16 | 16.0000 | - Total elements in blk.6: (~93M) 93074433 - Percentage of total elements: 1.24% - Bits per Weight (BPW) for blk.6: 16.0023 bits ### Block 7 Tensor Group : ~93M Elements | T_ID | Tensor Layer Name | Human Friendly Tensor Layer Name | Elements | Shape | Type | BPW | | ---: | :------------------------------- | :--------------------------------------------- | :--------------- | :-------------------- | :--- | ------: | | 666 | blk.7.attn_norm.weight | Block 7 Attention Normalization (W) | ( ~3K) 2560 | 2560 x 1 x 1 x 1 | F32 | 32.0000 | | 667 | blk.7.layer_output_scale.weight | Block 7 Layer_Output_Scale (W) | ( 1) 1 | 1 x 1 x 1 x 1 | F32 | 32.0000 | | 668 | blk.7.ffn_down.weight | Block 7 Feed-Forward Network "Down" (W) | ( ~26M) 26214400 | 10240 x 2560 x 1 x 1 | F16 | 16.0000 | | 669 | blk.7.ffn_gate.weight | Block 7 Feed-Forward Network "Gate" (W) | ( ~26M) 26214400 | 2560 x 10240 x 1 x 1 | F16 | 16.0000 | | 670 | blk.7.ffn_up.weight | Block 7 Feed-Forward Network "Up" (W) | ( ~26M) 26214400 | 2560 x 10240 x 1 x 1 | F16 | 16.0000 | | 671 | blk.7.inp_gate.weight | Block 7 Inp_Gate (W) | (~655K) 655360 | 2560 x 256 x 1 x 1 | F16 | 16.0000 | | 672 | blk.7.proj.weight | Block 7 Proj (W) | (~655K) 655360 | 256 x 2560 x 1 x 1 | F16 | 16.0000 | | 673 | blk.7.post_attention_norm.weight | Block 7 Post_Attention_Norm (W) | ( ~3K) 2560 | 2560 x 1 x 1 x 1 | F32 | 32.0000 | | 674 | blk.7.post_ffw_norm.weight | Block 7 Post_Ffw_Norm (W) | ( ~3K) 2560 | 2560 x 1 x 1 x 1 | F32 | 32.0000 | | 675 | blk.7.post_norm.weight | Block 7 Post_Norm (W) | ( ~3K) 2560 | 2560 x 1 x 1 x 1 | F32 | 32.0000 | | 676 | blk.7.ffn_norm.weight | Block 7 Feed-Forward Network Normalization (W) | ( ~3K) 2560 | 2560 x 1 x 1 x 1 | F32 | 32.0000 | | 677 | blk.7.attn_k_norm.weight | Block 7 Attn_K_Norm (W) | ( 256) 256 | 256 x 1 x 1 x 1 | F32 | 32.0000 | | 678 | blk.7.attn_k.weight | Block 7 Attention Key (W) | ( ~1M) 1310720 | 2560 x 512 x 1 x 1 | F16 | 16.0000 | | 679 | blk.7.attn_output.weight | Block 7 Attention Output (W) | ( ~5M) 5242880 | 2048 x 2560 x 1 x 1 | F16 | 16.0000 | | 680 | blk.7.attn_q_norm.weight | Block 7 Attn_Q_Norm (W) | ( 256) 256 | 256 x 1 x 1 x 1 | F32 | 32.0000 | | 681 | blk.7.attn_q.weight | Block 7 Attention Query (W) | ( ~5M) 5242880 | 2560 x 2048 x 1 x 1 | F16 | 16.0000 | | 682 | blk.7.attn_v.weight | Block 7 Attention Value (W) | ( ~1M) 1310720 | 2560 x 512 x 1 x 1 | F16 | 16.0000 | - Total elements in blk.7: (~93M) 93074433 - Percentage of total elements: 1.24% - Bits per Weight (BPW) for blk.7: 16.0023 bits ### Block 8 Tensor Group : ~93M Elements | T_ID | Tensor Layer Name | Human Friendly Tensor Layer Name | Elements | Shape | Type | BPW | | ---: | :------------------------------- | :--------------------------------------------- | :--------------- | :-------------------- | :--- | ------: | | 683 | blk.8.attn_norm.weight | Block 8 Attention Normalization (W) | ( ~3K) 2560 | 2560 x 1 x 1 x 1 | F32 | 32.0000 | | 684 | blk.8.layer_output_scale.weight | Block 8 Layer_Output_Scale (W) | ( 1) 1 | 1 x 1 x 1 x 1 | F32 | 32.0000 | | 685 | blk.8.ffn_down.weight | Block 8 Feed-Forward Network "Down" (W) | ( ~26M) 26214400 | 10240 x 2560 x 1 x 1 | F16 | 16.0000 | | 686 | blk.8.ffn_gate.weight | Block 8 Feed-Forward Network "Gate" (W) | ( ~26M) 26214400 | 2560 x 10240 x 1 x 1 | F16 | 16.0000 | | 687 | blk.8.ffn_up.weight | Block 8 Feed-Forward Network "Up" (W) | ( ~26M) 26214400 | 2560 x 10240 x 1 x 1 | F16 | 16.0000 | | 688 | blk.8.inp_gate.weight | Block 8 Inp_Gate (W) | (~655K) 655360 | 2560 x 256 x 1 x 1 | F16 | 16.0000 | | 689 | blk.8.proj.weight | Block 8 Proj (W) | (~655K) 655360 | 256 x 2560 x 1 x 1 | F16 | 16.0000 | | 690 | blk.8.post_attention_norm.weight | Block 8 Post_Attention_Norm (W) | ( ~3K) 2560 | 2560 x 1 x 1 x 1 | F32 | 32.0000 | | 691 | blk.8.post_ffw_norm.weight | Block 8 Post_Ffw_Norm (W) | ( ~3K) 2560 | 2560 x 1 x 1 x 1 | F32 | 32.0000 | | 692 | blk.8.post_norm.weight | Block 8 Post_Norm (W) | ( ~3K) 2560 | 2560 x 1 x 1 x 1 | F32 | 32.0000 | | 693 | blk.8.ffn_norm.weight | Block 8 Feed-Forward Network Normalization (W) | ( ~3K) 2560 | 2560 x 1 x 1 x 1 | F32 | 32.0000 | | 694 | blk.8.attn_k_norm.weight | Block 8 Attn_K_Norm (W) | ( 256) 256 | 256 x 1 x 1 x 1 | F32 | 32.0000 | | 695 | blk.8.attn_k.weight | Block 8 Attention Key (W) | ( ~1M) 1310720 | 2560 x 512 x 1 x 1 | F16 | 16.0000 | | 696 | blk.8.attn_output.weight | Block 8 Attention Output (W) | ( ~5M) 5242880 | 2048 x 2560 x 1 x 1 | F16 | 16.0000 | | 697 | blk.8.attn_q_norm.weight | Block 8 Attn_Q_Norm (W) | ( 256) 256 | 256 x 1 x 1 x 1 | F32 | 32.0000 | | 698 | blk.8.attn_q.weight | Block 8 Attention Query (W) | ( ~5M) 5242880 | 2560 x 2048 x 1 x 1 | F16 | 16.0000 | | 699 | blk.8.attn_v.weight | Block 8 Attention Value (W) | ( ~1M) 1310720 | 2560 x 512 x 1 x 1 | F16 | 16.0000 | - Total elements in blk.8: (~93M) 93074433 - Percentage of total elements: 1.24% - Bits per Weight (BPW) for blk.8: 16.0023 bits ### Block 9 Tensor Group : ~93M Elements | T_ID | Tensor Layer Name | Human Friendly Tensor Layer Name | Elements | Shape | Type | BPW | | ---: | :------------------------------- | :--------------------------------------------- | :--------------- | :-------------------- | :--- | ------: | | 700 | blk.9.attn_norm.weight | Block 9 Attention Normalization (W) | ( ~3K) 2560 | 2560 x 1 x 1 x 1 | F32 | 32.0000 | | 701 | blk.9.layer_output_scale.weight | Block 9 Layer_Output_Scale (W) | ( 1) 1 | 1 x 1 x 1 x 1 | F32 | 32.0000 | | 702 | blk.9.ffn_down.weight | Block 9 Feed-Forward Network "Down" (W) | ( ~26M) 26214400 | 10240 x 2560 x 1 x 1 | F16 | 16.0000 | | 703 | blk.9.ffn_gate.weight | Block 9 Feed-Forward Network "Gate" (W) | ( ~26M) 26214400 | 2560 x 10240 x 1 x 1 | F16 | 16.0000 | | 704 | blk.9.ffn_up.weight | Block 9 Feed-Forward Network "Up" (W) | ( ~26M) 26214400 | 2560 x 10240 x 1 x 1 | F16 | 16.0000 | | 705 | blk.9.inp_gate.weight | Block 9 Inp_Gate (W) | (~655K) 655360 | 2560 x 256 x 1 x 1 | F16 | 16.0000 | | 706 | blk.9.proj.weight | Block 9 Proj (W) | (~655K) 655360 | 256 x 2560 x 1 x 1 | F16 | 16.0000 | | 707 | blk.9.post_attention_norm.weight | Block 9 Post_Attention_Norm (W) | ( ~3K) 2560 | 2560 x 1 x 1 x 1 | F32 | 32.0000 | | 708 | blk.9.post_ffw_norm.weight | Block 9 Post_Ffw_Norm (W) | ( ~3K) 2560 | 2560 x 1 x 1 x 1 | F32 | 32.0000 | | 709 | blk.9.post_norm.weight | Block 9 Post_Norm (W) | ( ~3K) 2560 | 2560 x 1 x 1 x 1 | F32 | 32.0000 | | 710 | blk.9.ffn_norm.weight | Block 9 Feed-Forward Network Normalization (W) | ( ~3K) 2560 | 2560 x 1 x 1 x 1 | F32 | 32.0000 | | 711 | blk.9.attn_k_norm.weight | Block 9 Attn_K_Norm (W) | ( 256) 256 | 256 x 1 x 1 x 1 | F32 | 32.0000 | | 712 | blk.9.attn_k.weight | Block 9 Attention Key (W) | ( ~1M) 1310720 | 2560 x 512 x 1 x 1 | F16 | 16.0000 | | 713 | blk.9.attn_output.weight | Block 9 Attention Output (W) | ( ~5M) 5242880 | 2048 x 2560 x 1 x 1 | F16 | 16.0000 | | 714 | blk.9.attn_q_norm.weight | Block 9 Attn_Q_Norm (W) | ( 256) 256 | 256 x 1 x 1 x 1 | F32 | 32.0000 | | 715 | blk.9.attn_q.weight | Block 9 Attention Query (W) | ( ~5M) 5242880 | 2560 x 2048 x 1 x 1 | F16 | 16.0000 | | 716 | blk.9.attn_v.weight | Block 9 Attention Value (W) | ( ~1M) 1310720 | 2560 x 512 x 1 x 1 | F16 | 16.0000 | - Total elements in blk.9: (~93M) 93074433 - Percentage of total elements: 1.24% - Bits per Weight (BPW) for blk.9: 16.0023 bits Total BPW for gemma-4-E4B-it-F16.gguf: 16.0012 bits