# gemma-4-E4B-it-Q2_K.gguf - GGUF Internal File Dump - Endian: LITTLE endian ## Key Value Metadata Store There are 52 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 | 49 | | 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 | FLOAT32 | 1 | gemma4.final_logit_softcapping | 30.0 | | 26 | UINT32 | 1 | gemma4.attention.sliding_window | 512 | | 27 | UINT32 | 1 | gemma4.attention.shared_kv_layers | 18 | | 28 | UINT32 | 1 | gemma4.embedding_length_per_layer_input | 256 | | 29 | [BOOL] | 42 | gemma4.attention.sliding_window_pattern | [ True, True, True, True, True, False, True, ... ] | | 30 | UINT32 | 1 | gemma4.attention.key_length_swa | 256 | | 31 | UINT32 | 1 | gemma4.attention.value_length_swa | 256 | | 32 | UINT32 | 1 | gemma4.rope.dimension_count | 512 | | 33 | UINT32 | 1 | gemma4.rope.dimension_count_swa | 256 | | 34 | STRING | 1 | tokenizer.ggml.model | `gemma4` | | 35 | [STRING] | 262144 | tokenizer.ggml.tokens | [ ``, ``, ``, ``, ``, ... ] | | 36 | [FLOAT32] | 262144 | tokenizer.ggml.scores | [ -1000.0, -1000.0, -1000.0, -1000.0, -1000.0, -1000.0, -1000.0, ... ] | | 37 | [INT32] | 262144 | tokenizer.ggml.token_type | [ 3, 3, 3, 3, 3, 1, 1, ... ] | | 38 | [STRING] | 514906 | tokenizer.ggml.merges | [ ``...``, `▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁`...`▁▁▁▁▁▁▁▁▁▁▁▁▁ ▁`, ``...``, ``...``, `▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁`...`▁▁▁▁▁▁▁▁▁▁▁▁ ▁▁`, ... ] | | 39 | UINT32 | 1 | tokenizer.ggml.bos_token_id | 2 | | 40 | UINT32 | 1 | tokenizer.ggml.eos_token_id | 1 | | 41 | UINT32 | 1 | tokenizer.ggml.unknown_token_id | 3 | | 42 | UINT32 | 1 | tokenizer.ggml.padding_token_id | 0 | | 43 | UINT32 | 1 | tokenizer.ggml.mask_token_id | 4 | | 44 | STRING | 1 | tokenizer.chat_template | `{%- macro format_parameters(pr`...` {%- endif -%} {%- endif -%}` | | 45 | BOOL | 1 | tokenizer.ggml.add_space_prefix | False | | 46 | BOOL | 1 | tokenizer.ggml.add_bos_token | True | | 47 | UINT32 | 1 | general.quantization_version | 2 | | 48 | UINT32 | 1 | general.file_type | 28 | | 49 | STRING | 1 | quantize.imatrix.file | `gemma-4-E4B-it-WIP/imatrix/ima`...`rix-gemma-4-E4B-it-medium.gguf` | | 50 | STRING | 1 | quantize.imatrix.dataset | `../datasets/imatrix/combined_eur_medium.txt` | | 51 | UINT32 | 1 | quantize.imatrix.entries_count | 342 | | 52 | UINT32 | 1 | quantize.imatrix.chunks_count | 2471 | ## Tensors Overview ~8B Elements Total number of elements in all tensors: 7518069290 Elements - [/Users/ed/Development/AI/hf/gemma-4-E4B-it-WIP/gemma-4-E4B-it-Q2\_K.gguf - GGUF Internal File Dump](#userseddevelopmentaihfgemma-4-e4b-it-wipgemma-4-e4b-it-q2_kgguf---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 2 Tensor Group : ~93M Elements](#block-2-tensor-group--93m-elements) - [Block 3 Tensor Group : ~93M Elements](#block-3-tensor-group--93m-elements) - [Block 4 Tensor Group : ~93M Elements](#block-4-tensor-group--93m-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) - [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 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 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 40 Tensor Group : ~93M Elements](#block-40-tensor-group--93m-elements) - [Block 41 Tensor Group : ~106M Elements](#block-41-tensor-group--106m-elements) ### Tensor Data Offset This table contains the offset and data segment relative to start of file | T_ID | Tensor Layer Name | Data Offset (B) | Data Size (B) | | ---: | :-------------------------------- | --------------: | ------------: | | 0 | output_norm.weight | 0xf173e0 | 0x2800 | | 1 | per_layer_model_proj.weight | 0xf19be0 | 0x3480000 | | 2 | per_layer_proj_norm.weight | 0x4399be0 | 0x400 | | 3 | per_layer_token_embd.weight | 0x4399fe0 | 0x37200000 | | 4 | rope_freqs.weight | 0x3b599fe0 | 0x400 | | 5 | token_embd.weight | 0x3b59a3e0 | 0xd200000 | | 6 | blk.0.attn_k.weight | 0x4879a3e0 | 0x69000 | | 7 | blk.0.attn_k_norm.weight | 0x488033e0 | 0x400 | | 8 | blk.0.attn_norm.weight | 0x488037e0 | 0x2800 | | 9 | blk.0.attn_output.weight | 0x48805fe0 | 0x1a4000 | | 10 | blk.0.attn_q.weight | 0x489a9fe0 | 0x1a4000 | | 11 | blk.0.attn_q_norm.weight | 0x48b4dfe0 | 0x400 | | 12 | blk.0.attn_v.weight | 0x48b4e3e0 | 0x52800 | | 13 | blk.0.ffn_down.weight | 0x48ba0be0 | 0x578000 | | 14 | blk.0.ffn_gate.weight | 0x49118be0 | 0x578000 | | 15 | blk.0.ffn_norm.weight | 0x49690be0 | 0x2800 | | 16 | blk.0.ffn_up.weight | 0x496933e0 | 0x672000 | | 17 | blk.0.inp_gate.weight | 0x49d053e0 | 0x23000 | | 18 | blk.0.layer_output_scale.weight | 0x49d283e0 | 0x4 | | 19 | blk.0.post_attention_norm.weight | 0x49d28400 | 0x2800 | | 20 | blk.0.post_ffw_norm.weight | 0x49d2ac00 | 0x2800 | | 21 | blk.0.post_norm.weight | 0x49d2d400 | 0x2800 | | 22 | blk.0.proj.weight | 0x49d2fc00 | 0x5a000 | | 23 | blk.1.attn_k.weight | 0x49d89c00 | 0x5c800 | | 24 | blk.1.attn_k_norm.weight | 0x49de6400 | 0x400 | | 25 | blk.1.attn_norm.weight | 0x49de6800 | 0x2800 | | 26 | blk.1.attn_output.weight | 0x49de9000 | 0x226000 | | 27 | blk.1.attn_q.weight | 0x4a00f000 | 0x172000 | | 28 | blk.1.attn_q_norm.weight | 0x4a181000 | 0x400 | | 29 | blk.1.attn_v.weight | 0x4a181400 | 0x69000 | | 30 | blk.1.ffn_down.weight | 0x4a1ea400 | 0x73a000 | | 31 | blk.1.ffn_gate.weight | 0x4a924400 | 0x578000 | | 32 | blk.1.ffn_norm.weight | 0x4ae9c400 | 0x2800 | | 33 | blk.1.ffn_up.weight | 0x4ae9ec00 | 0x834000 | | 34 | blk.1.inp_gate.weight | 0x4b6d2c00 | 0x34800 | | 35 | blk.1.layer_output_scale.weight | 0x4b707400 | 0x4 | | 36 | blk.1.post_attention_norm.weight | 0x4b707420 | 0x2800 | | 37 | blk.1.post_ffw_norm.weight | 0x4b709c20 | 0x2800 | | 38 | blk.1.post_norm.weight | 0x4b70c420 | 0x2800 | | 39 | blk.1.proj.weight | 0x4b70ec20 | 0x34800 | | 40 | blk.2.attn_k.weight | 0x4b743420 | 0x5c800 | | 41 | blk.2.attn_k_norm.weight | 0x4b79fc20 | 0x400 | | 42 | blk.2.attn_norm.weight | 0x4b7a0020 | 0x2800 | | 43 | blk.2.attn_output.weight | 0x4b7a2820 | 0x226000 | | 44 | blk.2.attn_q.weight | 0x4b9c8820 | 0x1ea000 | | 45 | blk.2.attn_q_norm.weight | 0x4bbb2820 | 0x400 | | 46 | blk.2.attn_v.weight | 0x4bbb2c20 | 0x69000 | | 47 | blk.2.ffn_down.weight | 0x4bc1bc20 | 0x73a000 | | 48 | blk.2.ffn_gate.weight | 0x4c355c20 | 0x578000 | | 49 | blk.2.ffn_norm.weight | 0x4c8cdc20 | 0x2800 | | 50 | blk.2.ffn_up.weight | 0x4c8d0420 | 0x672000 | | 51 | blk.2.inp_gate.weight | 0x4cf42420 | 0x34800 | | 52 | blk.2.layer_output_scale.weight | 0x4cf76c20 | 0x4 | | 53 | blk.2.post_attention_norm.weight | 0x4cf76c40 | 0x2800 | | 54 | blk.2.post_ffw_norm.weight | 0x4cf79440 | 0x2800 | | 55 | blk.2.post_norm.weight | 0x4cf7bc40 | 0x2800 | | 56 | blk.2.proj.weight | 0x4cf7e440 | 0x34800 | | 57 | blk.3.attn_k.weight | 0x4cfb2c40 | 0x5c800 | | 58 | blk.3.attn_k_norm.weight | 0x4d00f440 | 0x400 | | 59 | blk.3.attn_norm.weight | 0x4d00f840 | 0x2800 | | 60 | blk.3.attn_output.weight | 0x4d012040 | 0x226000 | | 61 | blk.3.attn_q.weight | 0x4d238040 | 0x172000 | | 62 | blk.3.attn_q_norm.weight | 0x4d3aa040 | 0x400 | | 63 | blk.3.attn_v.weight | 0x4d3aa440 | 0x69000 | | 64 | blk.3.ffn_down.weight | 0x4d413440 | 0x672000 | | 65 | blk.3.ffn_gate.weight | 0x4da85440 | 0x578000 | | 66 | blk.3.ffn_norm.weight | 0x4dffd440 | 0x2800 | | 67 | blk.3.ffn_up.weight | 0x4dfffc40 | 0x834000 | | 68 | blk.3.inp_gate.weight | 0x4e833c40 | 0x23000 | | 69 | blk.3.layer_output_scale.weight | 0x4e856c40 | 0x4 | | 70 | blk.3.post_attention_norm.weight | 0x4e856c60 | 0x2800 | | 71 | blk.3.post_ffw_norm.weight | 0x4e859460 | 0x2800 | | 72 | blk.3.post_norm.weight | 0x4e85bc60 | 0x2800 | | 73 | blk.3.proj.weight | 0x4e85e460 | 0x34800 | | 74 | blk.4.attn_k.weight | 0x4e892c60 | 0x5c800 | | 75 | blk.4.attn_k_norm.weight | 0x4e8ef460 | 0x400 | | 76 | blk.4.attn_norm.weight | 0x4e8ef860 | 0x2800 | | 77 | blk.4.attn_output.weight | 0x4e8f2060 | 0x226000 | | 78 | blk.4.attn_q.weight | 0x4eb18060 | 0x172000 | | 79 | blk.4.attn_q_norm.weight | 0x4ec8a060 | 0x400 | | 80 | blk.4.attn_v.weight | 0x4ec8a460 | 0x52800 | | 81 | blk.4.ffn_down.weight | 0x4ecdcc60 | 0x672000 | | 82 | blk.4.ffn_gate.weight | 0x4f34ec60 | 0x578000 | | 83 | blk.4.ffn_norm.weight | 0x4f8c6c60 | 0x2800 | | 84 | blk.4.ffn_up.weight | 0x4f8c9460 | 0x672000 | | 85 | blk.4.inp_gate.weight | 0x4ff3b460 | 0x23000 | | 86 | blk.4.layer_output_scale.weight | 0x4ff5e460 | 0x4 | | 87 | blk.4.post_attention_norm.weight | 0x4ff5e480 | 0x2800 | | 88 | blk.4.post_ffw_norm.weight | 0x4ff60c80 | 0x2800 | | 89 | blk.4.post_norm.weight | 0x4ff63480 | 0x2800 | | 90 | blk.4.proj.weight | 0x4ff65c80 | 0x34800 | | 91 | blk.5.attn_k.weight | 0x4ff9a480 | 0xb9000 | | 92 | blk.5.attn_k_norm.weight | 0x50053480 | 0x800 | | 93 | blk.5.attn_norm.weight | 0x50053c80 | 0x2800 | | 94 | blk.5.attn_output.weight | 0x50056480 | 0x348000 | | 95 | blk.5.attn_q.weight | 0x5039e480 | 0x2e4000 | | 96 | blk.5.attn_q_norm.weight | 0x50682480 | 0x800 | | 97 | blk.5.attn_v.weight | 0x50682c80 | 0xa5000 | | 98 | blk.5.ffn_down.weight | 0x50727c80 | 0x73a000 | | 99 | blk.5.ffn_gate.weight | 0x50e61c80 | 0x578000 | | 100 | blk.5.ffn_norm.weight | 0x513d9c80 | 0x2800 | | 101 | blk.5.ffn_up.weight | 0x513dc480 | 0x834000 | | 102 | blk.5.inp_gate.weight | 0x51c10480 | 0x34800 | | 103 | blk.5.layer_output_scale.weight | 0x51c44c80 | 0x4 | | 104 | blk.5.post_attention_norm.weight | 0x51c44ca0 | 0x2800 | | 105 | blk.5.post_ffw_norm.weight | 0x51c474a0 | 0x2800 | | 106 | blk.5.post_norm.weight | 0x51c49ca0 | 0x2800 | | 107 | blk.5.proj.weight | 0x51c4c4a0 | 0x34800 | | 108 | blk.6.attn_k.weight | 0x51c80ca0 | 0x69000 | | 109 | blk.6.attn_k_norm.weight | 0x51ce9ca0 | 0x400 | | 110 | blk.6.attn_norm.weight | 0x51cea0a0 | 0x2800 | | 111 | blk.6.attn_output.weight | 0x51cec8a0 | 0x1ea000 | | 112 | blk.6.attn_q.weight | 0x51ed68a0 | 0x1a4000 | | 113 | blk.6.attn_q_norm.weight | 0x5207a8a0 | 0x400 | | 114 | blk.6.attn_v.weight | 0x5207aca0 | 0x69000 | | 115 | blk.6.ffn_down.weight | 0x520e3ca0 | 0x672000 | | 116 | blk.6.ffn_gate.weight | 0x52755ca0 | 0x578000 | | 117 | blk.6.ffn_norm.weight | 0x52ccdca0 | 0x2800 | | 118 | blk.6.ffn_up.weight | 0x52cd04a0 | 0x834000 | | 119 | blk.6.inp_gate.weight | 0x535044a0 | 0x34800 | | 120 | blk.6.layer_output_scale.weight | 0x53538ca0 | 0x4 | | 121 | blk.6.post_attention_norm.weight | 0x53538cc0 | 0x2800 | | 122 | blk.6.post_ffw_norm.weight | 0x5353b4c0 | 0x2800 | | 123 | blk.6.post_norm.weight | 0x5353dcc0 | 0x2800 | | 124 | blk.6.proj.weight | 0x535404c0 | 0x34800 | | 125 | blk.7.attn_k.weight | 0x53574cc0 | 0x5c800 | | 126 | blk.7.attn_k_norm.weight | 0x535d14c0 | 0x400 | | 127 | blk.7.attn_norm.weight | 0x535d18c0 | 0x2800 | | 128 | blk.7.attn_output.weight | 0x535d40c0 | 0x226000 | | 129 | blk.7.attn_q.weight | 0x537fa0c0 | 0x172000 | | 130 | blk.7.attn_q_norm.weight | 0x5396c0c0 | 0x400 | | 131 | blk.7.attn_v.weight | 0x5396c4c0 | 0x52800 | | 132 | blk.7.ffn_down.weight | 0x539becc0 | 0x672000 | | 133 | blk.7.ffn_gate.weight | 0x54030cc0 | 0x578000 | | 134 | blk.7.ffn_norm.weight | 0x545a8cc0 | 0x2800 | | 135 | blk.7.ffn_up.weight | 0x545ab4c0 | 0x672000 | | 136 | blk.7.inp_gate.weight | 0x54c1d4c0 | 0x23000 | | 137 | blk.7.layer_output_scale.weight | 0x54c404c0 | 0x4 | | 138 | blk.7.post_attention_norm.weight | 0x54c404e0 | 0x2800 | | 139 | blk.7.post_ffw_norm.weight | 0x54c42ce0 | 0x2800 | | 140 | blk.7.post_norm.weight | 0x54c454e0 | 0x2800 | | 141 | blk.7.proj.weight | 0x54c47ce0 | 0x34800 | | 142 | blk.8.attn_k.weight | 0x54c7c4e0 | 0x5c800 | | 143 | blk.8.attn_k_norm.weight | 0x54cd8ce0 | 0x400 | | 144 | blk.8.attn_norm.weight | 0x54cd90e0 | 0x2800 | | 145 | blk.8.attn_output.weight | 0x54cdb8e0 | 0x226000 | | 146 | blk.8.attn_q.weight | 0x54f018e0 | 0x172000 | | 147 | blk.8.attn_q_norm.weight | 0x550738e0 | 0x400 | | 148 | blk.8.attn_v.weight | 0x55073ce0 | 0x52800 | | 149 | blk.8.ffn_down.weight | 0x550c64e0 | 0x672000 | | 150 | blk.8.ffn_gate.weight | 0x557384e0 | 0x672000 | | 151 | blk.8.ffn_norm.weight | 0x55daa4e0 | 0x2800 | | 152 | blk.8.ffn_up.weight | 0x55dacce0 | 0x672000 | | 153 | blk.8.inp_gate.weight | 0x5641ece0 | 0x23000 | | 154 | blk.8.layer_output_scale.weight | 0x56441ce0 | 0x4 | | 155 | blk.8.post_attention_norm.weight | 0x56441d00 | 0x2800 | | 156 | blk.8.post_ffw_norm.weight | 0x56444500 | 0x2800 | | 157 | blk.8.post_norm.weight | 0x56446d00 | 0x2800 | | 158 | blk.8.proj.weight | 0x56449500 | 0x34800 | | 159 | blk.9.attn_k.weight | 0x5647dd00 | 0x5c800 | | 160 | blk.9.attn_k_norm.weight | 0x564da500 | 0x400 | | 161 | blk.9.attn_norm.weight | 0x564da900 | 0x2800 | | 162 | blk.9.attn_output.weight | 0x564dd100 | 0x226000 | | 163 | blk.9.attn_q.weight | 0x56703100 | 0x172000 | | 164 | blk.9.attn_q_norm.weight | 0x56875100 | 0x400 | | 165 | blk.9.attn_v.weight | 0x56875500 | 0x52800 | | 166 | blk.9.ffn_down.weight | 0x568c7d00 | 0x672000 | | 167 | blk.9.ffn_gate.weight | 0x56f39d00 | 0x672000 | | 168 | blk.9.ffn_norm.weight | 0x575abd00 | 0x2800 | | 169 | blk.9.ffn_up.weight | 0x575ae500 | 0x672000 | | 170 | blk.9.inp_gate.weight | 0x57c20500 | 0x23000 | | 171 | blk.9.layer_output_scale.weight | 0x57c43500 | 0x4 | | 172 | blk.9.post_attention_norm.weight | 0x57c43520 | 0x2800 | | 173 | blk.9.post_ffw_norm.weight | 0x57c45d20 | 0x2800 | | 174 | blk.9.post_norm.weight | 0x57c48520 | 0x2800 | | 175 | blk.9.proj.weight | 0x57c4ad20 | 0x34800 | | 176 | blk.10.attn_k.weight | 0x57c7f520 | 0x5c800 | | 177 | blk.10.attn_k_norm.weight | 0x57cdbd20 | 0x400 | | 178 | blk.10.attn_norm.weight | 0x57cdc120 | 0x2800 | | 179 | blk.10.attn_output.weight | 0x57cde920 | 0x226000 | | 180 | blk.10.attn_q.weight | 0x57f04920 | 0x1ea000 | | 181 | blk.10.attn_q_norm.weight | 0x580ee920 | 0x400 | | 182 | blk.10.attn_v.weight | 0x580eed20 | 0x69000 | | 183 | blk.10.ffn_down.weight | 0x58157d20 | 0x672000 | | 184 | blk.10.ffn_gate.weight | 0x587c9d20 | 0x672000 | | 185 | blk.10.ffn_norm.weight | 0x58e3bd20 | 0x2800 | | 186 | blk.10.ffn_up.weight | 0x58e3e520 | 0x834000 | | 187 | blk.10.inp_gate.weight | 0x59672520 | 0x23000 | | 188 | blk.10.layer_output_scale.weight | 0x59695520 | 0x4 | | 189 | blk.10.post_attention_norm.weight | 0x59695540 | 0x2800 | | 190 | blk.10.post_ffw_norm.weight | 0x59697d40 | 0x2800 | | 191 | blk.10.post_norm.weight | 0x5969a540 | 0x2800 | | 192 | blk.10.proj.weight | 0x5969cd40 | 0x5a000 | | 193 | blk.11.attn_k.weight | 0x596f6d40 | 0xb9000 | | 194 | blk.11.attn_k_norm.weight | 0x597afd40 | 0x800 | | 195 | blk.11.attn_norm.weight | 0x597b0540 | 0x2800 | | 196 | blk.11.attn_output.weight | 0x597b2d40 | 0x348000 | | 197 | blk.11.attn_q.weight | 0x59afad40 | 0x3d4000 | | 198 | blk.11.attn_q_norm.weight | 0x59eced40 | 0x800 | | 199 | blk.11.attn_v.weight | 0x59ecf540 | 0xd2000 | | 200 | blk.11.ffn_down.weight | 0x59fa1540 | 0x672000 | | 201 | blk.11.ffn_gate.weight | 0x5a613540 | 0x578000 | | 202 | blk.11.ffn_norm.weight | 0x5ab8b540 | 0x2800 | | 203 | blk.11.ffn_up.weight | 0x5ab8dd40 | 0x672000 | | 204 | blk.11.inp_gate.weight | 0x5b1ffd40 | 0x23000 | | 205 | blk.11.layer_output_scale.weight | 0x5b222d40 | 0x4 | | 206 | blk.11.post_attention_norm.weight | 0x5b222d60 | 0x2800 | | 207 | blk.11.post_ffw_norm.weight | 0x5b225560 | 0x2800 | | 208 | blk.11.post_norm.weight | 0x5b227d60 | 0x2800 | | 209 | blk.11.proj.weight | 0x5b22a560 | 0x34800 | | 210 | blk.12.attn_k.weight | 0x5b25ed60 | 0x69000 | | 211 | blk.12.attn_k_norm.weight | 0x5b2c7d60 | 0x400 | | 212 | blk.12.attn_norm.weight | 0x5b2c8160 | 0x2800 | | 213 | blk.12.attn_output.weight | 0x5b2ca960 | 0x1ea000 | | 214 | blk.12.attn_q.weight | 0x5b4b4960 | 0x1a4000 | | 215 | blk.12.attn_q_norm.weight | 0x5b658960 | 0x400 | | 216 | blk.12.attn_v.weight | 0x5b658d60 | 0x69000 | | 217 | blk.12.ffn_down.weight | 0x5b6c1d60 | 0x672000 | | 218 | blk.12.ffn_gate.weight | 0x5bd33d60 | 0x672000 | | 219 | blk.12.ffn_norm.weight | 0x5c3a5d60 | 0x2800 | | 220 | blk.12.ffn_up.weight | 0x5c3a8560 | 0x834000 | | 221 | blk.12.inp_gate.weight | 0x5cbdc560 | 0x23000 | | 222 | blk.12.layer_output_scale.weight | 0x5cbff560 | 0x4 | | 223 | blk.12.post_attention_norm.weight | 0x5cbff580 | 0x2800 | | 224 | blk.12.post_ffw_norm.weight | 0x5cc01d80 | 0x2800 | | 225 | blk.12.post_norm.weight | 0x5cc04580 | 0x2800 | | 226 | blk.12.proj.weight | 0x5cc06d80 | 0x34800 | | 227 | blk.13.attn_k.weight | 0x5cc3b580 | 0x7a800 | | 228 | blk.13.attn_k_norm.weight | 0x5ccb5d80 | 0x400 | | 229 | blk.13.attn_norm.weight | 0x5ccb6180 | 0x2800 | | 230 | blk.13.attn_output.weight | 0x5ccb8980 | 0x226000 | | 231 | blk.13.attn_q.weight | 0x5cede980 | 0x1ea000 | | 232 | blk.13.attn_q_norm.weight | 0x5d0c8980 | 0x400 | | 233 | blk.13.attn_v.weight | 0x5d0c8d80 | 0x69000 | | 234 | blk.13.ffn_down.weight | 0x5d131d80 | 0x672000 | | 235 | blk.13.ffn_gate.weight | 0x5d7a3d80 | 0x578000 | | 236 | blk.13.ffn_norm.weight | 0x5dd1bd80 | 0x2800 | | 237 | blk.13.ffn_up.weight | 0x5dd1e580 | 0x672000 | | 238 | blk.13.inp_gate.weight | 0x5e390580 | 0x23000 | | 239 | blk.13.layer_output_scale.weight | 0x5e3b3580 | 0x4 | | 240 | blk.13.post_attention_norm.weight | 0x5e3b35a0 | 0x2800 | | 241 | blk.13.post_ffw_norm.weight | 0x5e3b5da0 | 0x2800 | | 242 | blk.13.post_norm.weight | 0x5e3b85a0 | 0x2800 | | 243 | blk.13.proj.weight | 0x5e3bada0 | 0x6e000 | | 244 | blk.14.attn_k.weight | 0x5e428da0 | 0x7a800 | | 245 | blk.14.attn_k_norm.weight | 0x5e4a35a0 | 0x400 | | 246 | blk.14.attn_norm.weight | 0x5e4a39a0 | 0x2800 | | 247 | blk.14.attn_output.weight | 0x5e4a61a0 | 0x226000 | | 248 | blk.14.attn_q.weight | 0x5e6cc1a0 | 0x172000 | | 249 | blk.14.attn_q_norm.weight | 0x5e83e1a0 | 0x400 | | 250 | blk.14.attn_v.weight | 0x5e83e5a0 | 0x69000 | | 251 | blk.14.ffn_down.weight | 0x5e8a75a0 | 0x672000 | | 252 | blk.14.ffn_gate.weight | 0x5ef195a0 | 0x672000 | | 253 | blk.14.ffn_norm.weight | 0x5f58b5a0 | 0x2800 | | 254 | blk.14.ffn_up.weight | 0x5f58dda0 | 0x672000 | | 255 | blk.14.inp_gate.weight | 0x5fbffda0 | 0x29400 | | 256 | blk.14.layer_output_scale.weight | 0x5fc291a0 | 0x4 | | 257 | blk.14.post_attention_norm.weight | 0x5fc291c0 | 0x2800 | | 258 | blk.14.post_ffw_norm.weight | 0x5fc2b9c0 | 0x2800 | | 259 | blk.14.post_norm.weight | 0x5fc2e1c0 | 0x2800 | | 260 | blk.14.proj.weight | 0x5fc309c0 | 0x5a000 | | 261 | blk.15.attn_k.weight | 0x5fc8a9c0 | 0x7a800 | | 262 | blk.15.attn_k_norm.weight | 0x5fd051c0 | 0x400 | | 263 | blk.15.attn_norm.weight | 0x5fd055c0 | 0x2800 | | 264 | blk.15.attn_output.weight | 0x5fd07dc0 | 0x226000 | | 265 | blk.15.attn_q.weight | 0x5ff2ddc0 | 0x172000 | | 266 | blk.15.attn_q_norm.weight | 0x6009fdc0 | 0x400 | | 267 | blk.15.attn_v.weight | 0x600a01c0 | 0x69000 | | 268 | blk.15.ffn_down.weight | 0x601091c0 | 0x672000 | | 269 | blk.15.ffn_gate.weight | 0x6077b1c0 | 0x672000 | | 270 | blk.15.ffn_norm.weight | 0x60ded1c0 | 0x2800 | | 271 | blk.15.ffn_up.weight | 0x60def9c0 | 0x834000 | | 272 | blk.15.inp_gate.weight | 0x616239c0 | 0x23000 | | 273 | blk.15.layer_output_scale.weight | 0x616469c0 | 0x4 | | 274 | blk.15.post_attention_norm.weight | 0x616469e0 | 0x2800 | | 275 | blk.15.post_ffw_norm.weight | 0x616491e0 | 0x2800 | | 276 | blk.15.post_norm.weight | 0x6164b9e0 | 0x2800 | | 277 | blk.15.proj.weight | 0x6164e1e0 | 0x6e000 | | 278 | blk.16.attn_k.weight | 0x616bc1e0 | 0x69000 | | 279 | blk.16.attn_k_norm.weight | 0x617251e0 | 0x400 | | 280 | blk.16.attn_norm.weight | 0x617255e0 | 0x2800 | | 281 | blk.16.attn_output.weight | 0x61727de0 | 0x226000 | | 282 | blk.16.attn_q.weight | 0x6194dde0 | 0x172000 | | 283 | blk.16.attn_q_norm.weight | 0x61abfde0 | 0x400 | | 284 | blk.16.attn_v.weight | 0x61ac01e0 | 0x69000 | | 285 | blk.16.ffn_down.weight | 0x61b291e0 | 0x73a000 | | 286 | blk.16.ffn_gate.weight | 0x622631e0 | 0x672000 | | 287 | blk.16.ffn_norm.weight | 0x628d51e0 | 0x2800 | | 288 | blk.16.ffn_up.weight | 0x628d79e0 | 0x834000 | | 289 | blk.16.inp_gate.weight | 0x6310b9e0 | 0x23000 | | 290 | blk.16.layer_output_scale.weight | 0x6312e9e0 | 0x4 | | 291 | blk.16.post_attention_norm.weight | 0x6312ea00 | 0x2800 | | 292 | blk.16.post_ffw_norm.weight | 0x63131200 | 0x2800 | | 293 | blk.16.post_norm.weight | 0x63133a00 | 0x2800 | | 294 | blk.16.proj.weight | 0x63136200 | 0x64000 | | 295 | blk.17.attn_k.weight | 0x6319a200 | 0xb9000 | | 296 | blk.17.attn_k_norm.weight | 0x63253200 | 0x800 | | 297 | blk.17.attn_norm.weight | 0x63253a00 | 0x2800 | | 298 | blk.17.attn_output.weight | 0x63256200 | 0x348000 | | 299 | blk.17.attn_q.weight | 0x6359e200 | 0x2e4000 | | 300 | blk.17.attn_q_norm.weight | 0x63882200 | 0x800 | | 301 | blk.17.attn_v.weight | 0x63882a00 | 0xd2000 | | 302 | blk.17.ffn_down.weight | 0x63954a00 | 0x672000 | | 303 | blk.17.ffn_gate.weight | 0x63fc6a00 | 0x672000 | | 304 | blk.17.ffn_norm.weight | 0x64638a00 | 0x2800 | | 305 | blk.17.ffn_up.weight | 0x6463b200 | 0x834000 | | 306 | blk.17.inp_gate.weight | 0x64e6f200 | 0x23000 | | 307 | blk.17.layer_output_scale.weight | 0x64e92200 | 0x4 | | 308 | blk.17.post_attention_norm.weight | 0x64e92220 | 0x2800 | | 309 | blk.17.post_ffw_norm.weight | 0x64e94a20 | 0x2800 | | 310 | blk.17.post_norm.weight | 0x64e97220 | 0x2800 | | 311 | blk.17.proj.weight | 0x64e99a20 | 0x5a000 | | 312 | blk.18.attn_k.weight | 0x64ef3a20 | 0x7a800 | | 313 | blk.18.attn_k_norm.weight | 0x64f6e220 | 0x400 | | 314 | blk.18.attn_norm.weight | 0x64f6e620 | 0x2800 | | 315 | blk.18.attn_output.weight | 0x64f70e20 | 0x226000 | | 316 | blk.18.attn_q.weight | 0x65196e20 | 0x1ea000 | | 317 | blk.18.attn_q_norm.weight | 0x65380e20 | 0x400 | | 318 | blk.18.attn_v.weight | 0x65381220 | 0x69000 | | 319 | blk.18.ffn_down.weight | 0x653ea220 | 0x73a000 | | 320 | blk.18.ffn_gate.weight | 0x65b24220 | 0x672000 | | 321 | blk.18.ffn_norm.weight | 0x66196220 | 0x2800 | | 322 | blk.18.ffn_up.weight | 0x66198a20 | 0x672000 | | 323 | blk.18.inp_gate.weight | 0x6680aa20 | 0x23000 | | 324 | blk.18.layer_output_scale.weight | 0x6682da20 | 0x4 | | 325 | blk.18.post_attention_norm.weight | 0x6682da40 | 0x2800 | | 326 | blk.18.post_ffw_norm.weight | 0x66830240 | 0x2800 | | 327 | blk.18.post_norm.weight | 0x66832a40 | 0x2800 | | 328 | blk.18.proj.weight | 0x66835240 | 0x64000 | | 329 | blk.19.attn_k.weight | 0x66899240 | 0x7a800 | | 330 | blk.19.attn_k_norm.weight | 0x66913a40 | 0x400 | | 331 | blk.19.attn_norm.weight | 0x66913e40 | 0x2800 | | 332 | blk.19.attn_output.weight | 0x66916640 | 0x226000 | | 333 | blk.19.attn_q.weight | 0x66b3c640 | 0x1ea000 | | 334 | blk.19.attn_q_norm.weight | 0x66d26640 | 0x400 | | 335 | blk.19.attn_v.weight | 0x66d26a40 | 0x69000 | | 336 | blk.19.ffn_down.weight | 0x66d8fa40 | 0x73a000 | | 337 | blk.19.ffn_gate.weight | 0x674c9a40 | 0x672000 | | 338 | blk.19.ffn_norm.weight | 0x67b3ba40 | 0x2800 | | 339 | blk.19.ffn_up.weight | 0x67b3e240 | 0x672000 | | 340 | blk.19.inp_gate.weight | 0x681b0240 | 0x23000 | | 341 | blk.19.layer_output_scale.weight | 0x681d3240 | 0x4 | | 342 | blk.19.post_attention_norm.weight | 0x681d3260 | 0x2800 | | 343 | blk.19.post_ffw_norm.weight | 0x681d5a60 | 0x2800 | | 344 | blk.19.post_norm.weight | 0x681d8260 | 0x2800 | | 345 | blk.19.proj.weight | 0x681daa60 | 0x55000 | | 346 | blk.20.attn_k.weight | 0x6822fa60 | 0x7a800 | | 347 | blk.20.attn_k_norm.weight | 0x682aa260 | 0x400 | | 348 | blk.20.attn_norm.weight | 0x682aa660 | 0x2800 | | 349 | blk.20.attn_output.weight | 0x682ace60 | 0x226000 | | 350 | blk.20.attn_q.weight | 0x684d2e60 | 0x1ea000 | | 351 | blk.20.attn_q_norm.weight | 0x686bce60 | 0x400 | | 352 | blk.20.attn_v.weight | 0x686bd260 | 0x69000 | | 353 | blk.20.ffn_down.weight | 0x68726260 | 0x672000 | | 354 | blk.20.ffn_gate.weight | 0x68d98260 | 0x672000 | | 355 | blk.20.ffn_norm.weight | 0x6940a260 | 0x2800 | | 356 | blk.20.ffn_up.weight | 0x6940ca60 | 0x834000 | | 357 | blk.20.inp_gate.weight | 0x69c40a60 | 0x23000 | | 358 | blk.20.layer_output_scale.weight | 0x69c63a60 | 0x4 | | 359 | blk.20.post_attention_norm.weight | 0x69c63a80 | 0x2800 | | 360 | blk.20.post_ffw_norm.weight | 0x69c66280 | 0x2800 | | 361 | blk.20.post_norm.weight | 0x69c68a80 | 0x2800 | | 362 | blk.20.proj.weight | 0x69c6b280 | 0x34800 | | 363 | blk.21.attn_k.weight | 0x69c9fa80 | 0x7a800 | | 364 | blk.21.attn_k_norm.weight | 0x69d1a280 | 0x400 | | 365 | blk.21.attn_norm.weight | 0x69d1a680 | 0x2800 | | 366 | blk.21.attn_output.weight | 0x69d1ce80 | 0x226000 | | 367 | blk.21.attn_q.weight | 0x69f42e80 | 0x1ea000 | | 368 | blk.21.attn_q_norm.weight | 0x6a12ce80 | 0x400 | | 369 | blk.21.attn_v.weight | 0x6a12d280 | 0x69000 | | 370 | blk.21.ffn_down.weight | 0x6a196280 | 0x73a000 | | 371 | blk.21.ffn_gate.weight | 0x6a8d0280 | 0x672000 | | 372 | blk.21.ffn_norm.weight | 0x6af42280 | 0x2800 | | 373 | blk.21.ffn_up.weight | 0x6af44a80 | 0x834000 | | 374 | blk.21.inp_gate.weight | 0x6b778a80 | 0x23000 | | 375 | blk.21.layer_output_scale.weight | 0x6b79ba80 | 0x4 | | 376 | blk.21.post_attention_norm.weight | 0x6b79baa0 | 0x2800 | | 377 | blk.21.post_ffw_norm.weight | 0x6b79e2a0 | 0x2800 | | 378 | blk.21.post_norm.weight | 0x6b7a0aa0 | 0x2800 | | 379 | blk.21.proj.weight | 0x6b7a32a0 | 0x55000 | | 380 | blk.22.attn_k.weight | 0x6b7f82a0 | 0x7a800 | | 381 | blk.22.attn_k_norm.weight | 0x6b872aa0 | 0x400 | | 382 | blk.22.attn_norm.weight | 0x6b872ea0 | 0x2800 | | 383 | blk.22.attn_output.weight | 0x6b8756a0 | 0x226000 | | 384 | blk.22.attn_q.weight | 0x6ba9b6a0 | 0x1ea000 | | 385 | blk.22.attn_q_norm.weight | 0x6bc856a0 | 0x400 | | 386 | blk.22.attn_v.weight | 0x6bc85aa0 | 0x69000 | | 387 | blk.22.ffn_down.weight | 0x6bceeaa0 | 0x834000 | | 388 | blk.22.ffn_gate.weight | 0x6c522aa0 | 0x672000 | | 389 | blk.22.ffn_norm.weight | 0x6cb94aa0 | 0x2800 | | 390 | blk.22.ffn_up.weight | 0x6cb972a0 | 0x834000 | | 391 | blk.22.inp_gate.weight | 0x6d3cb2a0 | 0x23000 | | 392 | blk.22.layer_output_scale.weight | 0x6d3ee2a0 | 0x4 | | 393 | blk.22.post_attention_norm.weight | 0x6d3ee2c0 | 0x2800 | | 394 | blk.22.post_ffw_norm.weight | 0x6d3f0ac0 | 0x2800 | | 395 | blk.22.post_norm.weight | 0x6d3f32c0 | 0x2800 | | 396 | blk.22.proj.weight | 0x6d3f5ac0 | 0x34800 | | 397 | blk.23.attn_k.weight | 0x6d42a2c0 | 0xf5000 | | 398 | blk.23.attn_k_norm.weight | 0x6d51f2c0 | 0x800 | | 399 | blk.23.attn_norm.weight | 0x6d51fac0 | 0x2800 | | 400 | blk.23.attn_output.weight | 0x6d5222c0 | 0x348000 | | 401 | blk.23.attn_q.weight | 0x6d86a2c0 | 0x3d4000 | | 402 | blk.23.attn_q_norm.weight | 0x6dc3e2c0 | 0x800 | | 403 | blk.23.attn_v.weight | 0x6dc3eac0 | 0xf5000 | | 404 | blk.23.ffn_down.weight | 0x6dd33ac0 | 0x672000 | | 405 | blk.23.ffn_gate.weight | 0x6e3a5ac0 | 0x672000 | | 406 | blk.23.ffn_norm.weight | 0x6ea17ac0 | 0x2800 | | 407 | blk.23.ffn_up.weight | 0x6ea1a2c0 | 0x834000 | | 408 | blk.23.inp_gate.weight | 0x6f24e2c0 | 0x34800 | | 409 | blk.23.layer_output_scale.weight | 0x6f282ac0 | 0x4 | | 410 | blk.23.post_attention_norm.weight | 0x6f282ae0 | 0x2800 | | 411 | blk.23.post_ffw_norm.weight | 0x6f2852e0 | 0x2800 | | 412 | blk.23.post_norm.weight | 0x6f287ae0 | 0x2800 | | 413 | blk.23.proj.weight | 0x6f28a2e0 | 0x5a000 | | 414 | blk.24.attn_k.weight | 0x6f2e42e0 | 0x89800 | | 415 | blk.24.attn_k_norm.weight | 0x6f36dae0 | 0x400 | | 416 | blk.24.attn_norm.weight | 0x6f36dee0 | 0x2800 | | 417 | blk.24.attn_output.weight | 0x6f3706e0 | 0x1ea000 | | 418 | blk.24.attn_q.weight | 0x6f55a6e0 | 0x1ea000 | | 419 | blk.24.attn_q_norm.weight | 0x6f7446e0 | 0x400 | | 420 | blk.24.attn_v.weight | 0x6f744ae0 | 0x69000 | | 421 | blk.24.ffn_down.weight | 0x6f7adae0 | 0x672000 | | 422 | blk.24.ffn_gate.weight | 0x6fe1fae0 | 0x672000 | | 423 | blk.24.ffn_norm.weight | 0x70491ae0 | 0x2800 | | 424 | blk.24.ffn_up.weight | 0x704942e0 | 0x834000 | | 425 | blk.24.inp_gate.weight | 0x70cc82e0 | 0x34800 | | 426 | blk.24.layer_output_scale.weight | 0x70cfcae0 | 0x4 | | 427 | blk.24.post_attention_norm.weight | 0x70cfcb00 | 0x2800 | | 428 | blk.24.post_ffw_norm.weight | 0x70cff300 | 0x2800 | | 429 | blk.24.post_norm.weight | 0x70d01b00 | 0x2800 | | 430 | blk.24.proj.weight | 0x70d04300 | 0x34800 | | 431 | blk.25.attn_k.weight | 0x70d38b00 | 0x89800 | | 432 | blk.25.attn_k_norm.weight | 0x70dc2300 | 0x400 | | 433 | blk.25.attn_norm.weight | 0x70dc2700 | 0x2800 | | 434 | blk.25.attn_output.weight | 0x70dc4f00 | 0x226000 | | 435 | blk.25.attn_q.weight | 0x70feaf00 | 0x1a4000 | | 436 | blk.25.attn_q_norm.weight | 0x7118ef00 | 0x400 | | 437 | blk.25.attn_v.weight | 0x7118f300 | 0x69000 | | 438 | blk.25.ffn_down.weight | 0x711f8300 | 0x672000 | | 439 | blk.25.ffn_gate.weight | 0x7186a300 | 0x672000 | | 440 | blk.25.ffn_norm.weight | 0x71edc300 | 0x2800 | | 441 | blk.25.ffn_up.weight | 0x71edeb00 | 0x834000 | | 442 | blk.25.inp_gate.weight | 0x72712b00 | 0x29400 | | 443 | blk.25.layer_output_scale.weight | 0x7273bf00 | 0x4 | | 444 | blk.25.post_attention_norm.weight | 0x7273bf20 | 0x2800 | | 445 | blk.25.post_ffw_norm.weight | 0x7273e720 | 0x2800 | | 446 | blk.25.post_norm.weight | 0x72740f20 | 0x2800 | | 447 | blk.25.proj.weight | 0x72743720 | 0x5a000 | | 448 | blk.26.attn_k.weight | 0x7279d720 | 0x89800 | | 449 | blk.26.attn_k_norm.weight | 0x72826f20 | 0x400 | | 450 | blk.26.attn_norm.weight | 0x72827320 | 0x2800 | | 451 | blk.26.attn_output.weight | 0x72829b20 | 0x1ea000 | | 452 | blk.26.attn_q.weight | 0x72a13b20 | 0x1a4000 | | 453 | blk.26.attn_q_norm.weight | 0x72bb7b20 | 0x400 | | 454 | blk.26.attn_v.weight | 0x72bb7f20 | 0x69000 | | 455 | blk.26.ffn_down.weight | 0x72c20f20 | 0x672000 | | 456 | blk.26.ffn_gate.weight | 0x73292f20 | 0x672000 | | 457 | blk.26.ffn_norm.weight | 0x73904f20 | 0x2800 | | 458 | blk.26.ffn_up.weight | 0x73907720 | 0x672000 | | 459 | blk.26.inp_gate.weight | 0x73f79720 | 0x23000 | | 460 | blk.26.layer_output_scale.weight | 0x73f9c720 | 0x4 | | 461 | blk.26.post_attention_norm.weight | 0x73f9c740 | 0x2800 | | 462 | blk.26.post_ffw_norm.weight | 0x73f9ef40 | 0x2800 | | 463 | blk.26.post_norm.weight | 0x73fa1740 | 0x2800 | | 464 | blk.26.proj.weight | 0x73fa3f40 | 0x5a000 | | 465 | blk.27.attn_k.weight | 0x73ffdf40 | 0x89800 | | 466 | blk.27.attn_k_norm.weight | 0x74087740 | 0x400 | | 467 | blk.27.attn_norm.weight | 0x74087b40 | 0x2800 | | 468 | blk.27.attn_output.weight | 0x7408a340 | 0x1ea000 | | 469 | blk.27.attn_q.weight | 0x74274340 | 0x1a4000 | | 470 | blk.27.attn_q_norm.weight | 0x74418340 | 0x400 | | 471 | blk.27.attn_v.weight | 0x74418740 | 0x69000 | | 472 | blk.27.ffn_down.weight | 0x74481740 | 0x672000 | | 473 | blk.27.ffn_gate.weight | 0x74af3740 | 0x672000 | | 474 | blk.27.ffn_norm.weight | 0x75165740 | 0x2800 | | 475 | blk.27.ffn_up.weight | 0x75167f40 | 0x834000 | | 476 | blk.27.inp_gate.weight | 0x7599bf40 | 0x23000 | | 477 | blk.27.layer_output_scale.weight | 0x759bef40 | 0x4 | | 478 | blk.27.post_attention_norm.weight | 0x759bef60 | 0x2800 | | 479 | blk.27.post_ffw_norm.weight | 0x759c1760 | 0x2800 | | 480 | blk.27.post_norm.weight | 0x759c3f60 | 0x2800 | | 481 | blk.27.proj.weight | 0x759c6760 | 0x5a000 | | 482 | blk.28.attn_k.weight | 0x75a20760 | 0x89800 | | 483 | blk.28.attn_k_norm.weight | 0x75aa9f60 | 0x400 | | 484 | blk.28.attn_norm.weight | 0x75aaa360 | 0x2800 | | 485 | blk.28.attn_output.weight | 0x75aacb60 | 0x1ea000 | | 486 | blk.28.attn_q.weight | 0x75c96b60 | 0x1a4000 | | 487 | blk.28.attn_q_norm.weight | 0x75e3ab60 | 0x400 | | 488 | blk.28.attn_v.weight | 0x75e3af60 | 0x69000 | | 489 | blk.28.ffn_down.weight | 0x75ea3f60 | 0x672000 | | 490 | blk.28.ffn_gate.weight | 0x76515f60 | 0x672000 | | 491 | blk.28.ffn_norm.weight | 0x76b87f60 | 0x2800 | | 492 | blk.28.ffn_up.weight | 0x76b8a760 | 0x672000 | | 493 | blk.28.inp_gate.weight | 0x771fc760 | 0x23000 | | 494 | blk.28.layer_output_scale.weight | 0x7721f760 | 0x4 | | 495 | blk.28.post_attention_norm.weight | 0x7721f780 | 0x2800 | | 496 | blk.28.post_ffw_norm.weight | 0x77221f80 | 0x2800 | | 497 | blk.28.post_norm.weight | 0x77224780 | 0x2800 | | 498 | blk.28.proj.weight | 0x77226f80 | 0x5a000 | | 499 | blk.29.attn_k.weight | 0x77280f80 | 0x113000 | | 500 | blk.29.attn_k_norm.weight | 0x77393f80 | 0x800 | | 501 | blk.29.attn_norm.weight | 0x77394780 | 0x2800 | | 502 | blk.29.attn_output.weight | 0x77396f80 | 0x348000 | | 503 | blk.29.attn_q.weight | 0x776def80 | 0x348000 | | 504 | blk.29.attn_q_norm.weight | 0x77a26f80 | 0x800 | | 505 | blk.29.attn_v.weight | 0x77a27780 | 0xd2000 | | 506 | blk.29.ffn_down.weight | 0x77af9780 | 0x672000 | | 507 | blk.29.ffn_gate.weight | 0x7816b780 | 0x672000 | | 508 | blk.29.ffn_norm.weight | 0x787dd780 | 0x2800 | | 509 | blk.29.ffn_up.weight | 0x787dff80 | 0x834000 | | 510 | blk.29.inp_gate.weight | 0x79013f80 | 0x29400 | | 511 | blk.29.layer_output_scale.weight | 0x7903d380 | 0x4 | | 512 | blk.29.post_attention_norm.weight | 0x7903d3a0 | 0x2800 | | 513 | blk.29.post_ffw_norm.weight | 0x7903fba0 | 0x2800 | | 514 | blk.29.post_norm.weight | 0x790423a0 | 0x2800 | | 515 | blk.29.proj.weight | 0x79044ba0 | 0x5a000 | | 516 | blk.30.attn_k.weight | 0x7909eba0 | 0x89800 | | 517 | blk.30.attn_k_norm.weight | 0x791283a0 | 0x400 | | 518 | blk.30.attn_norm.weight | 0x791287a0 | 0x2800 | | 519 | blk.30.attn_output.weight | 0x7912afa0 | 0x1ea000 | | 520 | blk.30.attn_q.weight | 0x79314fa0 | 0x1ea000 | | 521 | blk.30.attn_q_norm.weight | 0x794fefa0 | 0x400 | | 522 | blk.30.attn_v.weight | 0x794ff3a0 | 0x69000 | | 523 | blk.30.ffn_down.weight | 0x795683a0 | 0x73a000 | | 524 | blk.30.ffn_gate.weight | 0x79ca23a0 | 0x672000 | | 525 | blk.30.ffn_norm.weight | 0x7a3143a0 | 0x2800 | | 526 | blk.30.ffn_up.weight | 0x7a316ba0 | 0x672000 | | 527 | blk.30.inp_gate.weight | 0x7a988ba0 | 0x29400 | | 528 | blk.30.layer_output_scale.weight | 0x7a9b1fa0 | 0x4 | | 529 | blk.30.post_attention_norm.weight | 0x7a9b1fc0 | 0x2800 | | 530 | blk.30.post_ffw_norm.weight | 0x7a9b47c0 | 0x2800 | | 531 | blk.30.post_norm.weight | 0x7a9b6fc0 | 0x2800 | | 532 | blk.30.proj.weight | 0x7a9b97c0 | 0x5a000 | | 533 | blk.31.attn_k.weight | 0x7aa137c0 | 0x89800 | | 534 | blk.31.attn_k_norm.weight | 0x7aa9cfc0 | 0x400 | | 535 | blk.31.attn_norm.weight | 0x7aa9d3c0 | 0x2800 | | 536 | blk.31.attn_output.weight | 0x7aa9fbc0 | 0x1ea000 | | 537 | blk.31.attn_q.weight | 0x7ac89bc0 | 0x1ea000 | | 538 | blk.31.attn_q_norm.weight | 0x7ae73bc0 | 0x400 | | 539 | blk.31.attn_v.weight | 0x7ae73fc0 | 0x69000 | | 540 | blk.31.ffn_down.weight | 0x7aedcfc0 | 0x834000 | | 541 | blk.31.ffn_gate.weight | 0x7b710fc0 | 0x672000 | | 542 | blk.31.ffn_norm.weight | 0x7bd82fc0 | 0x2800 | | 543 | blk.31.ffn_up.weight | 0x7bd857c0 | 0x672000 | | 544 | blk.31.inp_gate.weight | 0x7c3f77c0 | 0x29400 | | 545 | blk.31.layer_output_scale.weight | 0x7c420bc0 | 0x4 | | 546 | blk.31.post_attention_norm.weight | 0x7c420be0 | 0x2800 | | 547 | blk.31.post_ffw_norm.weight | 0x7c4233e0 | 0x2800 | | 548 | blk.31.post_norm.weight | 0x7c425be0 | 0x2800 | | 549 | blk.31.proj.weight | 0x7c4283e0 | 0x64000 | | 550 | blk.32.attn_k.weight | 0x7c48c3e0 | 0x89800 | | 551 | blk.32.attn_k_norm.weight | 0x7c515be0 | 0x400 | | 552 | blk.32.attn_norm.weight | 0x7c515fe0 | 0x2800 | | 553 | blk.32.attn_output.weight | 0x7c5187e0 | 0x1ea000 | | 554 | blk.32.attn_q.weight | 0x7c7027e0 | 0x172000 | | 555 | blk.32.attn_q_norm.weight | 0x7c8747e0 | 0x400 | | 556 | blk.32.attn_v.weight | 0x7c874be0 | 0x69000 | | 557 | blk.32.ffn_down.weight | 0x7c8ddbe0 | 0x834000 | | 558 | blk.32.ffn_gate.weight | 0x7d111be0 | 0x578000 | | 559 | blk.32.ffn_norm.weight | 0x7d689be0 | 0x2800 | | 560 | blk.32.ffn_up.weight | 0x7d68c3e0 | 0x672000 | | 561 | blk.32.inp_gate.weight | 0x7dcfe3e0 | 0x29400 | | 562 | blk.32.layer_output_scale.weight | 0x7dd277e0 | 0x4 | | 563 | blk.32.post_attention_norm.weight | 0x7dd27800 | 0x2800 | | 564 | blk.32.post_ffw_norm.weight | 0x7dd2a000 | 0x2800 | | 565 | blk.32.post_norm.weight | 0x7dd2c800 | 0x2800 | | 566 | blk.32.proj.weight | 0x7dd2f000 | 0x64000 | | 567 | blk.33.attn_k.weight | 0x7dd93000 | 0x89800 | | 568 | blk.33.attn_k_norm.weight | 0x7de1c800 | 0x400 | | 569 | blk.33.attn_norm.weight | 0x7de1cc00 | 0x2800 | | 570 | blk.33.attn_output.weight | 0x7de1f400 | 0x1ea000 | | 571 | blk.33.attn_q.weight | 0x7e009400 | 0x172000 | | 572 | blk.33.attn_q_norm.weight | 0x7e17b400 | 0x400 | | 573 | blk.33.attn_v.weight | 0x7e17b800 | 0x69000 | | 574 | blk.33.ffn_down.weight | 0x7e1e4800 | 0x834000 | | 575 | blk.33.ffn_gate.weight | 0x7ea18800 | 0x578000 | | 576 | blk.33.ffn_norm.weight | 0x7ef90800 | 0x2800 | | 577 | blk.33.ffn_up.weight | 0x7ef93000 | 0x672000 | | 578 | blk.33.inp_gate.weight | 0x7f605000 | 0x29400 | | 579 | blk.33.layer_output_scale.weight | 0x7f62e400 | 0x4 | | 580 | blk.33.post_attention_norm.weight | 0x7f62e420 | 0x2800 | | 581 | blk.33.post_ffw_norm.weight | 0x7f630c20 | 0x2800 | | 582 | blk.33.post_norm.weight | 0x7f633420 | 0x2800 | | 583 | blk.33.proj.weight | 0x7f635c20 | 0x64000 | | 584 | blk.34.attn_k.weight | 0x7f699c20 | 0x89800 | | 585 | blk.34.attn_k_norm.weight | 0x7f723420 | 0x400 | | 586 | blk.34.attn_norm.weight | 0x7f723820 | 0x2800 | | 587 | blk.34.attn_output.weight | 0x7f726020 | 0x1ea000 | | 588 | blk.34.attn_q.weight | 0x7f910020 | 0x1a4000 | | 589 | blk.34.attn_q_norm.weight | 0x7fab4020 | 0x400 | | 590 | blk.34.attn_v.weight | 0x7fab4420 | 0x69000 | | 591 | blk.34.ffn_down.weight | 0x7fb1d420 | 0x834000 | | 592 | blk.34.ffn_gate.weight | 0x80351420 | 0x672000 | | 593 | blk.34.ffn_norm.weight | 0x809c3420 | 0x2800 | | 594 | blk.34.ffn_up.weight | 0x809c5c20 | 0x672000 | | 595 | blk.34.inp_gate.weight | 0x81037c20 | 0x29400 | | 596 | blk.34.layer_output_scale.weight | 0x81061020 | 0x4 | | 597 | blk.34.post_attention_norm.weight | 0x81061040 | 0x2800 | | 598 | blk.34.post_ffw_norm.weight | 0x81063840 | 0x2800 | | 599 | blk.34.post_norm.weight | 0x81066040 | 0x2800 | | 600 | blk.34.proj.weight | 0x81068840 | 0x34800 | | 601 | blk.35.attn_k.weight | 0x8109d040 | 0x113000 | | 602 | blk.35.attn_k_norm.weight | 0x811b0040 | 0x800 | | 603 | blk.35.attn_norm.weight | 0x811b0840 | 0x2800 | | 604 | blk.35.attn_output.weight | 0x811b3040 | 0x348000 | | 605 | blk.35.attn_q.weight | 0x814fb040 | 0x348000 | | 606 | blk.35.attn_q_norm.weight | 0x81843040 | 0x800 | | 607 | blk.35.attn_v.weight | 0x81843840 | 0xd2000 | | 608 | blk.35.ffn_down.weight | 0x81915840 | 0x834000 | | 609 | blk.35.ffn_gate.weight | 0x82149840 | 0x672000 | | 610 | blk.35.ffn_norm.weight | 0x827bb840 | 0x2800 | | 611 | blk.35.ffn_up.weight | 0x827be040 | 0x834000 | | 612 | blk.35.inp_gate.weight | 0x82ff2040 | 0x29400 | | 613 | blk.35.layer_output_scale.weight | 0x8301b440 | 0x4 | | 614 | blk.35.post_attention_norm.weight | 0x8301b460 | 0x2800 | | 615 | blk.35.post_ffw_norm.weight | 0x8301dc60 | 0x2800 | | 616 | blk.35.post_norm.weight | 0x83020460 | 0x2800 | | 617 | blk.35.proj.weight | 0x83022c60 | 0x64000 | | 618 | blk.36.attn_k.weight | 0x83086c60 | 0x89800 | | 619 | blk.36.attn_k_norm.weight | 0x83110460 | 0x400 | | 620 | blk.36.attn_norm.weight | 0x83110860 | 0x2800 | | 621 | blk.36.attn_output.weight | 0x83113060 | 0x1a4000 | | 622 | blk.36.attn_q.weight | 0x832b7060 | 0x172000 | | 623 | blk.36.attn_q_norm.weight | 0x83429060 | 0x400 | | 624 | blk.36.attn_v.weight | 0x83429460 | 0x69000 | | 625 | blk.36.ffn_down.weight | 0x83492460 | 0x834000 | | 626 | blk.36.ffn_gate.weight | 0x83cc6460 | 0x672000 | | 627 | blk.36.ffn_norm.weight | 0x84338460 | 0x2800 | | 628 | blk.36.ffn_up.weight | 0x8433ac60 | 0x672000 | | 629 | blk.36.inp_gate.weight | 0x849acc60 | 0x29400 | | 630 | blk.36.layer_output_scale.weight | 0x849d6060 | 0x4 | | 631 | blk.36.post_attention_norm.weight | 0x849d6080 | 0x2800 | | 632 | blk.36.post_ffw_norm.weight | 0x849d8880 | 0x2800 | | 633 | blk.36.post_norm.weight | 0x849db080 | 0x2800 | | 634 | blk.36.proj.weight | 0x849dd880 | 0x34800 | | 635 | blk.37.attn_k.weight | 0x84a12080 | 0x89800 | | 636 | blk.37.attn_k_norm.weight | 0x84a9b880 | 0x400 | | 637 | blk.37.attn_norm.weight | 0x84a9bc80 | 0x2800 | | 638 | blk.37.attn_output.weight | 0x84a9e480 | 0x1ea000 | | 639 | blk.37.attn_q.weight | 0x84c88480 | 0x172000 | | 640 | blk.37.attn_q_norm.weight | 0x84dfa480 | 0x400 | | 641 | blk.37.attn_v.weight | 0x84dfa880 | 0x69000 | | 642 | blk.37.ffn_down.weight | 0x84e63880 | 0x834000 | | 643 | blk.37.ffn_gate.weight | 0x85697880 | 0x672000 | | 644 | blk.37.ffn_norm.weight | 0x85d09880 | 0x2800 | | 645 | blk.37.ffn_up.weight | 0x85d0c080 | 0x672000 | | 646 | blk.37.inp_gate.weight | 0x8637e080 | 0x29400 | | 647 | blk.37.layer_output_scale.weight | 0x863a7480 | 0x4 | | 648 | blk.37.post_attention_norm.weight | 0x863a74a0 | 0x2800 | | 649 | blk.37.post_ffw_norm.weight | 0x863a9ca0 | 0x2800 | | 650 | blk.37.post_norm.weight | 0x863ac4a0 | 0x2800 | | 651 | blk.37.proj.weight | 0x863aeca0 | 0x5a000 | | 652 | blk.38.attn_k.weight | 0x86408ca0 | 0x89800 | | 653 | blk.38.attn_k_norm.weight | 0x864924a0 | 0x400 | | 654 | blk.38.attn_norm.weight | 0x864928a0 | 0x2800 | | 655 | blk.38.attn_output.weight | 0x864950a0 | 0x1ea000 | | 656 | blk.38.attn_q.weight | 0x8667f0a0 | 0x172000 | | 657 | blk.38.attn_q_norm.weight | 0x867f10a0 | 0x400 | | 658 | blk.38.attn_v.weight | 0x867f14a0 | 0x69000 | | 659 | blk.38.ffn_down.weight | 0x8685a4a0 | 0x834000 | | 660 | blk.38.ffn_gate.weight | 0x8708e4a0 | 0x672000 | | 661 | blk.38.ffn_norm.weight | 0x877004a0 | 0x2800 | | 662 | blk.38.ffn_up.weight | 0x87702ca0 | 0x672000 | | 663 | blk.38.inp_gate.weight | 0x87d74ca0 | 0x29400 | | 664 | blk.38.layer_output_scale.weight | 0x87d9e0a0 | 0x4 | | 665 | blk.38.post_attention_norm.weight | 0x87d9e0c0 | 0x2800 | | 666 | blk.38.post_ffw_norm.weight | 0x87da08c0 | 0x2800 | | 667 | blk.38.post_norm.weight | 0x87da30c0 | 0x2800 | | 668 | blk.38.proj.weight | 0x87da58c0 | 0x5a000 | | 669 | blk.39.attn_k.weight | 0x87dff8c0 | 0x89800 | | 670 | blk.39.attn_k_norm.weight | 0x87e890c0 | 0x400 | | 671 | blk.39.attn_norm.weight | 0x87e894c0 | 0x2800 | | 672 | blk.39.attn_output.weight | 0x87e8bcc0 | 0x1ea000 | | 673 | blk.39.attn_q.weight | 0x88075cc0 | 0x172000 | | 674 | blk.39.attn_q_norm.weight | 0x881e7cc0 | 0x400 | | 675 | blk.39.attn_v.weight | 0x881e80c0 | 0x69000 | | 676 | blk.39.ffn_down.weight | 0x882510c0 | 0x834000 | | 677 | blk.39.ffn_gate.weight | 0x88a850c0 | 0x672000 | | 678 | blk.39.ffn_norm.weight | 0x890f70c0 | 0x2800 | | 679 | blk.39.ffn_up.weight | 0x890f98c0 | 0x672000 | | 680 | blk.39.inp_gate.weight | 0x8976b8c0 | 0x29400 | | 681 | blk.39.layer_output_scale.weight | 0x89794cc0 | 0x4 | | 682 | blk.39.post_attention_norm.weight | 0x89794ce0 | 0x2800 | | 683 | blk.39.post_ffw_norm.weight | 0x897974e0 | 0x2800 | | 684 | blk.39.post_norm.weight | 0x89799ce0 | 0x2800 | | 685 | blk.39.proj.weight | 0x8979c4e0 | 0x5a000 | | 686 | blk.40.attn_k.weight | 0x897f64e0 | 0x89800 | | 687 | blk.40.attn_k_norm.weight | 0x8987fce0 | 0x400 | | 688 | blk.40.attn_norm.weight | 0x898800e0 | 0x2800 | | 689 | blk.40.attn_output.weight | 0x898828e0 | 0x1ea000 | | 690 | blk.40.attn_q.weight | 0x89a6c8e0 | 0x172000 | | 691 | blk.40.attn_q_norm.weight | 0x89bde8e0 | 0x400 | | 692 | blk.40.attn_v.weight | 0x89bdece0 | 0x69000 | | 693 | blk.40.ffn_down.weight | 0x89c47ce0 | 0x672000 | | 694 | blk.40.ffn_gate.weight | 0x8a2b9ce0 | 0x834000 | | 695 | blk.40.ffn_norm.weight | 0x8aaedce0 | 0x2800 | | 696 | blk.40.ffn_up.weight | 0x8aaf04e0 | 0x834000 | | 697 | blk.40.inp_gate.weight | 0x8b3244e0 | 0x23000 | | 698 | blk.40.layer_output_scale.weight | 0x8b3474e0 | 0x4 | | 699 | blk.40.post_attention_norm.weight | 0x8b347500 | 0x2800 | | 700 | blk.40.post_ffw_norm.weight | 0x8b349d00 | 0x2800 | | 701 | blk.40.post_norm.weight | 0x8b34c500 | 0x2800 | | 702 | blk.40.proj.weight | 0x8b34ed00 | 0x64000 | | 703 | blk.41.attn_k.weight | 0x8b3b2d00 | 0x113000 | | 704 | blk.41.attn_k_norm.weight | 0x8b4c5d00 | 0x800 | | 705 | blk.41.attn_norm.weight | 0x8b4c6500 | 0x2800 | | 706 | blk.41.attn_output.weight | 0x8b4c8d00 | 0x348000 | | 707 | blk.41.attn_q.weight | 0x8b810d00 | 0x2e4000 | | 708 | blk.41.attn_q_norm.weight | 0x8baf4d00 | 0x800 | | 709 | blk.41.attn_v.weight | 0x8baf5500 | 0xd2000 | | 710 | blk.41.ffn_down.weight | 0x8bbc7500 | 0x672000 | | 711 | blk.41.ffn_gate.weight | 0x8c239500 | 0x672000 | | 712 | blk.41.ffn_norm.weight | 0x8c8ab500 | 0x2800 | | 713 | blk.41.ffn_up.weight | 0x8c8add00 | 0x672000 | | 714 | blk.41.inp_gate.weight | 0x8cf1fd00 | 0x23000 | | 715 | blk.41.layer_output_scale.weight | 0x8cf42d00 | 0x4 | | 716 | blk.41.post_attention_norm.weight | 0x8cf42d20 | 0x2800 | | 717 | blk.41.post_ffw_norm.weight | 0x8cf45520 | 0x2800 | | 718 | blk.41.post_norm.weight | 0x8cf47d20 | 0x2800 | | 719 | blk.41.proj.weight | 0x8cf4a520 | 0x5a000 | ### Base Tensor Group : ~4B Elements | T_ID | Tensor Layer Name | Human Friendly Tensor Layer Name | Elements | Shape | Type | BPW | | ---: | :-------------------------- | :------------------------------- | :----------------- | :--------------------- | :--- | ------: | | 0 | output_norm.weight | Output Normalization (W) | ( ~3K) 2560 | 2560 x 1 x 1 x 1 | F32 | 32.0000 | | 1 | per_layer_model_proj.weight | Per_Layer_Model_Proj (W) | ( ~28M) 27525120 | 2560 x 10752 x 1 x 1 | F16 | 16.0000 | | 2 | per_layer_proj_norm.weight | Per_Layer_Proj_Norm (W) | ( 256) 256 | 256 x 1 x 1 x 1 | F32 | 32.0000 | | 3 | per_layer_token_embd.weight | Per_Layer_Token_Embd (W) | ( ~3B) 2818572288 | 10752 x 262144 x 1 x 1 | Q2_K | 2.6250 | | 4 | rope_freqs.weight | Rope_Freqs (W) | ( 256) 256 | 256 x 1 x 1 x 1 | F32 | 32.0000 | | 5 | token_embd.weight | Token Embedding (W) | (~671M) 671088640 | 2560 x 262144 x 1 x 1 | Q2_K | 2.6250 | - Total elements in base: ( ~4B) 3517189120 - Percentage of total elements: 46.78% - Bits per Weight (BPW) for base: 2.7297 bits ### Block 0 Tensor Group : ~93M Elements | T_ID | Tensor Layer Name | Human Friendly Tensor Layer Name | Elements | Shape | Type | BPW | | ---: | :------------------------------- | :--------------------------------------------- | :--------------- | :-------------------- | :------ | ------: | | 6 | blk.0.attn_k.weight | Block 0 Attention Key (W) | ( ~1M) 1310720 | 2560 x 512 x 1 x 1 | Q2_K | 2.6250 | | 7 | blk.0.attn_k_norm.weight | Block 0 Attn_K_Norm (W) | ( 256) 256 | 256 x 1 x 1 x 1 | F32 | 32.0000 | | 8 | blk.0.attn_norm.weight | Block 0 Attention Normalization (W) | ( ~3K) 2560 | 2560 x 1 x 1 x 1 | F32 | 32.0000 | | 9 | blk.0.attn_output.weight | Block 0 Attention Output (W) | ( ~5M) 5242880 | 2048 x 2560 x 1 x 1 | Q2_K | 2.6250 | | 10 | blk.0.attn_q.weight | Block 0 Attention Query (W) | ( ~5M) 5242880 | 2560 x 2048 x 1 x 1 | Q2_K | 2.6250 | | 11 | blk.0.attn_q_norm.weight | Block 0 Attn_Q_Norm (W) | ( 256) 256 | 256 x 1 x 1 x 1 | F32 | 32.0000 | | 12 | blk.0.attn_v.weight | Block 0 Attention Value (W) | ( ~1M) 1310720 | 2560 x 512 x 1 x 1 | IQ2_XXS | 2.0625 | | 13 | blk.0.ffn_down.weight | Block 0 Feed-Forward Network "Down" (W) | ( ~26M) 26214400 | 10240 x 2560 x 1 x 1 | IQ1_M | 1.7500 | | 14 | blk.0.ffn_gate.weight | Block 0 Feed-Forward Network "Gate" (W) | ( ~26M) 26214400 | 2560 x 10240 x 1 x 1 | IQ1_M | 1.7500 | | 15 | blk.0.ffn_norm.weight | Block 0 Feed-Forward Network Normalization (W) | ( ~3K) 2560 | 2560 x 1 x 1 x 1 | F32 | 32.0000 | | 16 | blk.0.ffn_up.weight | Block 0 Feed-Forward Network "Up" (W) | ( ~26M) 26214400 | 2560 x 10240 x 1 x 1 | IQ2_XXS | 2.0625 | | 17 | blk.0.inp_gate.weight | Block 0 Inp_Gate (W) | (~655K) 655360 | 2560 x 256 x 1 x 1 | IQ1_M | 1.7500 | | 18 | blk.0.layer_output_scale.weight | Block 0 Layer_Output_Scale (W) | ( 1) 1 | 1 x 1 x 1 x 1 | F32 | 32.0000 | | 19 | blk.0.post_attention_norm.weight | Block 0 Post_Attention_Norm (W) | ( ~3K) 2560 | 2560 x 1 x 1 x 1 | F32 | 32.0000 | | 20 | blk.0.post_ffw_norm.weight | Block 0 Post_Ffw_Norm (W) | ( ~3K) 2560 | 2560 x 1 x 1 x 1 | F32 | 32.0000 | | 21 | blk.0.post_norm.weight | Block 0 Post_Norm (W) | ( ~3K) 2560 | 2560 x 1 x 1 x 1 | F32 | 32.0000 | | 22 | blk.0.proj.weight | Block 0 Proj (W) | (~655K) 655360 | 256 x 2560 x 1 x 1 | Q4_K | 4.5000 | - Total elements in blk.0: (~93M) 93074433 - Percentage of total elements: 1.24% - Bits per Weight (BPW) for blk.0: 1.9770 bits ### Block 1 Tensor Group : ~93M Elements | T_ID | Tensor Layer Name | Human Friendly Tensor Layer Name | Elements | Shape | Type | BPW | | ---: | :------------------------------- | :--------------------------------------------- | :--------------- | :-------------------- | :----- | ------: | | 23 | blk.1.attn_k.weight | Block 1 Attention Key (W) | ( ~1M) 1310720 | 2560 x 512 x 1 x 1 | IQ2_XS | 2.3125 | | 24 | blk.1.attn_k_norm.weight | Block 1 Attn_K_Norm (W) | ( 256) 256 | 256 x 1 x 1 x 1 | F32 | 32.0000 | | 25 | blk.1.attn_norm.weight | Block 1 Attention Normalization (W) | ( ~3K) 2560 | 2560 x 1 x 1 x 1 | F32 | 32.0000 | | 26 | blk.1.attn_output.weight | Block 1 Attention Output (W) | ( ~5M) 5242880 | 2048 x 2560 x 1 x 1 | Q3_K | 3.4375 | | 27 | blk.1.attn_q.weight | Block 1 Attention Query (W) | ( ~5M) 5242880 | 2560 x 2048 x 1 x 1 | IQ2_XS | 2.3125 | | 28 | blk.1.attn_q_norm.weight | Block 1 Attn_Q_Norm (W) | ( 256) 256 | 256 x 1 x 1 x 1 | F32 | 32.0000 | | 29 | blk.1.attn_v.weight | Block 1 Attention Value (W) | ( ~1M) 1310720 | 2560 x 512 x 1 x 1 | Q2_K | 2.6250 | | 30 | blk.1.ffn_down.weight | Block 1 Feed-Forward Network "Down" (W) | ( ~26M) 26214400 | 10240 x 2560 x 1 x 1 | IQ2_XS | 2.3125 | | 31 | blk.1.ffn_gate.weight | Block 1 Feed-Forward Network "Gate" (W) | ( ~26M) 26214400 | 2560 x 10240 x 1 x 1 | IQ1_M | 1.7500 | | 32 | blk.1.ffn_norm.weight | Block 1 Feed-Forward Network Normalization (W) | ( ~3K) 2560 | 2560 x 1 x 1 x 1 | F32 | 32.0000 | | 33 | blk.1.ffn_up.weight | Block 1 Feed-Forward Network "Up" (W) | ( ~26M) 26214400 | 2560 x 10240 x 1 x 1 | Q2_K | 2.6250 | | 34 | blk.1.inp_gate.weight | Block 1 Inp_Gate (W) | (~655K) 655360 | 2560 x 256 x 1 x 1 | Q2_K | 2.6250 | | 35 | blk.1.layer_output_scale.weight | Block 1 Layer_Output_Scale (W) | ( 1) 1 | 1 x 1 x 1 x 1 | F32 | 32.0000 | | 36 | blk.1.post_attention_norm.weight | Block 1 Post_Attention_Norm (W) | ( ~3K) 2560 | 2560 x 1 x 1 x 1 | F32 | 32.0000 | | 37 | blk.1.post_ffw_norm.weight | Block 1 Post_Ffw_Norm (W) | ( ~3K) 2560 | 2560 x 1 x 1 x 1 | F32 | 32.0000 | | 38 | blk.1.post_norm.weight | Block 1 Post_Norm (W) | ( ~3K) 2560 | 2560 x 1 x 1 x 1 | F32 | 32.0000 | | 39 | blk.1.proj.weight | Block 1 Proj (W) | (~655K) 655360 | 256 x 2560 x 1 x 1 | Q2_K | 2.6250 | - Total elements in blk.1: (~93M) 93074433 - Percentage of total elements: 1.24% - Bits per Weight (BPW) for blk.1: 2.3185 bits ### Block 2 Tensor Group : ~93M Elements | T_ID | Tensor Layer Name | Human Friendly Tensor Layer Name | Elements | Shape | Type | BPW | | ---: | :------------------------------- | :--------------------------------------------- | :--------------- | :-------------------- | :------ | ------: | | 40 | blk.2.attn_k.weight | Block 2 Attention Key (W) | ( ~1M) 1310720 | 2560 x 512 x 1 x 1 | IQ2_XS | 2.3125 | | 41 | blk.2.attn_k_norm.weight | Block 2 Attn_K_Norm (W) | ( 256) 256 | 256 x 1 x 1 x 1 | F32 | 32.0000 | | 42 | blk.2.attn_norm.weight | Block 2 Attention Normalization (W) | ( ~3K) 2560 | 2560 x 1 x 1 x 1 | F32 | 32.0000 | | 43 | blk.2.attn_output.weight | Block 2 Attention Output (W) | ( ~5M) 5242880 | 2048 x 2560 x 1 x 1 | Q3_K | 3.4375 | | 44 | blk.2.attn_q.weight | Block 2 Attention Query (W) | ( ~5M) 5242880 | 2560 x 2048 x 1 x 1 | IQ3_XXS | 3.0625 | | 45 | blk.2.attn_q_norm.weight | Block 2 Attn_Q_Norm (W) | ( 256) 256 | 256 x 1 x 1 x 1 | F32 | 32.0000 | | 46 | blk.2.attn_v.weight | Block 2 Attention Value (W) | ( ~1M) 1310720 | 2560 x 512 x 1 x 1 | Q2_K | 2.6250 | | 47 | blk.2.ffn_down.weight | Block 2 Feed-Forward Network "Down" (W) | ( ~26M) 26214400 | 10240 x 2560 x 1 x 1 | IQ2_XS | 2.3125 | | 48 | blk.2.ffn_gate.weight | Block 2 Feed-Forward Network "Gate" (W) | ( ~26M) 26214400 | 2560 x 10240 x 1 x 1 | IQ1_M | 1.7500 | | 49 | blk.2.ffn_norm.weight | Block 2 Feed-Forward Network Normalization (W) | ( ~3K) 2560 | 2560 x 1 x 1 x 1 | F32 | 32.0000 | | 50 | blk.2.ffn_up.weight | Block 2 Feed-Forward Network "Up" (W) | ( ~26M) 26214400 | 2560 x 10240 x 1 x 1 | IQ2_XXS | 2.0625 | | 51 | blk.2.inp_gate.weight | Block 2 Inp_Gate (W) | (~655K) 655360 | 2560 x 256 x 1 x 1 | Q2_K | 2.6250 | | 52 | blk.2.layer_output_scale.weight | Block 2 Layer_Output_Scale (W) | ( 1) 1 | 1 x 1 x 1 x 1 | F32 | 32.0000 | | 53 | blk.2.post_attention_norm.weight | Block 2 Post_Attention_Norm (W) | ( ~3K) 2560 | 2560 x 1 x 1 x 1 | F32 | 32.0000 | | 54 | blk.2.post_ffw_norm.weight | Block 2 Post_Ffw_Norm (W) | ( ~3K) 2560 | 2560 x 1 x 1 x 1 | F32 | 32.0000 | | 55 | blk.2.post_norm.weight | Block 2 Post_Norm (W) | ( ~3K) 2560 | 2560 x 1 x 1 x 1 | F32 | 32.0000 | | 56 | blk.2.proj.weight | Block 2 Proj (W) | (~655K) 655360 | 256 x 2560 x 1 x 1 | Q2_K | 2.6250 | - Total elements in blk.2: (~93M) 93074433 - Percentage of total elements: 1.24% - Bits per Weight (BPW) for blk.2: 2.2023 bits ### Block 3 Tensor Group : ~93M Elements | T_ID | Tensor Layer Name | Human Friendly Tensor Layer Name | Elements | Shape | Type | BPW | | ---: | :------------------------------- | :--------------------------------------------- | :--------------- | :-------------------- | :------ | ------: | | 57 | blk.3.attn_k.weight | Block 3 Attention Key (W) | ( ~1M) 1310720 | 2560 x 512 x 1 x 1 | IQ2_XS | 2.3125 | | 58 | blk.3.attn_k_norm.weight | Block 3 Attn_K_Norm (W) | ( 256) 256 | 256 x 1 x 1 x 1 | F32 | 32.0000 | | 59 | blk.3.attn_norm.weight | Block 3 Attention Normalization (W) | ( ~3K) 2560 | 2560 x 1 x 1 x 1 | F32 | 32.0000 | | 60 | blk.3.attn_output.weight | Block 3 Attention Output (W) | ( ~5M) 5242880 | 2048 x 2560 x 1 x 1 | Q3_K | 3.4375 | | 61 | blk.3.attn_q.weight | Block 3 Attention Query (W) | ( ~5M) 5242880 | 2560 x 2048 x 1 x 1 | IQ2_XS | 2.3125 | | 62 | blk.3.attn_q_norm.weight | Block 3 Attn_Q_Norm (W) | ( 256) 256 | 256 x 1 x 1 x 1 | F32 | 32.0000 | | 63 | blk.3.attn_v.weight | Block 3 Attention Value (W) | ( ~1M) 1310720 | 2560 x 512 x 1 x 1 | Q2_K | 2.6250 | | 64 | blk.3.ffn_down.weight | Block 3 Feed-Forward Network "Down" (W) | ( ~26M) 26214400 | 10240 x 2560 x 1 x 1 | IQ2_XXS | 2.0625 | | 65 | blk.3.ffn_gate.weight | Block 3 Feed-Forward Network "Gate" (W) | ( ~26M) 26214400 | 2560 x 10240 x 1 x 1 | IQ1_M | 1.7500 | | 66 | blk.3.ffn_norm.weight | Block 3 Feed-Forward Network Normalization (W) | ( ~3K) 2560 | 2560 x 1 x 1 x 1 | F32 | 32.0000 | | 67 | blk.3.ffn_up.weight | Block 3 Feed-Forward Network "Up" (W) | ( ~26M) 26214400 | 2560 x 10240 x 1 x 1 | Q2_K | 2.6250 | | 68 | blk.3.inp_gate.weight | Block 3 Inp_Gate (W) | (~655K) 655360 | 2560 x 256 x 1 x 1 | IQ1_M | 1.7500 | | 69 | blk.3.layer_output_scale.weight | Block 3 Layer_Output_Scale (W) | ( 1) 1 | 1 x 1 x 1 x 1 | F32 | 32.0000 | | 70 | blk.3.post_attention_norm.weight | Block 3 Post_Attention_Norm (W) | ( ~3K) 2560 | 2560 x 1 x 1 x 1 | F32 | 32.0000 | | 71 | blk.3.post_ffw_norm.weight | Block 3 Post_Ffw_Norm (W) | ( ~3K) 2560 | 2560 x 1 x 1 x 1 | F32 | 32.0000 | | 72 | blk.3.post_norm.weight | Block 3 Post_Norm (W) | ( ~3K) 2560 | 2560 x 1 x 1 x 1 | F32 | 32.0000 | | 73 | blk.3.proj.weight | Block 3 Proj (W) | (~655K) 655360 | 256 x 2560 x 1 x 1 | Q2_K | 2.6250 | - Total elements in blk.3: (~93M) 93074433 - Percentage of total elements: 1.24% - Bits per Weight (BPW) for blk.3: 2.2419 bits ### Block 4 Tensor Group : ~93M Elements | T_ID | Tensor Layer Name | Human Friendly Tensor Layer Name | Elements | Shape | Type | BPW | | ---: | :------------------------------- | :--------------------------------------------- | :--------------- | :-------------------- | :------ | ------: | | 74 | blk.4.attn_k.weight | Block 4 Attention Key (W) | ( ~1M) 1310720 | 2560 x 512 x 1 x 1 | IQ2_XS | 2.3125 | | 75 | blk.4.attn_k_norm.weight | Block 4 Attn_K_Norm (W) | ( 256) 256 | 256 x 1 x 1 x 1 | F32 | 32.0000 | | 76 | blk.4.attn_norm.weight | Block 4 Attention Normalization (W) | ( ~3K) 2560 | 2560 x 1 x 1 x 1 | F32 | 32.0000 | | 77 | blk.4.attn_output.weight | Block 4 Attention Output (W) | ( ~5M) 5242880 | 2048 x 2560 x 1 x 1 | Q3_K | 3.4375 | | 78 | blk.4.attn_q.weight | Block 4 Attention Query (W) | ( ~5M) 5242880 | 2560 x 2048 x 1 x 1 | IQ2_XS | 2.3125 | | 79 | blk.4.attn_q_norm.weight | Block 4 Attn_Q_Norm (W) | ( 256) 256 | 256 x 1 x 1 x 1 | F32 | 32.0000 | | 80 | blk.4.attn_v.weight | Block 4 Attention Value (W) | ( ~1M) 1310720 | 2560 x 512 x 1 x 1 | IQ2_XXS | 2.0625 | | 81 | blk.4.ffn_down.weight | Block 4 Feed-Forward Network "Down" (W) | ( ~26M) 26214400 | 10240 x 2560 x 1 x 1 | IQ2_XXS | 2.0625 | | 82 | blk.4.ffn_gate.weight | Block 4 Feed-Forward Network "Gate" (W) | ( ~26M) 26214400 | 2560 x 10240 x 1 x 1 | IQ1_M | 1.7500 | | 83 | blk.4.ffn_norm.weight | Block 4 Feed-Forward Network Normalization (W) | ( ~3K) 2560 | 2560 x 1 x 1 x 1 | F32 | 32.0000 | | 84 | blk.4.ffn_up.weight | Block 4 Feed-Forward Network "Up" (W) | ( ~26M) 26214400 | 2560 x 10240 x 1 x 1 | IQ2_XXS | 2.0625 | | 85 | blk.4.inp_gate.weight | Block 4 Inp_Gate (W) | (~655K) 655360 | 2560 x 256 x 1 x 1 | IQ1_M | 1.7500 | | 86 | blk.4.layer_output_scale.weight | Block 4 Layer_Output_Scale (W) | ( 1) 1 | 1 x 1 x 1 x 1 | F32 | 32.0000 | | 87 | blk.4.post_attention_norm.weight | Block 4 Post_Attention_Norm (W) | ( ~3K) 2560 | 2560 x 1 x 1 x 1 | F32 | 32.0000 | | 88 | blk.4.post_ffw_norm.weight | Block 4 Post_Ffw_Norm (W) | ( ~3K) 2560 | 2560 x 1 x 1 x 1 | F32 | 32.0000 | | 89 | blk.4.post_norm.weight | Block 4 Post_Norm (W) | ( ~3K) 2560 | 2560 x 1 x 1 x 1 | F32 | 32.0000 | | 90 | blk.4.proj.weight | Block 4 Proj (W) | (~655K) 655360 | 256 x 2560 x 1 x 1 | Q2_K | 2.6250 | - Total elements in blk.4: (~93M) 93074433 - Percentage of total elements: 1.24% - Bits per Weight (BPW) for blk.4: 2.0756 bits ### Block 5 Tensor Group : ~106M Elements | T_ID | Tensor Layer Name | Human Friendly Tensor Layer Name | Elements | Shape | Type | BPW | | ---: | :------------------------------- | :--------------------------------------------- | :--------------- | :-------------------- | :------ | ------: | | 91 | blk.5.attn_k.weight | Block 5 Attention Key (W) | ( ~3M) 2621440 | 2560 x 1024 x 1 x 1 | IQ2_XS | 2.3125 | | 92 | blk.5.attn_k_norm.weight | Block 5 Attn_K_Norm (W) | ( 512) 512 | 512 x 1 x 1 x 1 | F32 | 32.0000 | | 93 | blk.5.attn_norm.weight | Block 5 Attention Normalization (W) | ( ~3K) 2560 | 2560 x 1 x 1 x 1 | F32 | 32.0000 | | 94 | blk.5.attn_output.weight | Block 5 Attention Output (W) | ( ~10M) 10485760 | 4096 x 2560 x 1 x 1 | Q2_K | 2.6250 | | 95 | blk.5.attn_q.weight | Block 5 Attention Query (W) | ( ~10M) 10485760 | 2560 x 4096 x 1 x 1 | IQ2_XS | 2.3125 | | 96 | blk.5.attn_q_norm.weight | Block 5 Attn_Q_Norm (W) | ( 512) 512 | 512 x 1 x 1 x 1 | F32 | 32.0000 | | 97 | blk.5.attn_v.weight | Block 5 Attention Value (W) | ( ~3M) 2621440 | 2560 x 1024 x 1 x 1 | IQ2_XXS | 2.0625 | | 98 | blk.5.ffn_down.weight | Block 5 Feed-Forward Network "Down" (W) | ( ~26M) 26214400 | 10240 x 2560 x 1 x 1 | IQ2_XS | 2.3125 | | 99 | blk.5.ffn_gate.weight | Block 5 Feed-Forward Network "Gate" (W) | ( ~26M) 26214400 | 2560 x 10240 x 1 x 1 | IQ1_M | 1.7500 | | 100 | blk.5.ffn_norm.weight | Block 5 Feed-Forward Network Normalization (W) | ( ~3K) 2560 | 2560 x 1 x 1 x 1 | F32 | 32.0000 | | 101 | blk.5.ffn_up.weight | Block 5 Feed-Forward Network "Up" (W) | ( ~26M) 26214400 | 2560 x 10240 x 1 x 1 | Q2_K | 2.6250 | | 102 | blk.5.inp_gate.weight | Block 5 Inp_Gate (W) | (~655K) 655360 | 2560 x 256 x 1 x 1 | Q2_K | 2.6250 | | 103 | blk.5.layer_output_scale.weight | Block 5 Layer_Output_Scale (W) | ( 1) 1 | 1 x 1 x 1 x 1 | F32 | 32.0000 | | 104 | blk.5.post_attention_norm.weight | Block 5 Post_Attention_Norm (W) | ( ~3K) 2560 | 2560 x 1 x 1 x 1 | F32 | 32.0000 | | 105 | blk.5.post_ffw_norm.weight | Block 5 Post_Ffw_Norm (W) | ( ~3K) 2560 | 2560 x 1 x 1 x 1 | F32 | 32.0000 | | 106 | blk.5.post_norm.weight | Block 5 Post_Norm (W) | ( ~3K) 2560 | 2560 x 1 x 1 x 1 | F32 | 32.0000 | | 107 | blk.5.proj.weight | Block 5 Proj (W) | (~655K) 655360 | 256 x 2560 x 1 x 1 | Q2_K | 2.6250 | - Total elements in blk.5: (~106M) 106182145 - Percentage of total elements: 1.41% - Bits per Weight (BPW) for blk.5: 2.2832 bits ### Block 6 Tensor Group : ~93M Elements | T_ID | Tensor Layer Name | Human Friendly Tensor Layer Name | Elements | Shape | Type | BPW | | ---: | :------------------------------- | :--------------------------------------------- | :--------------- | :-------------------- | :------ | ------: | | 108 | blk.6.attn_k.weight | Block 6 Attention Key (W) | ( ~1M) 1310720 | 2560 x 512 x 1 x 1 | Q2_K | 2.6250 | | 109 | blk.6.attn_k_norm.weight | Block 6 Attn_K_Norm (W) | ( 256) 256 | 256 x 1 x 1 x 1 | F32 | 32.0000 | | 110 | blk.6.attn_norm.weight | Block 6 Attention Normalization (W) | ( ~3K) 2560 | 2560 x 1 x 1 x 1 | F32 | 32.0000 | | 111 | blk.6.attn_output.weight | Block 6 Attention Output (W) | ( ~5M) 5242880 | 2048 x 2560 x 1 x 1 | IQ3_XXS | 3.0625 | | 112 | blk.6.attn_q.weight | Block 6 Attention Query (W) | ( ~5M) 5242880 | 2560 x 2048 x 1 x 1 | Q2_K | 2.6250 | | 113 | blk.6.attn_q_norm.weight | Block 6 Attn_Q_Norm (W) | ( 256) 256 | 256 x 1 x 1 x 1 | F32 | 32.0000 | | 114 | blk.6.attn_v.weight | Block 6 Attention Value (W) | ( ~1M) 1310720 | 2560 x 512 x 1 x 1 | Q2_K | 2.6250 | | 115 | blk.6.ffn_down.weight | Block 6 Feed-Forward Network "Down" (W) | ( ~26M) 26214400 | 10240 x 2560 x 1 x 1 | IQ2_XXS | 2.0625 | | 116 | blk.6.ffn_gate.weight | Block 6 Feed-Forward Network "Gate" (W) | ( ~26M) 26214400 | 2560 x 10240 x 1 x 1 | IQ1_M | 1.7500 | | 117 | blk.6.ffn_norm.weight | Block 6 Feed-Forward Network Normalization (W) | ( ~3K) 2560 | 2560 x 1 x 1 x 1 | F32 | 32.0000 | | 118 | blk.6.ffn_up.weight | Block 6 Feed-Forward Network "Up" (W) | ( ~26M) 26214400 | 2560 x 10240 x 1 x 1 | Q2_K | 2.6250 | | 119 | blk.6.inp_gate.weight | Block 6 Inp_Gate (W) | (~655K) 655360 | 2560 x 256 x 1 x 1 | Q2_K | 2.6250 | | 120 | blk.6.layer_output_scale.weight | Block 6 Layer_Output_Scale (W) | ( 1) 1 | 1 x 1 x 1 x 1 | F32 | 32.0000 | | 121 | blk.6.post_attention_norm.weight | Block 6 Post_Attention_Norm (W) | ( ~3K) 2560 | 2560 x 1 x 1 x 1 | F32 | 32.0000 | | 122 | blk.6.post_ffw_norm.weight | Block 6 Post_Ffw_Norm (W) | ( ~3K) 2560 | 2560 x 1 x 1 x 1 | F32 | 32.0000 | | 123 | blk.6.post_norm.weight | Block 6 Post_Norm (W) | ( ~3K) 2560 | 2560 x 1 x 1 x 1 | F32 | 32.0000 | | 124 | blk.6.proj.weight | Block 6 Proj (W) | (~655K) 655360 | 256 x 2560 x 1 x 1 | Q2_K | 2.6250 | - Total elements in blk.6: (~93M) 93074433 - Percentage of total elements: 1.24% - Bits per Weight (BPW) for blk.6: 2.2490 bits ### Block 7 Tensor Group : ~93M Elements | T_ID | Tensor Layer Name | Human Friendly Tensor Layer Name | Elements | Shape | Type | BPW | | ---: | :------------------------------- | :--------------------------------------------- | :--------------- | :-------------------- | :------ | ------: | | 125 | blk.7.attn_k.weight | Block 7 Attention Key (W) | ( ~1M) 1310720 | 2560 x 512 x 1 x 1 | IQ2_XS | 2.3125 | | 126 | blk.7.attn_k_norm.weight | Block 7 Attn_K_Norm (W) | ( 256) 256 | 256 x 1 x 1 x 1 | F32 | 32.0000 | | 127 | blk.7.attn_norm.weight | Block 7 Attention Normalization (W) | ( ~3K) 2560 | 2560 x 1 x 1 x 1 | F32 | 32.0000 | | 128 | blk.7.attn_output.weight | Block 7 Attention Output (W) | ( ~5M) 5242880 | 2048 x 2560 x 1 x 1 | Q3_K | 3.4375 | | 129 | blk.7.attn_q.weight | Block 7 Attention Query (W) | ( ~5M) 5242880 | 2560 x 2048 x 1 x 1 | IQ2_XS | 2.3125 | | 130 | blk.7.attn_q_norm.weight | Block 7 Attn_Q_Norm (W) | ( 256) 256 | 256 x 1 x 1 x 1 | F32 | 32.0000 | | 131 | blk.7.attn_v.weight | Block 7 Attention Value (W) | ( ~1M) 1310720 | 2560 x 512 x 1 x 1 | IQ2_XXS | 2.0625 | | 132 | blk.7.ffn_down.weight | Block 7 Feed-Forward Network "Down" (W) | ( ~26M) 26214400 | 10240 x 2560 x 1 x 1 | IQ2_XXS | 2.0625 | | 133 | blk.7.ffn_gate.weight | Block 7 Feed-Forward Network "Gate" (W) | ( ~26M) 26214400 | 2560 x 10240 x 1 x 1 | IQ1_M | 1.7500 | | 134 | blk.7.ffn_norm.weight | Block 7 Feed-Forward Network Normalization (W) | ( ~3K) 2560 | 2560 x 1 x 1 x 1 | F32 | 32.0000 | | 135 | blk.7.ffn_up.weight | Block 7 Feed-Forward Network "Up" (W) | ( ~26M) 26214400 | 2560 x 10240 x 1 x 1 | IQ2_XXS | 2.0625 | | 136 | blk.7.inp_gate.weight | Block 7 Inp_Gate (W) | (~655K) 655360 | 2560 x 256 x 1 x 1 | IQ1_M | 1.7500 | | 137 | blk.7.layer_output_scale.weight | Block 7 Layer_Output_Scale (W) | ( 1) 1 | 1 x 1 x 1 x 1 | F32 | 32.0000 | | 138 | blk.7.post_attention_norm.weight | Block 7 Post_Attention_Norm (W) | ( ~3K) 2560 | 2560 x 1 x 1 x 1 | F32 | 32.0000 | | 139 | blk.7.post_ffw_norm.weight | Block 7 Post_Ffw_Norm (W) | ( ~3K) 2560 | 2560 x 1 x 1 x 1 | F32 | 32.0000 | | 140 | blk.7.post_norm.weight | Block 7 Post_Norm (W) | ( ~3K) 2560 | 2560 x 1 x 1 x 1 | F32 | 32.0000 | | 141 | blk.7.proj.weight | Block 7 Proj (W) | (~655K) 655360 | 256 x 2560 x 1 x 1 | Q2_K | 2.6250 | - Total elements in blk.7: (~93M) 93074433 - Percentage of total elements: 1.24% - Bits per Weight (BPW) for blk.7: 2.0756 bits ### Block 8 Tensor Group : ~93M Elements | T_ID | Tensor Layer Name | Human Friendly Tensor Layer Name | Elements | Shape | Type | BPW | | ---: | :------------------------------- | :--------------------------------------------- | :--------------- | :-------------------- | :------ | ------: | | 142 | blk.8.attn_k.weight | Block 8 Attention Key (W) | ( ~1M) 1310720 | 2560 x 512 x 1 x 1 | IQ2_XS | 2.3125 | | 143 | blk.8.attn_k_norm.weight | Block 8 Attn_K_Norm (W) | ( 256) 256 | 256 x 1 x 1 x 1 | F32 | 32.0000 | | 144 | blk.8.attn_norm.weight | Block 8 Attention Normalization (W) | ( ~3K) 2560 | 2560 x 1 x 1 x 1 | F32 | 32.0000 | | 145 | blk.8.attn_output.weight | Block 8 Attention Output (W) | ( ~5M) 5242880 | 2048 x 2560 x 1 x 1 | Q3_K | 3.4375 | | 146 | blk.8.attn_q.weight | Block 8 Attention Query (W) | ( ~5M) 5242880 | 2560 x 2048 x 1 x 1 | IQ2_XS | 2.3125 | | 147 | blk.8.attn_q_norm.weight | Block 8 Attn_Q_Norm (W) | ( 256) 256 | 256 x 1 x 1 x 1 | F32 | 32.0000 | | 148 | blk.8.attn_v.weight | Block 8 Attention Value (W) | ( ~1M) 1310720 | 2560 x 512 x 1 x 1 | IQ2_XXS | 2.0625 | | 149 | blk.8.ffn_down.weight | Block 8 Feed-Forward Network "Down" (W) | ( ~26M) 26214400 | 10240 x 2560 x 1 x 1 | IQ2_XXS | 2.0625 | | 150 | blk.8.ffn_gate.weight | Block 8 Feed-Forward Network "Gate" (W) | ( ~26M) 26214400 | 2560 x 10240 x 1 x 1 | IQ2_XXS | 2.0625 | | 151 | blk.8.ffn_norm.weight | Block 8 Feed-Forward Network Normalization (W) | ( ~3K) 2560 | 2560 x 1 x 1 x 1 | F32 | 32.0000 | | 152 | blk.8.ffn_up.weight | Block 8 Feed-Forward Network "Up" (W) | ( ~26M) 26214400 | 2560 x 10240 x 1 x 1 | IQ2_XXS | 2.0625 | | 153 | blk.8.inp_gate.weight | Block 8 Inp_Gate (W) | (~655K) 655360 | 2560 x 256 x 1 x 1 | IQ1_M | 1.7500 | | 154 | blk.8.layer_output_scale.weight | Block 8 Layer_Output_Scale (W) | ( 1) 1 | 1 x 1 x 1 x 1 | F32 | 32.0000 | | 155 | blk.8.post_attention_norm.weight | Block 8 Post_Attention_Norm (W) | ( ~3K) 2560 | 2560 x 1 x 1 x 1 | F32 | 32.0000 | | 156 | blk.8.post_ffw_norm.weight | Block 8 Post_Ffw_Norm (W) | ( ~3K) 2560 | 2560 x 1 x 1 x 1 | F32 | 32.0000 | | 157 | blk.8.post_norm.weight | Block 8 Post_Norm (W) | ( ~3K) 2560 | 2560 x 1 x 1 x 1 | F32 | 32.0000 | | 158 | blk.8.proj.weight | Block 8 Proj (W) | (~655K) 655360 | 256 x 2560 x 1 x 1 | Q2_K | 2.6250 | - Total elements in blk.8: (~93M) 93074433 - Percentage of total elements: 1.24% - Bits per Weight (BPW) for blk.8: 2.1636 bits ### Block 9 Tensor Group : ~93M Elements | T_ID | Tensor Layer Name | Human Friendly Tensor Layer Name | Elements | Shape | Type | BPW | | ---: | :------------------------------- | :--------------------------------------------- | :--------------- | :-------------------- | :------ | ------: | | 159 | blk.9.attn_k.weight | Block 9 Attention Key (W) | ( ~1M) 1310720 | 2560 x 512 x 1 x 1 | IQ2_XS | 2.3125 | | 160 | blk.9.attn_k_norm.weight | Block 9 Attn_K_Norm (W) | ( 256) 256 | 256 x 1 x 1 x 1 | F32 | 32.0000 | | 161 | blk.9.attn_norm.weight | Block 9 Attention Normalization (W) | ( ~3K) 2560 | 2560 x 1 x 1 x 1 | F32 | 32.0000 | | 162 | blk.9.attn_output.weight | Block 9 Attention Output (W) | ( ~5M) 5242880 | 2048 x 2560 x 1 x 1 | Q3_K | 3.4375 | | 163 | blk.9.attn_q.weight | Block 9 Attention Query (W) | ( ~5M) 5242880 | 2560 x 2048 x 1 x 1 | IQ2_XS | 2.3125 | | 164 | blk.9.attn_q_norm.weight | Block 9 Attn_Q_Norm (W) | ( 256) 256 | 256 x 1 x 1 x 1 | F32 | 32.0000 | | 165 | blk.9.attn_v.weight | Block 9 Attention Value (W) | ( ~1M) 1310720 | 2560 x 512 x 1 x 1 | IQ2_XXS | 2.0625 | | 166 | blk.9.ffn_down.weight | Block 9 Feed-Forward Network "Down" (W) | ( ~26M) 26214400 | 10240 x 2560 x 1 x 1 | IQ2_XXS | 2.0625 | | 167 | blk.9.ffn_gate.weight | Block 9 Feed-Forward Network "Gate" (W) | ( ~26M) 26214400 | 2560 x 10240 x 1 x 1 | IQ2_XXS | 2.0625 | | 168 | blk.9.ffn_norm.weight | Block 9 Feed-Forward Network Normalization (W) | ( ~3K) 2560 | 2560 x 1 x 1 x 1 | F32 | 32.0000 | | 169 | blk.9.ffn_up.weight | Block 9 Feed-Forward Network "Up" (W) | ( ~26M) 26214400 | 2560 x 10240 x 1 x 1 | IQ2_XXS | 2.0625 | | 170 | blk.9.inp_gate.weight | Block 9 Inp_Gate (W) | (~655K) 655360 | 2560 x 256 x 1 x 1 | IQ1_M | 1.7500 | | 171 | blk.9.layer_output_scale.weight | Block 9 Layer_Output_Scale (W) | ( 1) 1 | 1 x 1 x 1 x 1 | F32 | 32.0000 | | 172 | blk.9.post_attention_norm.weight | Block 9 Post_Attention_Norm (W) | ( ~3K) 2560 | 2560 x 1 x 1 x 1 | F32 | 32.0000 | | 173 | blk.9.post_ffw_norm.weight | Block 9 Post_Ffw_Norm (W) | ( ~3K) 2560 | 2560 x 1 x 1 x 1 | F32 | 32.0000 | | 174 | blk.9.post_norm.weight | Block 9 Post_Norm (W) | ( ~3K) 2560 | 2560 x 1 x 1 x 1 | F32 | 32.0000 | | 175 | blk.9.proj.weight | Block 9 Proj (W) | (~655K) 655360 | 256 x 2560 x 1 x 1 | Q2_K | 2.6250 | - Total elements in blk.9: (~93M) 93074433 - Percentage of total elements: 1.24% - Bits per Weight (BPW) for blk.9: 2.1636 bits ### Block 10 Tensor Group : ~93M Elements | T_ID | Tensor Layer Name | Human Friendly Tensor Layer Name | Elements | Shape | Type | BPW | | ---: | :-------------------------------- | :---------------------------------------------- | :--------------- | :-------------------- | :------ | ------: | | 176 | blk.10.attn_k.weight | Block 10 Attention Key (W) | ( ~1M) 1310720 | 2560 x 512 x 1 x 1 | IQ2_XS | 2.3125 | | 177 | blk.10.attn_k_norm.weight | Block 10 Attn_K_Norm (W) | ( 256) 256 | 256 x 1 x 1 x 1 | F32 | 32.0000 | | 178 | blk.10.attn_norm.weight | Block 10 Attention Normalization (W) | ( ~3K) 2560 | 2560 x 1 x 1 x 1 | F32 | 32.0000 | | 179 | blk.10.attn_output.weight | Block 10 Attention Output (W) | ( ~5M) 5242880 | 2048 x 2560 x 1 x 1 | Q3_K | 3.4375 | | 180 | blk.10.attn_q.weight | Block 10 Attention Query (W) | ( ~5M) 5242880 | 2560 x 2048 x 1 x 1 | IQ3_XXS | 3.0625 | | 181 | blk.10.attn_q_norm.weight | Block 10 Attn_Q_Norm (W) | ( 256) 256 | 256 x 1 x 1 x 1 | F32 | 32.0000 | | 182 | blk.10.attn_v.weight | Block 10 Attention Value (W) | ( ~1M) 1310720 | 2560 x 512 x 1 x 1 | Q2_K | 2.6250 | | 183 | blk.10.ffn_down.weight | Block 10 Feed-Forward Network "Down" (W) | ( ~26M) 26214400 | 10240 x 2560 x 1 x 1 | IQ2_XXS | 2.0625 | | 184 | blk.10.ffn_gate.weight | Block 10 Feed-Forward Network "Gate" (W) | ( ~26M) 26214400 | 2560 x 10240 x 1 x 1 | IQ2_XXS | 2.0625 | | 185 | blk.10.ffn_norm.weight | Block 10 Feed-Forward Network Normalization (W) | ( ~3K) 2560 | 2560 x 1 x 1 x 1 | F32 | 32.0000 | | 186 | blk.10.ffn_up.weight | Block 10 Feed-Forward Network "Up" (W) | ( ~26M) 26214400 | 2560 x 10240 x 1 x 1 | Q2_K | 2.6250 | | 187 | blk.10.inp_gate.weight | Block 10 Inp_Gate (W) | (~655K) 655360 | 2560 x 256 x 1 x 1 | IQ1_M | 1.7500 | | 188 | blk.10.layer_output_scale.weight | Block 10 Layer_Output_Scale (W) | ( 1) 1 | 1 x 1 x 1 x 1 | F32 | 32.0000 | | 189 | blk.10.post_attention_norm.weight | Block 10 Post_Attention_Norm (W) | ( ~3K) 2560 | 2560 x 1 x 1 x 1 | F32 | 32.0000 | | 190 | blk.10.post_ffw_norm.weight | Block 10 Post_Ffw_Norm (W) | ( ~3K) 2560 | 2560 x 1 x 1 x 1 | F32 | 32.0000 | | 191 | blk.10.post_norm.weight | Block 10 Post_Norm (W) | ( ~3K) 2560 | 2560 x 1 x 1 x 1 | F32 | 32.0000 | | 192 | blk.10.proj.weight | Block 10 Proj (W) | (~655K) 655360 | 256 x 2560 x 1 x 1 | Q4_K | 4.5000 | - Total elements in blk.10: (~93M) 93074433 - Percentage of total elements: 1.24% - Bits per Weight (BPW) for blk.10: 2.3854 bits ### Block 11 Tensor Group : ~106M Elements | T_ID | Tensor Layer Name | Human Friendly Tensor Layer Name | Elements | Shape | Type | BPW | | ---: | :-------------------------------- | :---------------------------------------------- | :--------------- | :-------------------- | :------ | ------: | | 193 | blk.11.attn_k.weight | Block 11 Attention Key (W) | ( ~3M) 2621440 | 2560 x 1024 x 1 x 1 | IQ2_XS | 2.3125 | | 194 | blk.11.attn_k_norm.weight | Block 11 Attn_K_Norm (W) | ( 512) 512 | 512 x 1 x 1 x 1 | F32 | 32.0000 | | 195 | blk.11.attn_norm.weight | Block 11 Attention Normalization (W) | ( ~3K) 2560 | 2560 x 1 x 1 x 1 | F32 | 32.0000 | | 196 | blk.11.attn_output.weight | Block 11 Attention Output (W) | ( ~10M) 10485760 | 4096 x 2560 x 1 x 1 | Q2_K | 2.6250 | | 197 | blk.11.attn_q.weight | Block 11 Attention Query (W) | ( ~10M) 10485760 | 2560 x 4096 x 1 x 1 | IQ3_XXS | 3.0625 | | 198 | blk.11.attn_q_norm.weight | Block 11 Attn_Q_Norm (W) | ( 512) 512 | 512 x 1 x 1 x 1 | F32 | 32.0000 | | 199 | blk.11.attn_v.weight | Block 11 Attention Value (W) | ( ~3M) 2621440 | 2560 x 1024 x 1 x 1 | Q2_K | 2.6250 | | 200 | blk.11.ffn_down.weight | Block 11 Feed-Forward Network "Down" (W) | ( ~26M) 26214400 | 10240 x 2560 x 1 x 1 | IQ2_XXS | 2.0625 | | 201 | blk.11.ffn_gate.weight | Block 11 Feed-Forward Network "Gate" (W) | ( ~26M) 26214400 | 2560 x 10240 x 1 x 1 | IQ1_M | 1.7500 | | 202 | blk.11.ffn_norm.weight | Block 11 Feed-Forward Network Normalization (W) | ( ~3K) 2560 | 2560 x 1 x 1 x 1 | F32 | 32.0000 | | 203 | blk.11.ffn_up.weight | Block 11 Feed-Forward Network "Up" (W) | ( ~26M) 26214400 | 2560 x 10240 x 1 x 1 | IQ2_XXS | 2.0625 | | 204 | blk.11.inp_gate.weight | Block 11 Inp_Gate (W) | (~655K) 655360 | 2560 x 256 x 1 x 1 | IQ1_M | 1.7500 | | 205 | blk.11.layer_output_scale.weight | Block 11 Layer_Output_Scale (W) | ( 1) 1 | 1 x 1 x 1 x 1 | F32 | 32.0000 | | 206 | blk.11.post_attention_norm.weight | Block 11 Post_Attention_Norm (W) | ( ~3K) 2560 | 2560 x 1 x 1 x 1 | F32 | 32.0000 | | 207 | blk.11.post_ffw_norm.weight | Block 11 Post_Ffw_Norm (W) | ( ~3K) 2560 | 2560 x 1 x 1 x 1 | F32 | 32.0000 | | 208 | blk.11.post_norm.weight | Block 11 Post_Norm (W) | ( ~3K) 2560 | 2560 x 1 x 1 x 1 | F32 | 32.0000 | | 209 | blk.11.proj.weight | Block 11 Proj (W) | (~655K) 655360 | 256 x 2560 x 1 x 1 | Q2_K | 2.6250 | - Total elements in blk.11: (~106M) 106182145 - Percentage of total elements: 1.41% - Bits per Weight (BPW) for blk.11: 2.1652 bits ### Block 12 Tensor Group : ~93M Elements | T_ID | Tensor Layer Name | Human Friendly Tensor Layer Name | Elements | Shape | Type | BPW | | ---: | :-------------------------------- | :---------------------------------------------- | :--------------- | :-------------------- | :------ | ------: | | 210 | blk.12.attn_k.weight | Block 12 Attention Key (W) | ( ~1M) 1310720 | 2560 x 512 x 1 x 1 | Q2_K | 2.6250 | | 211 | blk.12.attn_k_norm.weight | Block 12 Attn_K_Norm (W) | ( 256) 256 | 256 x 1 x 1 x 1 | F32 | 32.0000 | | 212 | blk.12.attn_norm.weight | Block 12 Attention Normalization (W) | ( ~3K) 2560 | 2560 x 1 x 1 x 1 | F32 | 32.0000 | | 213 | blk.12.attn_output.weight | Block 12 Attention Output (W) | ( ~5M) 5242880 | 2048 x 2560 x 1 x 1 | IQ3_XXS | 3.0625 | | 214 | blk.12.attn_q.weight | Block 12 Attention Query (W) | ( ~5M) 5242880 | 2560 x 2048 x 1 x 1 | Q2_K | 2.6250 | | 215 | blk.12.attn_q_norm.weight | Block 12 Attn_Q_Norm (W) | ( 256) 256 | 256 x 1 x 1 x 1 | F32 | 32.0000 | | 216 | blk.12.attn_v.weight | Block 12 Attention Value (W) | ( ~1M) 1310720 | 2560 x 512 x 1 x 1 | Q2_K | 2.6250 | | 217 | blk.12.ffn_down.weight | Block 12 Feed-Forward Network "Down" (W) | ( ~26M) 26214400 | 10240 x 2560 x 1 x 1 | IQ2_XXS | 2.0625 | | 218 | blk.12.ffn_gate.weight | Block 12 Feed-Forward Network "Gate" (W) | ( ~26M) 26214400 | 2560 x 10240 x 1 x 1 | IQ2_XXS | 2.0625 | | 219 | blk.12.ffn_norm.weight | Block 12 Feed-Forward Network Normalization (W) | ( ~3K) 2560 | 2560 x 1 x 1 x 1 | F32 | 32.0000 | | 220 | blk.12.ffn_up.weight | Block 12 Feed-Forward Network "Up" (W) | ( ~26M) 26214400 | 2560 x 10240 x 1 x 1 | Q2_K | 2.6250 | | 221 | blk.12.inp_gate.weight | Block 12 Inp_Gate (W) | (~655K) 655360 | 2560 x 256 x 1 x 1 | IQ1_M | 1.7500 | | 222 | blk.12.layer_output_scale.weight | Block 12 Layer_Output_Scale (W) | ( 1) 1 | 1 x 1 x 1 x 1 | F32 | 32.0000 | | 223 | blk.12.post_attention_norm.weight | Block 12 Post_Attention_Norm (W) | ( ~3K) 2560 | 2560 x 1 x 1 x 1 | F32 | 32.0000 | | 224 | blk.12.post_ffw_norm.weight | Block 12 Post_Ffw_Norm (W) | ( ~3K) 2560 | 2560 x 1 x 1 x 1 | F32 | 32.0000 | | 225 | blk.12.post_norm.weight | Block 12 Post_Norm (W) | ( ~3K) 2560 | 2560 x 1 x 1 x 1 | F32 | 32.0000 | | 226 | blk.12.proj.weight | Block 12 Proj (W) | (~655K) 655360 | 256 x 2560 x 1 x 1 | Q2_K | 2.6250 | - Total elements in blk.12: (~93M) 93074433 - Percentage of total elements: 1.24% - Bits per Weight (BPW) for blk.12: 2.3308 bits ### Block 13 Tensor Group : ~93M Elements | T_ID | Tensor Layer Name | Human Friendly Tensor Layer Name | Elements | Shape | Type | BPW | | ---: | :-------------------------------- | :---------------------------------------------- | :--------------- | :-------------------- | :------ | ------: | | 227 | blk.13.attn_k.weight | Block 13 Attention Key (W) | ( ~1M) 1310720 | 2560 x 512 x 1 x 1 | IQ3_XXS | 3.0625 | | 228 | blk.13.attn_k_norm.weight | Block 13 Attn_K_Norm (W) | ( 256) 256 | 256 x 1 x 1 x 1 | F32 | 32.0000 | | 229 | blk.13.attn_norm.weight | Block 13 Attention Normalization (W) | ( ~3K) 2560 | 2560 x 1 x 1 x 1 | F32 | 32.0000 | | 230 | blk.13.attn_output.weight | Block 13 Attention Output (W) | ( ~5M) 5242880 | 2048 x 2560 x 1 x 1 | Q3_K | 3.4375 | | 231 | blk.13.attn_q.weight | Block 13 Attention Query (W) | ( ~5M) 5242880 | 2560 x 2048 x 1 x 1 | IQ3_XXS | 3.0625 | | 232 | blk.13.attn_q_norm.weight | Block 13 Attn_Q_Norm (W) | ( 256) 256 | 256 x 1 x 1 x 1 | F32 | 32.0000 | | 233 | blk.13.attn_v.weight | Block 13 Attention Value (W) | ( ~1M) 1310720 | 2560 x 512 x 1 x 1 | Q2_K | 2.6250 | | 234 | blk.13.ffn_down.weight | Block 13 Feed-Forward Network "Down" (W) | ( ~26M) 26214400 | 10240 x 2560 x 1 x 1 | IQ2_XXS | 2.0625 | | 235 | blk.13.ffn_gate.weight | Block 13 Feed-Forward Network "Gate" (W) | ( ~26M) 26214400 | 2560 x 10240 x 1 x 1 | IQ1_M | 1.7500 | | 236 | blk.13.ffn_norm.weight | Block 13 Feed-Forward Network Normalization (W) | ( ~3K) 2560 | 2560 x 1 x 1 x 1 | F32 | 32.0000 | | 237 | blk.13.ffn_up.weight | Block 13 Feed-Forward Network "Up" (W) | ( ~26M) 26214400 | 2560 x 10240 x 1 x 1 | IQ2_XXS | 2.0625 | | 238 | blk.13.inp_gate.weight | Block 13 Inp_Gate (W) | (~655K) 655360 | 2560 x 256 x 1 x 1 | IQ1_M | 1.7500 | | 239 | blk.13.layer_output_scale.weight | Block 13 Layer_Output_Scale (W) | ( 1) 1 | 1 x 1 x 1 x 1 | F32 | 32.0000 | | 240 | blk.13.post_attention_norm.weight | Block 13 Post_Attention_Norm (W) | ( ~3K) 2560 | 2560 x 1 x 1 x 1 | F32 | 32.0000 | | 241 | blk.13.post_ffw_norm.weight | Block 13 Post_Ffw_Norm (W) | ( ~3K) 2560 | 2560 x 1 x 1 x 1 | F32 | 32.0000 | | 242 | blk.13.post_norm.weight | Block 13 Post_Norm (W) | ( ~3K) 2560 | 2560 x 1 x 1 x 1 | F32 | 32.0000 | | 243 | blk.13.proj.weight | Block 13 Proj (W) | (~655K) 655360 | 256 x 2560 x 1 x 1 | Q5_K | 5.5000 | - Total elements in blk.13: (~93M) 93074433 - Percentage of total elements: 1.24% - Bits per Weight (BPW) for blk.13: 2.1566 bits ### Block 14 Tensor Group : ~93M Elements | T_ID | Tensor Layer Name | Human Friendly Tensor Layer Name | Elements | Shape | Type | BPW | | ---: | :-------------------------------- | :---------------------------------------------- | :--------------- | :-------------------- | :------ | ------: | | 244 | blk.14.attn_k.weight | Block 14 Attention Key (W) | ( ~1M) 1310720 | 2560 x 512 x 1 x 1 | IQ3_XXS | 3.0625 | | 245 | blk.14.attn_k_norm.weight | Block 14 Attn_K_Norm (W) | ( 256) 256 | 256 x 1 x 1 x 1 | F32 | 32.0000 | | 246 | blk.14.attn_norm.weight | Block 14 Attention Normalization (W) | ( ~3K) 2560 | 2560 x 1 x 1 x 1 | F32 | 32.0000 | | 247 | blk.14.attn_output.weight | Block 14 Attention Output (W) | ( ~5M) 5242880 | 2048 x 2560 x 1 x 1 | Q3_K | 3.4375 | | 248 | blk.14.attn_q.weight | Block 14 Attention Query (W) | ( ~5M) 5242880 | 2560 x 2048 x 1 x 1 | IQ2_XS | 2.3125 | | 249 | blk.14.attn_q_norm.weight | Block 14 Attn_Q_Norm (W) | ( 256) 256 | 256 x 1 x 1 x 1 | F32 | 32.0000 | | 250 | blk.14.attn_v.weight | Block 14 Attention Value (W) | ( ~1M) 1310720 | 2560 x 512 x 1 x 1 | Q2_K | 2.6250 | | 251 | blk.14.ffn_down.weight | Block 14 Feed-Forward Network "Down" (W) | ( ~26M) 26214400 | 10240 x 2560 x 1 x 1 | IQ2_XXS | 2.0625 | | 252 | blk.14.ffn_gate.weight | Block 14 Feed-Forward Network "Gate" (W) | ( ~26M) 26214400 | 2560 x 10240 x 1 x 1 | IQ2_XXS | 2.0625 | | 253 | blk.14.ffn_norm.weight | Block 14 Feed-Forward Network Normalization (W) | ( ~3K) 2560 | 2560 x 1 x 1 x 1 | F32 | 32.0000 | | 254 | blk.14.ffn_up.weight | Block 14 Feed-Forward Network "Up" (W) | ( ~26M) 26214400 | 2560 x 10240 x 1 x 1 | IQ2_XXS | 2.0625 | | 255 | blk.14.inp_gate.weight | Block 14 Inp_Gate (W) | (~655K) 655360 | 2560 x 256 x 1 x 1 | IQ2_XXS | 2.0625 | | 256 | blk.14.layer_output_scale.weight | Block 14 Layer_Output_Scale (W) | ( 1) 1 | 1 x 1 x 1 x 1 | F32 | 32.0000 | | 257 | blk.14.post_attention_norm.weight | Block 14 Post_Attention_Norm (W) | ( ~3K) 2560 | 2560 x 1 x 1 x 1 | F32 | 32.0000 | | 258 | blk.14.post_ffw_norm.weight | Block 14 Post_Ffw_Norm (W) | ( ~3K) 2560 | 2560 x 1 x 1 x 1 | F32 | 32.0000 | | 259 | blk.14.post_norm.weight | Block 14 Post_Norm (W) | ( ~3K) 2560 | 2560 x 1 x 1 x 1 | F32 | 32.0000 | | 260 | blk.14.proj.weight | Block 14 Proj (W) | (~655K) 655360 | 256 x 2560 x 1 x 1 | Q4_K | 4.5000 | - Total elements in blk.14: (~93M) 93074433 - Percentage of total elements: 1.24% - Bits per Weight (BPW) for blk.14: 2.1975 bits ### Block 15 Tensor Group : ~93M Elements | T_ID | Tensor Layer Name | Human Friendly Tensor Layer Name | Elements | Shape | Type | BPW | | ---: | :-------------------------------- | :---------------------------------------------- | :--------------- | :-------------------- | :------ | ------: | | 261 | blk.15.attn_k.weight | Block 15 Attention Key (W) | ( ~1M) 1310720 | 2560 x 512 x 1 x 1 | IQ3_XXS | 3.0625 | | 262 | blk.15.attn_k_norm.weight | Block 15 Attn_K_Norm (W) | ( 256) 256 | 256 x 1 x 1 x 1 | F32 | 32.0000 | | 263 | blk.15.attn_norm.weight | Block 15 Attention Normalization (W) | ( ~3K) 2560 | 2560 x 1 x 1 x 1 | F32 | 32.0000 | | 264 | blk.15.attn_output.weight | Block 15 Attention Output (W) | ( ~5M) 5242880 | 2048 x 2560 x 1 x 1 | Q3_K | 3.4375 | | 265 | blk.15.attn_q.weight | Block 15 Attention Query (W) | ( ~5M) 5242880 | 2560 x 2048 x 1 x 1 | IQ2_XS | 2.3125 | | 266 | blk.15.attn_q_norm.weight | Block 15 Attn_Q_Norm (W) | ( 256) 256 | 256 x 1 x 1 x 1 | F32 | 32.0000 | | 267 | blk.15.attn_v.weight | Block 15 Attention Value (W) | ( ~1M) 1310720 | 2560 x 512 x 1 x 1 | Q2_K | 2.6250 | | 268 | blk.15.ffn_down.weight | Block 15 Feed-Forward Network "Down" (W) | ( ~26M) 26214400 | 10240 x 2560 x 1 x 1 | IQ2_XXS | 2.0625 | | 269 | blk.15.ffn_gate.weight | Block 15 Feed-Forward Network "Gate" (W) | ( ~26M) 26214400 | 2560 x 10240 x 1 x 1 | IQ2_XXS | 2.0625 | | 270 | blk.15.ffn_norm.weight | Block 15 Feed-Forward Network Normalization (W) | ( ~3K) 2560 | 2560 x 1 x 1 x 1 | F32 | 32.0000 | | 271 | blk.15.ffn_up.weight | Block 15 Feed-Forward Network "Up" (W) | ( ~26M) 26214400 | 2560 x 10240 x 1 x 1 | Q2_K | 2.6250 | | 272 | blk.15.inp_gate.weight | Block 15 Inp_Gate (W) | (~655K) 655360 | 2560 x 256 x 1 x 1 | IQ1_M | 1.7500 | | 273 | blk.15.layer_output_scale.weight | Block 15 Layer_Output_Scale (W) | ( 1) 1 | 1 x 1 x 1 x 1 | F32 | 32.0000 | | 274 | blk.15.post_attention_norm.weight | Block 15 Post_Attention_Norm (W) | ( ~3K) 2560 | 2560 x 1 x 1 x 1 | F32 | 32.0000 | | 275 | blk.15.post_ffw_norm.weight | Block 15 Post_Ffw_Norm (W) | ( ~3K) 2560 | 2560 x 1 x 1 x 1 | F32 | 32.0000 | | 276 | blk.15.post_norm.weight | Block 15 Post_Norm (W) | ( ~3K) 2560 | 2560 x 1 x 1 x 1 | F32 | 32.0000 | | 277 | blk.15.proj.weight | Block 15 Proj (W) | (~655K) 655360 | 256 x 2560 x 1 x 1 | Q5_K | 5.5000 | - Total elements in blk.15: (~93M) 93074433 - Percentage of total elements: 1.24% - Bits per Weight (BPW) for blk.15: 2.3608 bits ### Block 16 Tensor Group : ~93M Elements | T_ID | Tensor Layer Name | Human Friendly Tensor Layer Name | Elements | Shape | Type | BPW | | ---: | :-------------------------------- | :---------------------------------------------- | :--------------- | :-------------------- | :------ | ------: | | 278 | blk.16.attn_k.weight | Block 16 Attention Key (W) | ( ~1M) 1310720 | 2560 x 512 x 1 x 1 | Q2_K | 2.6250 | | 279 | blk.16.attn_k_norm.weight | Block 16 Attn_K_Norm (W) | ( 256) 256 | 256 x 1 x 1 x 1 | F32 | 32.0000 | | 280 | blk.16.attn_norm.weight | Block 16 Attention Normalization (W) | ( ~3K) 2560 | 2560 x 1 x 1 x 1 | F32 | 32.0000 | | 281 | blk.16.attn_output.weight | Block 16 Attention Output (W) | ( ~5M) 5242880 | 2048 x 2560 x 1 x 1 | Q3_K | 3.4375 | | 282 | blk.16.attn_q.weight | Block 16 Attention Query (W) | ( ~5M) 5242880 | 2560 x 2048 x 1 x 1 | IQ2_XS | 2.3125 | | 283 | blk.16.attn_q_norm.weight | Block 16 Attn_Q_Norm (W) | ( 256) 256 | 256 x 1 x 1 x 1 | F32 | 32.0000 | | 284 | blk.16.attn_v.weight | Block 16 Attention Value (W) | ( ~1M) 1310720 | 2560 x 512 x 1 x 1 | Q2_K | 2.6250 | | 285 | blk.16.ffn_down.weight | Block 16 Feed-Forward Network "Down" (W) | ( ~26M) 26214400 | 10240 x 2560 x 1 x 1 | IQ2_XS | 2.3125 | | 286 | blk.16.ffn_gate.weight | Block 16 Feed-Forward Network "Gate" (W) | ( ~26M) 26214400 | 2560 x 10240 x 1 x 1 | IQ2_XXS | 2.0625 | | 287 | blk.16.ffn_norm.weight | Block 16 Feed-Forward Network Normalization (W) | ( ~3K) 2560 | 2560 x 1 x 1 x 1 | F32 | 32.0000 | | 288 | blk.16.ffn_up.weight | Block 16 Feed-Forward Network "Up" (W) | ( ~26M) 26214400 | 2560 x 10240 x 1 x 1 | Q2_K | 2.6250 | | 289 | blk.16.inp_gate.weight | Block 16 Inp_Gate (W) | (~655K) 655360 | 2560 x 256 x 1 x 1 | IQ1_M | 1.7500 | | 290 | blk.16.layer_output_scale.weight | Block 16 Layer_Output_Scale (W) | ( 1) 1 | 1 x 1 x 1 x 1 | F32 | 32.0000 | | 291 | blk.16.post_attention_norm.weight | Block 16 Post_Attention_Norm (W) | ( ~3K) 2560 | 2560 x 1 x 1 x 1 | F32 | 32.0000 | | 292 | blk.16.post_ffw_norm.weight | Block 16 Post_Ffw_Norm (W) | ( ~3K) 2560 | 2560 x 1 x 1 x 1 | F32 | 32.0000 | | 293 | blk.16.post_norm.weight | Block 16 Post_Norm (W) | ( ~3K) 2560 | 2560 x 1 x 1 x 1 | F32 | 32.0000 | | 294 | blk.16.proj.weight | Block 16 Proj (W) | (~655K) 655360 | 256 x 2560 x 1 x 1 | Q4_1 | 5.0000 | - Total elements in blk.16: (~93M) 93074433 - Percentage of total elements: 1.24% - Bits per Weight (BPW) for blk.16: 2.4215 bits ### Block 17 Tensor Group : ~106M Elements | T_ID | Tensor Layer Name | Human Friendly Tensor Layer Name | Elements | Shape | Type | BPW | | ---: | :-------------------------------- | :---------------------------------------------- | :--------------- | :-------------------- | :------ | ------: | | 295 | blk.17.attn_k.weight | Block 17 Attention Key (W) | ( ~3M) 2621440 | 2560 x 1024 x 1 x 1 | IQ2_XS | 2.3125 | | 296 | blk.17.attn_k_norm.weight | Block 17 Attn_K_Norm (W) | ( 512) 512 | 512 x 1 x 1 x 1 | F32 | 32.0000 | | 297 | blk.17.attn_norm.weight | Block 17 Attention Normalization (W) | ( ~3K) 2560 | 2560 x 1 x 1 x 1 | F32 | 32.0000 | | 298 | blk.17.attn_output.weight | Block 17 Attention Output (W) | ( ~10M) 10485760 | 4096 x 2560 x 1 x 1 | Q2_K | 2.6250 | | 299 | blk.17.attn_q.weight | Block 17 Attention Query (W) | ( ~10M) 10485760 | 2560 x 4096 x 1 x 1 | IQ2_XS | 2.3125 | | 300 | blk.17.attn_q_norm.weight | Block 17 Attn_Q_Norm (W) | ( 512) 512 | 512 x 1 x 1 x 1 | F32 | 32.0000 | | 301 | blk.17.attn_v.weight | Block 17 Attention Value (W) | ( ~3M) 2621440 | 2560 x 1024 x 1 x 1 | Q2_K | 2.6250 | | 302 | blk.17.ffn_down.weight | Block 17 Feed-Forward Network "Down" (W) | ( ~26M) 26214400 | 10240 x 2560 x 1 x 1 | IQ2_XXS | 2.0625 | | 303 | blk.17.ffn_gate.weight | Block 17 Feed-Forward Network "Gate" (W) | ( ~26M) 26214400 | 2560 x 10240 x 1 x 1 | IQ2_XXS | 2.0625 | | 304 | blk.17.ffn_norm.weight | Block 17 Feed-Forward Network Normalization (W) | ( ~3K) 2560 | 2560 x 1 x 1 x 1 | F32 | 32.0000 | | 305 | blk.17.ffn_up.weight | Block 17 Feed-Forward Network "Up" (W) | ( ~26M) 26214400 | 2560 x 10240 x 1 x 1 | Q2_K | 2.6250 | | 306 | blk.17.inp_gate.weight | Block 17 Inp_Gate (W) | (~655K) 655360 | 2560 x 256 x 1 x 1 | IQ1_M | 1.7500 | | 307 | blk.17.layer_output_scale.weight | Block 17 Layer_Output_Scale (W) | ( 1) 1 | 1 x 1 x 1 x 1 | F32 | 32.0000 | | 308 | blk.17.post_attention_norm.weight | Block 17 Post_Attention_Norm (W) | ( ~3K) 2560 | 2560 x 1 x 1 x 1 | F32 | 32.0000 | | 309 | blk.17.post_ffw_norm.weight | Block 17 Post_Ffw_Norm (W) | ( ~3K) 2560 | 2560 x 1 x 1 x 1 | F32 | 32.0000 | | 310 | blk.17.post_norm.weight | Block 17 Post_Norm (W) | ( ~3K) 2560 | 2560 x 1 x 1 x 1 | F32 | 32.0000 | | 311 | blk.17.proj.weight | Block 17 Proj (W) | (~655K) 655360 | 256 x 2560 x 1 x 1 | Q4_K | 4.5000 | - Total elements in blk.17: (~106M) 106182145 - Percentage of total elements: 1.41% - Bits per Weight (BPW) for blk.17: 2.3187 bits ### Block 18 Tensor Group : ~93M Elements | T_ID | Tensor Layer Name | Human Friendly Tensor Layer Name | Elements | Shape | Type | BPW | | ---: | :-------------------------------- | :---------------------------------------------- | :--------------- | :-------------------- | :------ | ------: | | 312 | blk.18.attn_k.weight | Block 18 Attention Key (W) | ( ~1M) 1310720 | 2560 x 512 x 1 x 1 | IQ3_XXS | 3.0625 | | 313 | blk.18.attn_k_norm.weight | Block 18 Attn_K_Norm (W) | ( 256) 256 | 256 x 1 x 1 x 1 | F32 | 32.0000 | | 314 | blk.18.attn_norm.weight | Block 18 Attention Normalization (W) | ( ~3K) 2560 | 2560 x 1 x 1 x 1 | F32 | 32.0000 | | 315 | blk.18.attn_output.weight | Block 18 Attention Output (W) | ( ~5M) 5242880 | 2048 x 2560 x 1 x 1 | Q3_K | 3.4375 | | 316 | blk.18.attn_q.weight | Block 18 Attention Query (W) | ( ~5M) 5242880 | 2560 x 2048 x 1 x 1 | IQ3_XXS | 3.0625 | | 317 | blk.18.attn_q_norm.weight | Block 18 Attn_Q_Norm (W) | ( 256) 256 | 256 x 1 x 1 x 1 | F32 | 32.0000 | | 318 | blk.18.attn_v.weight | Block 18 Attention Value (W) | ( ~1M) 1310720 | 2560 x 512 x 1 x 1 | Q2_K | 2.6250 | | 319 | blk.18.ffn_down.weight | Block 18 Feed-Forward Network "Down" (W) | ( ~26M) 26214400 | 10240 x 2560 x 1 x 1 | IQ2_XS | 2.3125 | | 320 | blk.18.ffn_gate.weight | Block 18 Feed-Forward Network "Gate" (W) | ( ~26M) 26214400 | 2560 x 10240 x 1 x 1 | IQ2_XXS | 2.0625 | | 321 | blk.18.ffn_norm.weight | Block 18 Feed-Forward Network Normalization (W) | ( ~3K) 2560 | 2560 x 1 x 1 x 1 | F32 | 32.0000 | | 322 | blk.18.ffn_up.weight | Block 18 Feed-Forward Network "Up" (W) | ( ~26M) 26214400 | 2560 x 10240 x 1 x 1 | IQ2_XXS | 2.0625 | | 323 | blk.18.inp_gate.weight | Block 18 Inp_Gate (W) | (~655K) 655360 | 2560 x 256 x 1 x 1 | IQ1_M | 1.7500 | | 324 | blk.18.layer_output_scale.weight | Block 18 Layer_Output_Scale (W) | ( 1) 1 | 1 x 1 x 1 x 1 | F32 | 32.0000 | | 325 | blk.18.post_attention_norm.weight | Block 18 Post_Attention_Norm (W) | ( ~3K) 2560 | 2560 x 1 x 1 x 1 | F32 | 32.0000 | | 326 | blk.18.post_ffw_norm.weight | Block 18 Post_Ffw_Norm (W) | ( ~3K) 2560 | 2560 x 1 x 1 x 1 | F32 | 32.0000 | | 327 | blk.18.post_norm.weight | Block 18 Post_Norm (W) | ( ~3K) 2560 | 2560 x 1 x 1 x 1 | F32 | 32.0000 | | 328 | blk.18.proj.weight | Block 18 Proj (W) | (~655K) 655360 | 256 x 2560 x 1 x 1 | Q4_1 | 5.0000 | - Total elements in blk.18: (~93M) 93074433 - Percentage of total elements: 1.24% - Bits per Weight (BPW) for blk.18: 2.3115 bits ### Block 19 Tensor Group : ~93M Elements | T_ID | Tensor Layer Name | Human Friendly Tensor Layer Name | Elements | Shape | Type | BPW | | ---: | :-------------------------------- | :---------------------------------------------- | :--------------- | :-------------------- | :------ | ------: | | 329 | blk.19.attn_k.weight | Block 19 Attention Key (W) | ( ~1M) 1310720 | 2560 x 512 x 1 x 1 | IQ3_XXS | 3.0625 | | 330 | blk.19.attn_k_norm.weight | Block 19 Attn_K_Norm (W) | ( 256) 256 | 256 x 1 x 1 x 1 | F32 | 32.0000 | | 331 | blk.19.attn_norm.weight | Block 19 Attention Normalization (W) | ( ~3K) 2560 | 2560 x 1 x 1 x 1 | F32 | 32.0000 | | 332 | blk.19.attn_output.weight | Block 19 Attention Output (W) | ( ~5M) 5242880 | 2048 x 2560 x 1 x 1 | Q3_K | 3.4375 | | 333 | blk.19.attn_q.weight | Block 19 Attention Query (W) | ( ~5M) 5242880 | 2560 x 2048 x 1 x 1 | IQ3_XXS | 3.0625 | | 334 | blk.19.attn_q_norm.weight | Block 19 Attn_Q_Norm (W) | ( 256) 256 | 256 x 1 x 1 x 1 | F32 | 32.0000 | | 335 | blk.19.attn_v.weight | Block 19 Attention Value (W) | ( ~1M) 1310720 | 2560 x 512 x 1 x 1 | Q2_K | 2.6250 | | 336 | blk.19.ffn_down.weight | Block 19 Feed-Forward Network "Down" (W) | ( ~26M) 26214400 | 10240 x 2560 x 1 x 1 | IQ2_XS | 2.3125 | | 337 | blk.19.ffn_gate.weight | Block 19 Feed-Forward Network "Gate" (W) | ( ~26M) 26214400 | 2560 x 10240 x 1 x 1 | IQ2_XXS | 2.0625 | | 338 | blk.19.ffn_norm.weight | Block 19 Feed-Forward Network Normalization (W) | ( ~3K) 2560 | 2560 x 1 x 1 x 1 | F32 | 32.0000 | | 339 | blk.19.ffn_up.weight | Block 19 Feed-Forward Network "Up" (W) | ( ~26M) 26214400 | 2560 x 10240 x 1 x 1 | IQ2_XXS | 2.0625 | | 340 | blk.19.inp_gate.weight | Block 19 Inp_Gate (W) | (~655K) 655360 | 2560 x 256 x 1 x 1 | IQ1_M | 1.7500 | | 341 | blk.19.layer_output_scale.weight | Block 19 Layer_Output_Scale (W) | ( 1) 1 | 1 x 1 x 1 x 1 | F32 | 32.0000 | | 342 | blk.19.post_attention_norm.weight | Block 19 Post_Attention_Norm (W) | ( ~3K) 2560 | 2560 x 1 x 1 x 1 | F32 | 32.0000 | | 343 | blk.19.post_ffw_norm.weight | Block 19 Post_Ffw_Norm (W) | ( ~3K) 2560 | 2560 x 1 x 1 x 1 | F32 | 32.0000 | | 344 | blk.19.post_norm.weight | Block 19 Post_Norm (W) | ( ~3K) 2560 | 2560 x 1 x 1 x 1 | F32 | 32.0000 | | 345 | blk.19.proj.weight | Block 19 Proj (W) | (~655K) 655360 | 256 x 2560 x 1 x 1 | IQ4_XS | 4.2500 | - Total elements in blk.19: (~93M) 93074433 - Percentage of total elements: 1.24% - Bits per Weight (BPW) for blk.19: 2.3062 bits ### Block 20 Tensor Group : ~93M Elements | T_ID | Tensor Layer Name | Human Friendly Tensor Layer Name | Elements | Shape | Type | BPW | | ---: | :-------------------------------- | :---------------------------------------------- | :--------------- | :-------------------- | :------ | ------: | | 346 | blk.20.attn_k.weight | Block 20 Attention Key (W) | ( ~1M) 1310720 | 2560 x 512 x 1 x 1 | IQ3_XXS | 3.0625 | | 347 | blk.20.attn_k_norm.weight | Block 20 Attn_K_Norm (W) | ( 256) 256 | 256 x 1 x 1 x 1 | F32 | 32.0000 | | 348 | blk.20.attn_norm.weight | Block 20 Attention Normalization (W) | ( ~3K) 2560 | 2560 x 1 x 1 x 1 | F32 | 32.0000 | | 349 | blk.20.attn_output.weight | Block 20 Attention Output (W) | ( ~5M) 5242880 | 2048 x 2560 x 1 x 1 | Q3_K | 3.4375 | | 350 | blk.20.attn_q.weight | Block 20 Attention Query (W) | ( ~5M) 5242880 | 2560 x 2048 x 1 x 1 | IQ3_XXS | 3.0625 | | 351 | blk.20.attn_q_norm.weight | Block 20 Attn_Q_Norm (W) | ( 256) 256 | 256 x 1 x 1 x 1 | F32 | 32.0000 | | 352 | blk.20.attn_v.weight | Block 20 Attention Value (W) | ( ~1M) 1310720 | 2560 x 512 x 1 x 1 | Q2_K | 2.6250 | | 353 | blk.20.ffn_down.weight | Block 20 Feed-Forward Network "Down" (W) | ( ~26M) 26214400 | 10240 x 2560 x 1 x 1 | IQ2_XXS | 2.0625 | | 354 | blk.20.ffn_gate.weight | Block 20 Feed-Forward Network "Gate" (W) | ( ~26M) 26214400 | 2560 x 10240 x 1 x 1 | IQ2_XXS | 2.0625 | | 355 | blk.20.ffn_norm.weight | Block 20 Feed-Forward Network Normalization (W) | ( ~3K) 2560 | 2560 x 1 x 1 x 1 | F32 | 32.0000 | | 356 | blk.20.ffn_up.weight | Block 20 Feed-Forward Network "Up" (W) | ( ~26M) 26214400 | 2560 x 10240 x 1 x 1 | Q2_K | 2.6250 | | 357 | blk.20.inp_gate.weight | Block 20 Inp_Gate (W) | (~655K) 655360 | 2560 x 256 x 1 x 1 | IQ1_M | 1.7500 | | 358 | blk.20.layer_output_scale.weight | Block 20 Layer_Output_Scale (W) | ( 1) 1 | 1 x 1 x 1 x 1 | F32 | 32.0000 | | 359 | blk.20.post_attention_norm.weight | Block 20 Post_Attention_Norm (W) | ( ~3K) 2560 | 2560 x 1 x 1 x 1 | F32 | 32.0000 | | 360 | blk.20.post_ffw_norm.weight | Block 20 Post_Ffw_Norm (W) | ( ~3K) 2560 | 2560 x 1 x 1 x 1 | F32 | 32.0000 | | 361 | blk.20.post_norm.weight | Block 20 Post_Norm (W) | ( ~3K) 2560 | 2560 x 1 x 1 x 1 | F32 | 32.0000 | | 362 | blk.20.proj.weight | Block 20 Proj (W) | (~655K) 655360 | 256 x 2560 x 1 x 1 | Q2_K | 2.6250 | - Total elements in blk.20: (~93M) 93074433 - Percentage of total elements: 1.24% - Bits per Weight (BPW) for blk.20: 2.3828 bits ### Block 21 Tensor Group : ~93M Elements | T_ID | Tensor Layer Name | Human Friendly Tensor Layer Name | Elements | Shape | Type | BPW | | ---: | :-------------------------------- | :---------------------------------------------- | :--------------- | :-------------------- | :------ | ------: | | 363 | blk.21.attn_k.weight | Block 21 Attention Key (W) | ( ~1M) 1310720 | 2560 x 512 x 1 x 1 | IQ3_XXS | 3.0625 | | 364 | blk.21.attn_k_norm.weight | Block 21 Attn_K_Norm (W) | ( 256) 256 | 256 x 1 x 1 x 1 | F32 | 32.0000 | | 365 | blk.21.attn_norm.weight | Block 21 Attention Normalization (W) | ( ~3K) 2560 | 2560 x 1 x 1 x 1 | F32 | 32.0000 | | 366 | blk.21.attn_output.weight | Block 21 Attention Output (W) | ( ~5M) 5242880 | 2048 x 2560 x 1 x 1 | Q3_K | 3.4375 | | 367 | blk.21.attn_q.weight | Block 21 Attention Query (W) | ( ~5M) 5242880 | 2560 x 2048 x 1 x 1 | IQ3_XXS | 3.0625 | | 368 | blk.21.attn_q_norm.weight | Block 21 Attn_Q_Norm (W) | ( 256) 256 | 256 x 1 x 1 x 1 | F32 | 32.0000 | | 369 | blk.21.attn_v.weight | Block 21 Attention Value (W) | ( ~1M) 1310720 | 2560 x 512 x 1 x 1 | Q2_K | 2.6250 | | 370 | blk.21.ffn_down.weight | Block 21 Feed-Forward Network "Down" (W) | ( ~26M) 26214400 | 10240 x 2560 x 1 x 1 | IQ2_XS | 2.3125 | | 371 | blk.21.ffn_gate.weight | Block 21 Feed-Forward Network "Gate" (W) | ( ~26M) 26214400 | 2560 x 10240 x 1 x 1 | IQ2_XXS | 2.0625 | | 372 | blk.21.ffn_norm.weight | Block 21 Feed-Forward Network Normalization (W) | ( ~3K) 2560 | 2560 x 1 x 1 x 1 | F32 | 32.0000 | | 373 | blk.21.ffn_up.weight | Block 21 Feed-Forward Network "Up" (W) | ( ~26M) 26214400 | 2560 x 10240 x 1 x 1 | Q2_K | 2.6250 | | 374 | blk.21.inp_gate.weight | Block 21 Inp_Gate (W) | (~655K) 655360 | 2560 x 256 x 1 x 1 | IQ1_M | 1.7500 | | 375 | blk.21.layer_output_scale.weight | Block 21 Layer_Output_Scale (W) | ( 1) 1 | 1 x 1 x 1 x 1 | F32 | 32.0000 | | 376 | blk.21.post_attention_norm.weight | Block 21 Post_Attention_Norm (W) | ( ~3K) 2560 | 2560 x 1 x 1 x 1 | F32 | 32.0000 | | 377 | blk.21.post_ffw_norm.weight | Block 21 Post_Ffw_Norm (W) | ( ~3K) 2560 | 2560 x 1 x 1 x 1 | F32 | 32.0000 | | 378 | blk.21.post_norm.weight | Block 21 Post_Norm (W) | ( ~3K) 2560 | 2560 x 1 x 1 x 1 | F32 | 32.0000 | | 379 | blk.21.proj.weight | Block 21 Proj (W) | (~655K) 655360 | 256 x 2560 x 1 x 1 | IQ4_XS | 4.2500 | - Total elements in blk.21: (~93M) 93074433 - Percentage of total elements: 1.24% - Bits per Weight (BPW) for blk.21: 2.4646 bits ### Block 22 Tensor Group : ~93M Elements | T_ID | Tensor Layer Name | Human Friendly Tensor Layer Name | Elements | Shape | Type | BPW | | ---: | :-------------------------------- | :---------------------------------------------- | :--------------- | :-------------------- | :------ | ------: | | 380 | blk.22.attn_k.weight | Block 22 Attention Key (W) | ( ~1M) 1310720 | 2560 x 512 x 1 x 1 | IQ3_XXS | 3.0625 | | 381 | blk.22.attn_k_norm.weight | Block 22 Attn_K_Norm (W) | ( 256) 256 | 256 x 1 x 1 x 1 | F32 | 32.0000 | | 382 | blk.22.attn_norm.weight | Block 22 Attention Normalization (W) | ( ~3K) 2560 | 2560 x 1 x 1 x 1 | F32 | 32.0000 | | 383 | blk.22.attn_output.weight | Block 22 Attention Output (W) | ( ~5M) 5242880 | 2048 x 2560 x 1 x 1 | Q3_K | 3.4375 | | 384 | blk.22.attn_q.weight | Block 22 Attention Query (W) | ( ~5M) 5242880 | 2560 x 2048 x 1 x 1 | IQ3_XXS | 3.0625 | | 385 | blk.22.attn_q_norm.weight | Block 22 Attn_Q_Norm (W) | ( 256) 256 | 256 x 1 x 1 x 1 | F32 | 32.0000 | | 386 | blk.22.attn_v.weight | Block 22 Attention Value (W) | ( ~1M) 1310720 | 2560 x 512 x 1 x 1 | Q2_K | 2.6250 | | 387 | blk.22.ffn_down.weight | Block 22 Feed-Forward Network "Down" (W) | ( ~26M) 26214400 | 10240 x 2560 x 1 x 1 | Q2_K | 2.6250 | | 388 | blk.22.ffn_gate.weight | Block 22 Feed-Forward Network "Gate" (W) | ( ~26M) 26214400 | 2560 x 10240 x 1 x 1 | IQ2_XXS | 2.0625 | | 389 | blk.22.ffn_norm.weight | Block 22 Feed-Forward Network Normalization (W) | ( ~3K) 2560 | 2560 x 1 x 1 x 1 | F32 | 32.0000 | | 390 | blk.22.ffn_up.weight | Block 22 Feed-Forward Network "Up" (W) | ( ~26M) 26214400 | 2560 x 10240 x 1 x 1 | Q2_K | 2.6250 | | 391 | blk.22.inp_gate.weight | Block 22 Inp_Gate (W) | (~655K) 655360 | 2560 x 256 x 1 x 1 | IQ1_M | 1.7500 | | 392 | blk.22.layer_output_scale.weight | Block 22 Layer_Output_Scale (W) | ( 1) 1 | 1 x 1 x 1 x 1 | F32 | 32.0000 | | 393 | blk.22.post_attention_norm.weight | Block 22 Post_Attention_Norm (W) | ( ~3K) 2560 | 2560 x 1 x 1 x 1 | F32 | 32.0000 | | 394 | blk.22.post_ffw_norm.weight | Block 22 Post_Ffw_Norm (W) | ( ~3K) 2560 | 2560 x 1 x 1 x 1 | F32 | 32.0000 | | 395 | blk.22.post_norm.weight | Block 22 Post_Norm (W) | ( ~3K) 2560 | 2560 x 1 x 1 x 1 | F32 | 32.0000 | | 396 | blk.22.proj.weight | Block 22 Proj (W) | (~655K) 655360 | 256 x 2560 x 1 x 1 | Q2_K | 2.6250 | - Total elements in blk.22: (~93M) 93074433 - Percentage of total elements: 1.24% - Bits per Weight (BPW) for blk.22: 2.5412 bits ### Block 23 Tensor Group : ~106M Elements | T_ID | Tensor Layer Name | Human Friendly Tensor Layer Name | Elements | Shape | Type | BPW | | ---: | :-------------------------------- | :---------------------------------------------- | :--------------- | :-------------------- | :------ | ------: | | 397 | blk.23.attn_k.weight | Block 23 Attention Key (W) | ( ~3M) 2621440 | 2560 x 1024 x 1 x 1 | IQ3_XXS | 3.0625 | | 398 | blk.23.attn_k_norm.weight | Block 23 Attn_K_Norm (W) | ( 512) 512 | 512 x 1 x 1 x 1 | F32 | 32.0000 | | 399 | blk.23.attn_norm.weight | Block 23 Attention Normalization (W) | ( ~3K) 2560 | 2560 x 1 x 1 x 1 | F32 | 32.0000 | | 400 | blk.23.attn_output.weight | Block 23 Attention Output (W) | ( ~10M) 10485760 | 4096 x 2560 x 1 x 1 | Q2_K | 2.6250 | | 401 | blk.23.attn_q.weight | Block 23 Attention Query (W) | ( ~10M) 10485760 | 2560 x 4096 x 1 x 1 | IQ3_XXS | 3.0625 | | 402 | blk.23.attn_q_norm.weight | Block 23 Attn_Q_Norm (W) | ( 512) 512 | 512 x 1 x 1 x 1 | F32 | 32.0000 | | 403 | blk.23.attn_v.weight | Block 23 Attention Value (W) | ( ~3M) 2621440 | 2560 x 1024 x 1 x 1 | IQ3_XXS | 3.0625 | | 404 | blk.23.ffn_down.weight | Block 23 Feed-Forward Network "Down" (W) | ( ~26M) 26214400 | 10240 x 2560 x 1 x 1 | IQ2_XXS | 2.0625 | | 405 | blk.23.ffn_gate.weight | Block 23 Feed-Forward Network "Gate" (W) | ( ~26M) 26214400 | 2560 x 10240 x 1 x 1 | IQ2_XXS | 2.0625 | | 406 | blk.23.ffn_norm.weight | Block 23 Feed-Forward Network Normalization (W) | ( ~3K) 2560 | 2560 x 1 x 1 x 1 | F32 | 32.0000 | | 407 | blk.23.ffn_up.weight | Block 23 Feed-Forward Network "Up" (W) | ( ~26M) 26214400 | 2560 x 10240 x 1 x 1 | Q2_K | 2.6250 | | 408 | blk.23.inp_gate.weight | Block 23 Inp_Gate (W) | (~655K) 655360 | 2560 x 256 x 1 x 1 | Q2_K | 2.6250 | | 409 | blk.23.layer_output_scale.weight | Block 23 Layer_Output_Scale (W) | ( 1) 1 | 1 x 1 x 1 x 1 | F32 | 32.0000 | | 410 | blk.23.post_attention_norm.weight | Block 23 Post_Attention_Norm (W) | ( ~3K) 2560 | 2560 x 1 x 1 x 1 | F32 | 32.0000 | | 411 | blk.23.post_ffw_norm.weight | Block 23 Post_Ffw_Norm (W) | ( ~3K) 2560 | 2560 x 1 x 1 x 1 | F32 | 32.0000 | | 412 | blk.23.post_norm.weight | Block 23 Post_Norm (W) | ( ~3K) 2560 | 2560 x 1 x 1 x 1 | F32 | 32.0000 | | 413 | blk.23.proj.weight | Block 23 Proj (W) | (~655K) 655360 | 256 x 2560 x 1 x 1 | Q4_K | 4.5000 | - Total elements in blk.23: (~106M) 106182145 - Percentage of total elements: 1.41% - Bits per Weight (BPW) for blk.23: 2.4275 bits ### Block 24 Tensor Group : ~93M Elements | T_ID | Tensor Layer Name | Human Friendly Tensor Layer Name | Elements | Shape | Type | BPW | | ---: | :-------------------------------- | :---------------------------------------------- | :--------------- | :-------------------- | :------ | ------: | | 414 | blk.24.attn_k.weight | Block 24 Attention Key (W) | ( ~1M) 1310720 | 2560 x 512 x 1 x 1 | Q3_K | 3.4375 | | 415 | blk.24.attn_k_norm.weight | Block 24 Attn_K_Norm (W) | ( 256) 256 | 256 x 1 x 1 x 1 | F32 | 32.0000 | | 416 | blk.24.attn_norm.weight | Block 24 Attention Normalization (W) | ( ~3K) 2560 | 2560 x 1 x 1 x 1 | F32 | 32.0000 | | 417 | blk.24.attn_output.weight | Block 24 Attention Output (W) | ( ~5M) 5242880 | 2048 x 2560 x 1 x 1 | IQ3_XXS | 3.0625 | | 418 | blk.24.attn_q.weight | Block 24 Attention Query (W) | ( ~5M) 5242880 | 2560 x 2048 x 1 x 1 | IQ3_XXS | 3.0625 | | 419 | blk.24.attn_q_norm.weight | Block 24 Attn_Q_Norm (W) | ( 256) 256 | 256 x 1 x 1 x 1 | F32 | 32.0000 | | 420 | blk.24.attn_v.weight | Block 24 Attention Value (W) | ( ~1M) 1310720 | 2560 x 512 x 1 x 1 | Q2_K | 2.6250 | | 421 | blk.24.ffn_down.weight | Block 24 Feed-Forward Network "Down" (W) | ( ~26M) 26214400 | 10240 x 2560 x 1 x 1 | IQ2_XXS | 2.0625 | | 422 | blk.24.ffn_gate.weight | Block 24 Feed-Forward Network "Gate" (W) | ( ~26M) 26214400 | 2560 x 10240 x 1 x 1 | IQ2_XXS | 2.0625 | | 423 | blk.24.ffn_norm.weight | Block 24 Feed-Forward Network Normalization (W) | ( ~3K) 2560 | 2560 x 1 x 1 x 1 | F32 | 32.0000 | | 424 | blk.24.ffn_up.weight | Block 24 Feed-Forward Network "Up" (W) | ( ~26M) 26214400 | 2560 x 10240 x 1 x 1 | Q2_K | 2.6250 | | 425 | blk.24.inp_gate.weight | Block 24 Inp_Gate (W) | (~655K) 655360 | 2560 x 256 x 1 x 1 | Q2_K | 2.6250 | | 426 | blk.24.layer_output_scale.weight | Block 24 Layer_Output_Scale (W) | ( 1) 1 | 1 x 1 x 1 x 1 | F32 | 32.0000 | | 427 | blk.24.post_attention_norm.weight | Block 24 Post_Attention_Norm (W) | ( ~3K) 2560 | 2560 x 1 x 1 x 1 | F32 | 32.0000 | | 428 | blk.24.post_ffw_norm.weight | Block 24 Post_Ffw_Norm (W) | ( ~3K) 2560 | 2560 x 1 x 1 x 1 | F32 | 32.0000 | | 429 | blk.24.post_norm.weight | Block 24 Post_Norm (W) | ( ~3K) 2560 | 2560 x 1 x 1 x 1 | F32 | 32.0000 | | 430 | blk.24.proj.weight | Block 24 Proj (W) | (~655K) 655360 | 256 x 2560 x 1 x 1 | Q2_K | 2.6250 | - Total elements in blk.24: (~93M) 93074433 - Percentage of total elements: 1.24% - Bits per Weight (BPW) for blk.24: 2.3731 bits ### Block 25 Tensor Group : ~93M Elements | T_ID | Tensor Layer Name | Human Friendly Tensor Layer Name | Elements | Shape | Type | BPW | | ---: | :-------------------------------- | :---------------------------------------------- | :--------------- | :-------------------- | :------ | ------: | | 431 | blk.25.attn_k.weight | Block 25 Attention Key (W) | ( ~1M) 1310720 | 2560 x 512 x 1 x 1 | Q3_K | 3.4375 | | 432 | blk.25.attn_k_norm.weight | Block 25 Attn_K_Norm (W) | ( 256) 256 | 256 x 1 x 1 x 1 | F32 | 32.0000 | | 433 | blk.25.attn_norm.weight | Block 25 Attention Normalization (W) | ( ~3K) 2560 | 2560 x 1 x 1 x 1 | F32 | 32.0000 | | 434 | blk.25.attn_output.weight | Block 25 Attention Output (W) | ( ~5M) 5242880 | 2048 x 2560 x 1 x 1 | Q3_K | 3.4375 | | 435 | blk.25.attn_q.weight | Block 25 Attention Query (W) | ( ~5M) 5242880 | 2560 x 2048 x 1 x 1 | Q2_K | 2.6250 | | 436 | blk.25.attn_q_norm.weight | Block 25 Attn_Q_Norm (W) | ( 256) 256 | 256 x 1 x 1 x 1 | F32 | 32.0000 | | 437 | blk.25.attn_v.weight | Block 25 Attention Value (W) | ( ~1M) 1310720 | 2560 x 512 x 1 x 1 | Q2_K | 2.6250 | | 438 | blk.25.ffn_down.weight | Block 25 Feed-Forward Network "Down" (W) | ( ~26M) 26214400 | 10240 x 2560 x 1 x 1 | IQ2_XXS | 2.0625 | | 439 | blk.25.ffn_gate.weight | Block 25 Feed-Forward Network "Gate" (W) | ( ~26M) 26214400 | 2560 x 10240 x 1 x 1 | IQ2_XXS | 2.0625 | | 440 | blk.25.ffn_norm.weight | Block 25 Feed-Forward Network Normalization (W) | ( ~3K) 2560 | 2560 x 1 x 1 x 1 | F32 | 32.0000 | | 441 | blk.25.ffn_up.weight | Block 25 Feed-Forward Network "Up" (W) | ( ~26M) 26214400 | 2560 x 10240 x 1 x 1 | Q2_K | 2.6250 | | 442 | blk.25.inp_gate.weight | Block 25 Inp_Gate (W) | (~655K) 655360 | 2560 x 256 x 1 x 1 | IQ2_XXS | 2.0625 | | 443 | blk.25.layer_output_scale.weight | Block 25 Layer_Output_Scale (W) | ( 1) 1 | 1 x 1 x 1 x 1 | F32 | 32.0000 | | 444 | blk.25.post_attention_norm.weight | Block 25 Post_Attention_Norm (W) | ( ~3K) 2560 | 2560 x 1 x 1 x 1 | F32 | 32.0000 | | 445 | blk.25.post_ffw_norm.weight | Block 25 Post_Ffw_Norm (W) | ( ~3K) 2560 | 2560 x 1 x 1 x 1 | F32 | 32.0000 | | 446 | blk.25.post_norm.weight | Block 25 Post_Norm (W) | ( ~3K) 2560 | 2560 x 1 x 1 x 1 | F32 | 32.0000 | | 447 | blk.25.proj.weight | Block 25 Proj (W) | (~655K) 655360 | 256 x 2560 x 1 x 1 | Q4_K | 4.5000 | - Total elements in blk.25: (~93M) 93074433 - Percentage of total elements: 1.24% - Bits per Weight (BPW) for blk.25: 2.3788 bits ### Block 26 Tensor Group : ~93M Elements | T_ID | Tensor Layer Name | Human Friendly Tensor Layer Name | Elements | Shape | Type | BPW | | ---: | :-------------------------------- | :---------------------------------------------- | :--------------- | :-------------------- | :------ | ------: | | 448 | blk.26.attn_k.weight | Block 26 Attention Key (W) | ( ~1M) 1310720 | 2560 x 512 x 1 x 1 | Q3_K | 3.4375 | | 449 | blk.26.attn_k_norm.weight | Block 26 Attn_K_Norm (W) | ( 256) 256 | 256 x 1 x 1 x 1 | F32 | 32.0000 | | 450 | blk.26.attn_norm.weight | Block 26 Attention Normalization (W) | ( ~3K) 2560 | 2560 x 1 x 1 x 1 | F32 | 32.0000 | | 451 | blk.26.attn_output.weight | Block 26 Attention Output (W) | ( ~5M) 5242880 | 2048 x 2560 x 1 x 1 | IQ3_XXS | 3.0625 | | 452 | blk.26.attn_q.weight | Block 26 Attention Query (W) | ( ~5M) 5242880 | 2560 x 2048 x 1 x 1 | Q2_K | 2.6250 | | 453 | blk.26.attn_q_norm.weight | Block 26 Attn_Q_Norm (W) | ( 256) 256 | 256 x 1 x 1 x 1 | F32 | 32.0000 | | 454 | blk.26.attn_v.weight | Block 26 Attention Value (W) | ( ~1M) 1310720 | 2560 x 512 x 1 x 1 | Q2_K | 2.6250 | | 455 | blk.26.ffn_down.weight | Block 26 Feed-Forward Network "Down" (W) | ( ~26M) 26214400 | 10240 x 2560 x 1 x 1 | IQ2_XXS | 2.0625 | | 456 | blk.26.ffn_gate.weight | Block 26 Feed-Forward Network "Gate" (W) | ( ~26M) 26214400 | 2560 x 10240 x 1 x 1 | IQ2_XXS | 2.0625 | | 457 | blk.26.ffn_norm.weight | Block 26 Feed-Forward Network Normalization (W) | ( ~3K) 2560 | 2560 x 1 x 1 x 1 | F32 | 32.0000 | | 458 | blk.26.ffn_up.weight | Block 26 Feed-Forward Network "Up" (W) | ( ~26M) 26214400 | 2560 x 10240 x 1 x 1 | IQ2_XXS | 2.0625 | | 459 | blk.26.inp_gate.weight | Block 26 Inp_Gate (W) | (~655K) 655360 | 2560 x 256 x 1 x 1 | IQ1_M | 1.7500 | | 460 | blk.26.layer_output_scale.weight | Block 26 Layer_Output_Scale (W) | ( 1) 1 | 1 x 1 x 1 x 1 | F32 | 32.0000 | | 461 | blk.26.post_attention_norm.weight | Block 26 Post_Attention_Norm (W) | ( ~3K) 2560 | 2560 x 1 x 1 x 1 | F32 | 32.0000 | | 462 | blk.26.post_ffw_norm.weight | Block 26 Post_Ffw_Norm (W) | ( ~3K) 2560 | 2560 x 1 x 1 x 1 | F32 | 32.0000 | | 463 | blk.26.post_norm.weight | Block 26 Post_Norm (W) | ( ~3K) 2560 | 2560 x 1 x 1 x 1 | F32 | 32.0000 | | 464 | blk.26.proj.weight | Block 26 Proj (W) | (~655K) 655360 | 256 x 2560 x 1 x 1 | Q4_K | 4.5000 | - Total elements in blk.26: (~93M) 93074433 - Percentage of total elements: 1.24% - Bits per Weight (BPW) for blk.26: 2.1970 bits ### Block 27 Tensor Group : ~93M Elements | T_ID | Tensor Layer Name | Human Friendly Tensor Layer Name | Elements | Shape | Type | BPW | | ---: | :-------------------------------- | :---------------------------------------------- | :--------------- | :-------------------- | :------ | ------: | | 465 | blk.27.attn_k.weight | Block 27 Attention Key (W) | ( ~1M) 1310720 | 2560 x 512 x 1 x 1 | Q3_K | 3.4375 | | 466 | blk.27.attn_k_norm.weight | Block 27 Attn_K_Norm (W) | ( 256) 256 | 256 x 1 x 1 x 1 | F32 | 32.0000 | | 467 | blk.27.attn_norm.weight | Block 27 Attention Normalization (W) | ( ~3K) 2560 | 2560 x 1 x 1 x 1 | F32 | 32.0000 | | 468 | blk.27.attn_output.weight | Block 27 Attention Output (W) | ( ~5M) 5242880 | 2048 x 2560 x 1 x 1 | IQ3_XXS | 3.0625 | | 469 | blk.27.attn_q.weight | Block 27 Attention Query (W) | ( ~5M) 5242880 | 2560 x 2048 x 1 x 1 | Q2_K | 2.6250 | | 470 | blk.27.attn_q_norm.weight | Block 27 Attn_Q_Norm (W) | ( 256) 256 | 256 x 1 x 1 x 1 | F32 | 32.0000 | | 471 | blk.27.attn_v.weight | Block 27 Attention Value (W) | ( ~1M) 1310720 | 2560 x 512 x 1 x 1 | Q2_K | 2.6250 | | 472 | blk.27.ffn_down.weight | Block 27 Feed-Forward Network "Down" (W) | ( ~26M) 26214400 | 10240 x 2560 x 1 x 1 | IQ2_XXS | 2.0625 | | 473 | blk.27.ffn_gate.weight | Block 27 Feed-Forward Network "Gate" (W) | ( ~26M) 26214400 | 2560 x 10240 x 1 x 1 | IQ2_XXS | 2.0625 | | 474 | blk.27.ffn_norm.weight | Block 27 Feed-Forward Network Normalization (W) | ( ~3K) 2560 | 2560 x 1 x 1 x 1 | F32 | 32.0000 | | 475 | blk.27.ffn_up.weight | Block 27 Feed-Forward Network "Up" (W) | ( ~26M) 26214400 | 2560 x 10240 x 1 x 1 | Q2_K | 2.6250 | | 476 | blk.27.inp_gate.weight | Block 27 Inp_Gate (W) | (~655K) 655360 | 2560 x 256 x 1 x 1 | IQ1_M | 1.7500 | | 477 | blk.27.layer_output_scale.weight | Block 27 Layer_Output_Scale (W) | ( 1) 1 | 1 x 1 x 1 x 1 | F32 | 32.0000 | | 478 | blk.27.post_attention_norm.weight | Block 27 Post_Attention_Norm (W) | ( ~3K) 2560 | 2560 x 1 x 1 x 1 | F32 | 32.0000 | | 479 | blk.27.post_ffw_norm.weight | Block 27 Post_Ffw_Norm (W) | ( ~3K) 2560 | 2560 x 1 x 1 x 1 | F32 | 32.0000 | | 480 | blk.27.post_norm.weight | Block 27 Post_Norm (W) | ( ~3K) 2560 | 2560 x 1 x 1 x 1 | F32 | 32.0000 | | 481 | blk.27.proj.weight | Block 27 Proj (W) | (~655K) 655360 | 256 x 2560 x 1 x 1 | Q4_K | 4.5000 | - Total elements in blk.27: (~93M) 93074433 - Percentage of total elements: 1.24% - Bits per Weight (BPW) for blk.27: 2.3555 bits ### Block 28 Tensor Group : ~93M Elements | T_ID | Tensor Layer Name | Human Friendly Tensor Layer Name | Elements | Shape | Type | BPW | | ---: | :-------------------------------- | :---------------------------------------------- | :--------------- | :-------------------- | :------ | ------: | | 482 | blk.28.attn_k.weight | Block 28 Attention Key (W) | ( ~1M) 1310720 | 2560 x 512 x 1 x 1 | Q3_K | 3.4375 | | 483 | blk.28.attn_k_norm.weight | Block 28 Attn_K_Norm (W) | ( 256) 256 | 256 x 1 x 1 x 1 | F32 | 32.0000 | | 484 | blk.28.attn_norm.weight | Block 28 Attention Normalization (W) | ( ~3K) 2560 | 2560 x 1 x 1 x 1 | F32 | 32.0000 | | 485 | blk.28.attn_output.weight | Block 28 Attention Output (W) | ( ~5M) 5242880 | 2048 x 2560 x 1 x 1 | IQ3_XXS | 3.0625 | | 486 | blk.28.attn_q.weight | Block 28 Attention Query (W) | ( ~5M) 5242880 | 2560 x 2048 x 1 x 1 | Q2_K | 2.6250 | | 487 | blk.28.attn_q_norm.weight | Block 28 Attn_Q_Norm (W) | ( 256) 256 | 256 x 1 x 1 x 1 | F32 | 32.0000 | | 488 | blk.28.attn_v.weight | Block 28 Attention Value (W) | ( ~1M) 1310720 | 2560 x 512 x 1 x 1 | Q2_K | 2.6250 | | 489 | blk.28.ffn_down.weight | Block 28 Feed-Forward Network "Down" (W) | ( ~26M) 26214400 | 10240 x 2560 x 1 x 1 | IQ2_XXS | 2.0625 | | 490 | blk.28.ffn_gate.weight | Block 28 Feed-Forward Network "Gate" (W) | ( ~26M) 26214400 | 2560 x 10240 x 1 x 1 | IQ2_XXS | 2.0625 | | 491 | blk.28.ffn_norm.weight | Block 28 Feed-Forward Network Normalization (W) | ( ~3K) 2560 | 2560 x 1 x 1 x 1 | F32 | 32.0000 | | 492 | blk.28.ffn_up.weight | Block 28 Feed-Forward Network "Up" (W) | ( ~26M) 26214400 | 2560 x 10240 x 1 x 1 | IQ2_XXS | 2.0625 | | 493 | blk.28.inp_gate.weight | Block 28 Inp_Gate (W) | (~655K) 655360 | 2560 x 256 x 1 x 1 | IQ1_M | 1.7500 | | 494 | blk.28.layer_output_scale.weight | Block 28 Layer_Output_Scale (W) | ( 1) 1 | 1 x 1 x 1 x 1 | F32 | 32.0000 | | 495 | blk.28.post_attention_norm.weight | Block 28 Post_Attention_Norm (W) | ( ~3K) 2560 | 2560 x 1 x 1 x 1 | F32 | 32.0000 | | 496 | blk.28.post_ffw_norm.weight | Block 28 Post_Ffw_Norm (W) | ( ~3K) 2560 | 2560 x 1 x 1 x 1 | F32 | 32.0000 | | 497 | blk.28.post_norm.weight | Block 28 Post_Norm (W) | ( ~3K) 2560 | 2560 x 1 x 1 x 1 | F32 | 32.0000 | | 498 | blk.28.proj.weight | Block 28 Proj (W) | (~655K) 655360 | 256 x 2560 x 1 x 1 | Q4_K | 4.5000 | - Total elements in blk.28: (~93M) 93074433 - Percentage of total elements: 1.24% - Bits per Weight (BPW) for blk.28: 2.1970 bits ### Block 29 Tensor Group : ~106M Elements | T_ID | Tensor Layer Name | Human Friendly Tensor Layer Name | Elements | Shape | Type | BPW | | ---: | :-------------------------------- | :---------------------------------------------- | :--------------- | :-------------------- | :------ | ------: | | 499 | blk.29.attn_k.weight | Block 29 Attention Key (W) | ( ~3M) 2621440 | 2560 x 1024 x 1 x 1 | Q3_K | 3.4375 | | 500 | blk.29.attn_k_norm.weight | Block 29 Attn_K_Norm (W) | ( 512) 512 | 512 x 1 x 1 x 1 | F32 | 32.0000 | | 501 | blk.29.attn_norm.weight | Block 29 Attention Normalization (W) | ( ~3K) 2560 | 2560 x 1 x 1 x 1 | F32 | 32.0000 | | 502 | blk.29.attn_output.weight | Block 29 Attention Output (W) | ( ~10M) 10485760 | 4096 x 2560 x 1 x 1 | Q2_K | 2.6250 | | 503 | blk.29.attn_q.weight | Block 29 Attention Query (W) | ( ~10M) 10485760 | 2560 x 4096 x 1 x 1 | Q2_K | 2.6250 | | 504 | blk.29.attn_q_norm.weight | Block 29 Attn_Q_Norm (W) | ( 512) 512 | 512 x 1 x 1 x 1 | F32 | 32.0000 | | 505 | blk.29.attn_v.weight | Block 29 Attention Value (W) | ( ~3M) 2621440 | 2560 x 1024 x 1 x 1 | Q2_K | 2.6250 | | 506 | blk.29.ffn_down.weight | Block 29 Feed-Forward Network "Down" (W) | ( ~26M) 26214400 | 10240 x 2560 x 1 x 1 | IQ2_XXS | 2.0625 | | 507 | blk.29.ffn_gate.weight | Block 29 Feed-Forward Network "Gate" (W) | ( ~26M) 26214400 | 2560 x 10240 x 1 x 1 | IQ2_XXS | 2.0625 | | 508 | blk.29.ffn_norm.weight | Block 29 Feed-Forward Network Normalization (W) | ( ~3K) 2560 | 2560 x 1 x 1 x 1 | F32 | 32.0000 | | 509 | blk.29.ffn_up.weight | Block 29 Feed-Forward Network "Up" (W) | ( ~26M) 26214400 | 2560 x 10240 x 1 x 1 | Q2_K | 2.6250 | | 510 | blk.29.inp_gate.weight | Block 29 Inp_Gate (W) | (~655K) 655360 | 2560 x 256 x 1 x 1 | IQ2_XXS | 2.0625 | | 511 | blk.29.layer_output_scale.weight | Block 29 Layer_Output_Scale (W) | ( 1) 1 | 1 x 1 x 1 x 1 | F32 | 32.0000 | | 512 | blk.29.post_attention_norm.weight | Block 29 Post_Attention_Norm (W) | ( ~3K) 2560 | 2560 x 1 x 1 x 1 | F32 | 32.0000 | | 513 | blk.29.post_ffw_norm.weight | Block 29 Post_Ffw_Norm (W) | ( ~3K) 2560 | 2560 x 1 x 1 x 1 | F32 | 32.0000 | | 514 | blk.29.post_norm.weight | Block 29 Post_Norm (W) | ( ~3K) 2560 | 2560 x 1 x 1 x 1 | F32 | 32.0000 | | 515 | blk.29.proj.weight | Block 29 Proj (W) | (~655K) 655360 | 256 x 2560 x 1 x 1 | Q4_K | 4.5000 | - Total elements in blk.29: (~106M) 106182145 - Percentage of total elements: 1.41% - Bits per Weight (BPW) for blk.29: 2.3792 bits ### Block 30 Tensor Group : ~93M Elements | T_ID | Tensor Layer Name | Human Friendly Tensor Layer Name | Elements | Shape | Type | BPW | | ---: | :-------------------------------- | :---------------------------------------------- | :--------------- | :-------------------- | :------ | ------: | | 516 | blk.30.attn_k.weight | Block 30 Attention Key (W) | ( ~1M) 1310720 | 2560 x 512 x 1 x 1 | Q3_K | 3.4375 | | 517 | blk.30.attn_k_norm.weight | Block 30 Attn_K_Norm (W) | ( 256) 256 | 256 x 1 x 1 x 1 | F32 | 32.0000 | | 518 | blk.30.attn_norm.weight | Block 30 Attention Normalization (W) | ( ~3K) 2560 | 2560 x 1 x 1 x 1 | F32 | 32.0000 | | 519 | blk.30.attn_output.weight | Block 30 Attention Output (W) | ( ~5M) 5242880 | 2048 x 2560 x 1 x 1 | IQ3_XXS | 3.0625 | | 520 | blk.30.attn_q.weight | Block 30 Attention Query (W) | ( ~5M) 5242880 | 2560 x 2048 x 1 x 1 | IQ3_XXS | 3.0625 | | 521 | blk.30.attn_q_norm.weight | Block 30 Attn_Q_Norm (W) | ( 256) 256 | 256 x 1 x 1 x 1 | F32 | 32.0000 | | 522 | blk.30.attn_v.weight | Block 30 Attention Value (W) | ( ~1M) 1310720 | 2560 x 512 x 1 x 1 | Q2_K | 2.6250 | | 523 | blk.30.ffn_down.weight | Block 30 Feed-Forward Network "Down" (W) | ( ~26M) 26214400 | 10240 x 2560 x 1 x 1 | IQ2_XS | 2.3125 | | 524 | blk.30.ffn_gate.weight | Block 30 Feed-Forward Network "Gate" (W) | ( ~26M) 26214400 | 2560 x 10240 x 1 x 1 | IQ2_XXS | 2.0625 | | 525 | blk.30.ffn_norm.weight | Block 30 Feed-Forward Network Normalization (W) | ( ~3K) 2560 | 2560 x 1 x 1 x 1 | F32 | 32.0000 | | 526 | blk.30.ffn_up.weight | Block 30 Feed-Forward Network "Up" (W) | ( ~26M) 26214400 | 2560 x 10240 x 1 x 1 | IQ2_XXS | 2.0625 | | 527 | blk.30.inp_gate.weight | Block 30 Inp_Gate (W) | (~655K) 655360 | 2560 x 256 x 1 x 1 | IQ2_XXS | 2.0625 | | 528 | blk.30.layer_output_scale.weight | Block 30 Layer_Output_Scale (W) | ( 1) 1 | 1 x 1 x 1 x 1 | F32 | 32.0000 | | 529 | blk.30.post_attention_norm.weight | Block 30 Post_Attention_Norm (W) | ( ~3K) 2560 | 2560 x 1 x 1 x 1 | F32 | 32.0000 | | 530 | blk.30.post_ffw_norm.weight | Block 30 Post_Ffw_Norm (W) | ( ~3K) 2560 | 2560 x 1 x 1 x 1 | F32 | 32.0000 | | 531 | blk.30.post_norm.weight | Block 30 Post_Norm (W) | ( ~3K) 2560 | 2560 x 1 x 1 x 1 | F32 | 32.0000 | | 532 | blk.30.proj.weight | Block 30 Proj (W) | (~655K) 655360 | 256 x 2560 x 1 x 1 | Q4_K | 4.5000 | - Total elements in blk.30: (~93M) 93074433 - Percentage of total elements: 1.24% - Bits per Weight (BPW) for blk.30: 2.2943 bits ### Block 31 Tensor Group : ~93M Elements | T_ID | Tensor Layer Name | Human Friendly Tensor Layer Name | Elements | Shape | Type | BPW | | ---: | :-------------------------------- | :---------------------------------------------- | :--------------- | :-------------------- | :------ | ------: | | 533 | blk.31.attn_k.weight | Block 31 Attention Key (W) | ( ~1M) 1310720 | 2560 x 512 x 1 x 1 | Q3_K | 3.4375 | | 534 | blk.31.attn_k_norm.weight | Block 31 Attn_K_Norm (W) | ( 256) 256 | 256 x 1 x 1 x 1 | F32 | 32.0000 | | 535 | blk.31.attn_norm.weight | Block 31 Attention Normalization (W) | ( ~3K) 2560 | 2560 x 1 x 1 x 1 | F32 | 32.0000 | | 536 | blk.31.attn_output.weight | Block 31 Attention Output (W) | ( ~5M) 5242880 | 2048 x 2560 x 1 x 1 | IQ3_XXS | 3.0625 | | 537 | blk.31.attn_q.weight | Block 31 Attention Query (W) | ( ~5M) 5242880 | 2560 x 2048 x 1 x 1 | IQ3_XXS | 3.0625 | | 538 | blk.31.attn_q_norm.weight | Block 31 Attn_Q_Norm (W) | ( 256) 256 | 256 x 1 x 1 x 1 | F32 | 32.0000 | | 539 | blk.31.attn_v.weight | Block 31 Attention Value (W) | ( ~1M) 1310720 | 2560 x 512 x 1 x 1 | Q2_K | 2.6250 | | 540 | blk.31.ffn_down.weight | Block 31 Feed-Forward Network "Down" (W) | ( ~26M) 26214400 | 10240 x 2560 x 1 x 1 | Q2_K | 2.6250 | | 541 | blk.31.ffn_gate.weight | Block 31 Feed-Forward Network "Gate" (W) | ( ~26M) 26214400 | 2560 x 10240 x 1 x 1 | IQ2_XXS | 2.0625 | | 542 | blk.31.ffn_norm.weight | Block 31 Feed-Forward Network Normalization (W) | ( ~3K) 2560 | 2560 x 1 x 1 x 1 | F32 | 32.0000 | | 543 | blk.31.ffn_up.weight | Block 31 Feed-Forward Network "Up" (W) | ( ~26M) 26214400 | 2560 x 10240 x 1 x 1 | IQ2_XXS | 2.0625 | | 544 | blk.31.inp_gate.weight | Block 31 Inp_Gate (W) | (~655K) 655360 | 2560 x 256 x 1 x 1 | IQ2_XXS | 2.0625 | | 545 | blk.31.layer_output_scale.weight | Block 31 Layer_Output_Scale (W) | ( 1) 1 | 1 x 1 x 1 x 1 | F32 | 32.0000 | | 546 | blk.31.post_attention_norm.weight | Block 31 Post_Attention_Norm (W) | ( ~3K) 2560 | 2560 x 1 x 1 x 1 | F32 | 32.0000 | | 547 | blk.31.post_ffw_norm.weight | Block 31 Post_Ffw_Norm (W) | ( ~3K) 2560 | 2560 x 1 x 1 x 1 | F32 | 32.0000 | | 548 | blk.31.post_norm.weight | Block 31 Post_Norm (W) | ( ~3K) 2560 | 2560 x 1 x 1 x 1 | F32 | 32.0000 | | 549 | blk.31.proj.weight | Block 31 Proj (W) | (~655K) 655360 | 256 x 2560 x 1 x 1 | Q4_1 | 5.0000 | - Total elements in blk.31: (~93M) 93074433 - Percentage of total elements: 1.24% - Bits per Weight (BPW) for blk.31: 2.3858 bits ### Block 32 Tensor Group : ~93M Elements | T_ID | Tensor Layer Name | Human Friendly Tensor Layer Name | Elements | Shape | Type | BPW | | ---: | :-------------------------------- | :---------------------------------------------- | :--------------- | :-------------------- | :------ | ------: | | 550 | blk.32.attn_k.weight | Block 32 Attention Key (W) | ( ~1M) 1310720 | 2560 x 512 x 1 x 1 | Q3_K | 3.4375 | | 551 | blk.32.attn_k_norm.weight | Block 32 Attn_K_Norm (W) | ( 256) 256 | 256 x 1 x 1 x 1 | F32 | 32.0000 | | 552 | blk.32.attn_norm.weight | Block 32 Attention Normalization (W) | ( ~3K) 2560 | 2560 x 1 x 1 x 1 | F32 | 32.0000 | | 553 | blk.32.attn_output.weight | Block 32 Attention Output (W) | ( ~5M) 5242880 | 2048 x 2560 x 1 x 1 | IQ3_XXS | 3.0625 | | 554 | blk.32.attn_q.weight | Block 32 Attention Query (W) | ( ~5M) 5242880 | 2560 x 2048 x 1 x 1 | IQ2_XS | 2.3125 | | 555 | blk.32.attn_q_norm.weight | Block 32 Attn_Q_Norm (W) | ( 256) 256 | 256 x 1 x 1 x 1 | F32 | 32.0000 | | 556 | blk.32.attn_v.weight | Block 32 Attention Value (W) | ( ~1M) 1310720 | 2560 x 512 x 1 x 1 | Q2_K | 2.6250 | | 557 | blk.32.ffn_down.weight | Block 32 Feed-Forward Network "Down" (W) | ( ~26M) 26214400 | 10240 x 2560 x 1 x 1 | Q2_K | 2.6250 | | 558 | blk.32.ffn_gate.weight | Block 32 Feed-Forward Network "Gate" (W) | ( ~26M) 26214400 | 2560 x 10240 x 1 x 1 | IQ1_M | 1.7500 | | 559 | blk.32.ffn_norm.weight | Block 32 Feed-Forward Network Normalization (W) | ( ~3K) 2560 | 2560 x 1 x 1 x 1 | F32 | 32.0000 | | 560 | blk.32.ffn_up.weight | Block 32 Feed-Forward Network "Up" (W) | ( ~26M) 26214400 | 2560 x 10240 x 1 x 1 | IQ2_XXS | 2.0625 | | 561 | blk.32.inp_gate.weight | Block 32 Inp_Gate (W) | (~655K) 655360 | 2560 x 256 x 1 x 1 | IQ2_XXS | 2.0625 | | 562 | blk.32.layer_output_scale.weight | Block 32 Layer_Output_Scale (W) | ( 1) 1 | 1 x 1 x 1 x 1 | F32 | 32.0000 | | 563 | blk.32.post_attention_norm.weight | Block 32 Post_Attention_Norm (W) | ( ~3K) 2560 | 2560 x 1 x 1 x 1 | F32 | 32.0000 | | 564 | blk.32.post_ffw_norm.weight | Block 32 Post_Ffw_Norm (W) | ( ~3K) 2560 | 2560 x 1 x 1 x 1 | F32 | 32.0000 | | 565 | blk.32.post_norm.weight | Block 32 Post_Norm (W) | ( ~3K) 2560 | 2560 x 1 x 1 x 1 | F32 | 32.0000 | | 566 | blk.32.proj.weight | Block 32 Proj (W) | (~655K) 655360 | 256 x 2560 x 1 x 1 | Q4_1 | 5.0000 | - Total elements in blk.32: (~93M) 93074433 - Percentage of total elements: 1.24% - Bits per Weight (BPW) for blk.32: 2.2556 bits ### Block 33 Tensor Group : ~93M Elements | T_ID | Tensor Layer Name | Human Friendly Tensor Layer Name | Elements | Shape | Type | BPW | | ---: | :-------------------------------- | :---------------------------------------------- | :--------------- | :-------------------- | :------ | ------: | | 567 | blk.33.attn_k.weight | Block 33 Attention Key (W) | ( ~1M) 1310720 | 2560 x 512 x 1 x 1 | Q3_K | 3.4375 | | 568 | blk.33.attn_k_norm.weight | Block 33 Attn_K_Norm (W) | ( 256) 256 | 256 x 1 x 1 x 1 | F32 | 32.0000 | | 569 | blk.33.attn_norm.weight | Block 33 Attention Normalization (W) | ( ~3K) 2560 | 2560 x 1 x 1 x 1 | F32 | 32.0000 | | 570 | blk.33.attn_output.weight | Block 33 Attention Output (W) | ( ~5M) 5242880 | 2048 x 2560 x 1 x 1 | IQ3_XXS | 3.0625 | | 571 | blk.33.attn_q.weight | Block 33 Attention Query (W) | ( ~5M) 5242880 | 2560 x 2048 x 1 x 1 | IQ2_XS | 2.3125 | | 572 | blk.33.attn_q_norm.weight | Block 33 Attn_Q_Norm (W) | ( 256) 256 | 256 x 1 x 1 x 1 | F32 | 32.0000 | | 573 | blk.33.attn_v.weight | Block 33 Attention Value (W) | ( ~1M) 1310720 | 2560 x 512 x 1 x 1 | Q2_K | 2.6250 | | 574 | blk.33.ffn_down.weight | Block 33 Feed-Forward Network "Down" (W) | ( ~26M) 26214400 | 10240 x 2560 x 1 x 1 | Q2_K | 2.6250 | | 575 | blk.33.ffn_gate.weight | Block 33 Feed-Forward Network "Gate" (W) | ( ~26M) 26214400 | 2560 x 10240 x 1 x 1 | IQ1_M | 1.7500 | | 576 | blk.33.ffn_norm.weight | Block 33 Feed-Forward Network Normalization (W) | ( ~3K) 2560 | 2560 x 1 x 1 x 1 | F32 | 32.0000 | | 577 | blk.33.ffn_up.weight | Block 33 Feed-Forward Network "Up" (W) | ( ~26M) 26214400 | 2560 x 10240 x 1 x 1 | IQ2_XXS | 2.0625 | | 578 | blk.33.inp_gate.weight | Block 33 Inp_Gate (W) | (~655K) 655360 | 2560 x 256 x 1 x 1 | IQ2_XXS | 2.0625 | | 579 | blk.33.layer_output_scale.weight | Block 33 Layer_Output_Scale (W) | ( 1) 1 | 1 x 1 x 1 x 1 | F32 | 32.0000 | | 580 | blk.33.post_attention_norm.weight | Block 33 Post_Attention_Norm (W) | ( ~3K) 2560 | 2560 x 1 x 1 x 1 | F32 | 32.0000 | | 581 | blk.33.post_ffw_norm.weight | Block 33 Post_Ffw_Norm (W) | ( ~3K) 2560 | 2560 x 1 x 1 x 1 | F32 | 32.0000 | | 582 | blk.33.post_norm.weight | Block 33 Post_Norm (W) | ( ~3K) 2560 | 2560 x 1 x 1 x 1 | F32 | 32.0000 | | 583 | blk.33.proj.weight | Block 33 Proj (W) | (~655K) 655360 | 256 x 2560 x 1 x 1 | Q4_1 | 5.0000 | - Total elements in blk.33: (~93M) 93074433 - Percentage of total elements: 1.24% - Bits per Weight (BPW) for blk.33: 2.2556 bits ### Block 34 Tensor Group : ~93M Elements | T_ID | Tensor Layer Name | Human Friendly Tensor Layer Name | Elements | Shape | Type | BPW | | ---: | :-------------------------------- | :---------------------------------------------- | :--------------- | :-------------------- | :------ | ------: | | 584 | blk.34.attn_k.weight | Block 34 Attention Key (W) | ( ~1M) 1310720 | 2560 x 512 x 1 x 1 | Q3_K | 3.4375 | | 585 | blk.34.attn_k_norm.weight | Block 34 Attn_K_Norm (W) | ( 256) 256 | 256 x 1 x 1 x 1 | F32 | 32.0000 | | 586 | blk.34.attn_norm.weight | Block 34 Attention Normalization (W) | ( ~3K) 2560 | 2560 x 1 x 1 x 1 | F32 | 32.0000 | | 587 | blk.34.attn_output.weight | Block 34 Attention Output (W) | ( ~5M) 5242880 | 2048 x 2560 x 1 x 1 | IQ3_XXS | 3.0625 | | 588 | blk.34.attn_q.weight | Block 34 Attention Query (W) | ( ~5M) 5242880 | 2560 x 2048 x 1 x 1 | Q2_K | 2.6250 | | 589 | blk.34.attn_q_norm.weight | Block 34 Attn_Q_Norm (W) | ( 256) 256 | 256 x 1 x 1 x 1 | F32 | 32.0000 | | 590 | blk.34.attn_v.weight | Block 34 Attention Value (W) | ( ~1M) 1310720 | 2560 x 512 x 1 x 1 | Q2_K | 2.6250 | | 591 | blk.34.ffn_down.weight | Block 34 Feed-Forward Network "Down" (W) | ( ~26M) 26214400 | 10240 x 2560 x 1 x 1 | Q2_K | 2.6250 | | 592 | blk.34.ffn_gate.weight | Block 34 Feed-Forward Network "Gate" (W) | ( ~26M) 26214400 | 2560 x 10240 x 1 x 1 | IQ2_XXS | 2.0625 | | 593 | blk.34.ffn_norm.weight | Block 34 Feed-Forward Network Normalization (W) | ( ~3K) 2560 | 2560 x 1 x 1 x 1 | F32 | 32.0000 | | 594 | blk.34.ffn_up.weight | Block 34 Feed-Forward Network "Up" (W) | ( ~26M) 26214400 | 2560 x 10240 x 1 x 1 | IQ2_XXS | 2.0625 | | 595 | blk.34.inp_gate.weight | Block 34 Inp_Gate (W) | (~655K) 655360 | 2560 x 256 x 1 x 1 | IQ2_XXS | 2.0625 | | 596 | blk.34.layer_output_scale.weight | Block 34 Layer_Output_Scale (W) | ( 1) 1 | 1 x 1 x 1 x 1 | F32 | 32.0000 | | 597 | blk.34.post_attention_norm.weight | Block 34 Post_Attention_Norm (W) | ( ~3K) 2560 | 2560 x 1 x 1 x 1 | F32 | 32.0000 | | 598 | blk.34.post_ffw_norm.weight | Block 34 Post_Ffw_Norm (W) | ( ~3K) 2560 | 2560 x 1 x 1 x 1 | F32 | 32.0000 | | 599 | blk.34.post_norm.weight | Block 34 Post_Norm (W) | ( ~3K) 2560 | 2560 x 1 x 1 x 1 | F32 | 32.0000 | | 600 | blk.34.proj.weight | Block 34 Proj (W) | (~655K) 655360 | 256 x 2560 x 1 x 1 | Q2_K | 2.6250 | - Total elements in blk.34: (~93M) 93074433 - Percentage of total elements: 1.24% - Bits per Weight (BPW) for blk.34: 2.3445 bits ### Block 35 Tensor Group : ~106M Elements | T_ID | Tensor Layer Name | Human Friendly Tensor Layer Name | Elements | Shape | Type | BPW | | ---: | :-------------------------------- | :---------------------------------------------- | :--------------- | :-------------------- | :------ | ------: | | 601 | blk.35.attn_k.weight | Block 35 Attention Key (W) | ( ~3M) 2621440 | 2560 x 1024 x 1 x 1 | Q3_K | 3.4375 | | 602 | blk.35.attn_k_norm.weight | Block 35 Attn_K_Norm (W) | ( 512) 512 | 512 x 1 x 1 x 1 | F32 | 32.0000 | | 603 | blk.35.attn_norm.weight | Block 35 Attention Normalization (W) | ( ~3K) 2560 | 2560 x 1 x 1 x 1 | F32 | 32.0000 | | 604 | blk.35.attn_output.weight | Block 35 Attention Output (W) | ( ~10M) 10485760 | 4096 x 2560 x 1 x 1 | Q2_K | 2.6250 | | 605 | blk.35.attn_q.weight | Block 35 Attention Query (W) | ( ~10M) 10485760 | 2560 x 4096 x 1 x 1 | Q2_K | 2.6250 | | 606 | blk.35.attn_q_norm.weight | Block 35 Attn_Q_Norm (W) | ( 512) 512 | 512 x 1 x 1 x 1 | F32 | 32.0000 | | 607 | blk.35.attn_v.weight | Block 35 Attention Value (W) | ( ~3M) 2621440 | 2560 x 1024 x 1 x 1 | Q2_K | 2.6250 | | 608 | blk.35.ffn_down.weight | Block 35 Feed-Forward Network "Down" (W) | ( ~26M) 26214400 | 10240 x 2560 x 1 x 1 | Q2_K | 2.6250 | | 609 | blk.35.ffn_gate.weight | Block 35 Feed-Forward Network "Gate" (W) | ( ~26M) 26214400 | 2560 x 10240 x 1 x 1 | IQ2_XXS | 2.0625 | | 610 | blk.35.ffn_norm.weight | Block 35 Feed-Forward Network Normalization (W) | ( ~3K) 2560 | 2560 x 1 x 1 x 1 | F32 | 32.0000 | | 611 | blk.35.ffn_up.weight | Block 35 Feed-Forward Network "Up" (W) | ( ~26M) 26214400 | 2560 x 10240 x 1 x 1 | Q2_K | 2.6250 | | 612 | blk.35.inp_gate.weight | Block 35 Inp_Gate (W) | (~655K) 655360 | 2560 x 256 x 1 x 1 | IQ2_XXS | 2.0625 | | 613 | blk.35.layer_output_scale.weight | Block 35 Layer_Output_Scale (W) | ( 1) 1 | 1 x 1 x 1 x 1 | F32 | 32.0000 | | 614 | blk.35.post_attention_norm.weight | Block 35 Post_Attention_Norm (W) | ( ~3K) 2560 | 2560 x 1 x 1 x 1 | F32 | 32.0000 | | 615 | blk.35.post_ffw_norm.weight | Block 35 Post_Ffw_Norm (W) | ( ~3K) 2560 | 2560 x 1 x 1 x 1 | F32 | 32.0000 | | 616 | blk.35.post_norm.weight | Block 35 Post_Norm (W) | ( ~3K) 2560 | 2560 x 1 x 1 x 1 | F32 | 32.0000 | | 617 | blk.35.proj.weight | Block 35 Proj (W) | (~655K) 655360 | 256 x 2560 x 1 x 1 | Q4_1 | 5.0000 | - Total elements in blk.35: (~106M) 106182145 - Percentage of total elements: 1.41% - Bits per Weight (BPW) for blk.35: 2.5212 bits ### Block 36 Tensor Group : ~93M Elements | T_ID | Tensor Layer Name | Human Friendly Tensor Layer Name | Elements | Shape | Type | BPW | | ---: | :-------------------------------- | :---------------------------------------------- | :--------------- | :-------------------- | :------ | ------: | | 618 | blk.36.attn_k.weight | Block 36 Attention Key (W) | ( ~1M) 1310720 | 2560 x 512 x 1 x 1 | Q3_K | 3.4375 | | 619 | blk.36.attn_k_norm.weight | Block 36 Attn_K_Norm (W) | ( 256) 256 | 256 x 1 x 1 x 1 | F32 | 32.0000 | | 620 | blk.36.attn_norm.weight | Block 36 Attention Normalization (W) | ( ~3K) 2560 | 2560 x 1 x 1 x 1 | F32 | 32.0000 | | 621 | blk.36.attn_output.weight | Block 36 Attention Output (W) | ( ~5M) 5242880 | 2048 x 2560 x 1 x 1 | Q2_K | 2.6250 | | 622 | blk.36.attn_q.weight | Block 36 Attention Query (W) | ( ~5M) 5242880 | 2560 x 2048 x 1 x 1 | IQ2_XS | 2.3125 | | 623 | blk.36.attn_q_norm.weight | Block 36 Attn_Q_Norm (W) | ( 256) 256 | 256 x 1 x 1 x 1 | F32 | 32.0000 | | 624 | blk.36.attn_v.weight | Block 36 Attention Value (W) | ( ~1M) 1310720 | 2560 x 512 x 1 x 1 | Q2_K | 2.6250 | | 625 | blk.36.ffn_down.weight | Block 36 Feed-Forward Network "Down" (W) | ( ~26M) 26214400 | 10240 x 2560 x 1 x 1 | Q2_K | 2.6250 | | 626 | blk.36.ffn_gate.weight | Block 36 Feed-Forward Network "Gate" (W) | ( ~26M) 26214400 | 2560 x 10240 x 1 x 1 | IQ2_XXS | 2.0625 | | 627 | blk.36.ffn_norm.weight | Block 36 Feed-Forward Network Normalization (W) | ( ~3K) 2560 | 2560 x 1 x 1 x 1 | F32 | 32.0000 | | 628 | blk.36.ffn_up.weight | Block 36 Feed-Forward Network "Up" (W) | ( ~26M) 26214400 | 2560 x 10240 x 1 x 1 | IQ2_XXS | 2.0625 | | 629 | blk.36.inp_gate.weight | Block 36 Inp_Gate (W) | (~655K) 655360 | 2560 x 256 x 1 x 1 | IQ2_XXS | 2.0625 | | 630 | blk.36.layer_output_scale.weight | Block 36 Layer_Output_Scale (W) | ( 1) 1 | 1 x 1 x 1 x 1 | F32 | 32.0000 | | 631 | blk.36.post_attention_norm.weight | Block 36 Post_Attention_Norm (W) | ( ~3K) 2560 | 2560 x 1 x 1 x 1 | F32 | 32.0000 | | 632 | blk.36.post_ffw_norm.weight | Block 36 Post_Ffw_Norm (W) | ( ~3K) 2560 | 2560 x 1 x 1 x 1 | F32 | 32.0000 | | 633 | blk.36.post_norm.weight | Block 36 Post_Norm (W) | ( ~3K) 2560 | 2560 x 1 x 1 x 1 | F32 | 32.0000 | | 634 | blk.36.proj.weight | Block 36 Proj (W) | (~655K) 655360 | 256 x 2560 x 1 x 1 | Q2_K | 2.6250 | - Total elements in blk.36: (~93M) 93074433 - Percentage of total elements: 1.24% - Bits per Weight (BPW) for blk.36: 2.3022 bits ### Block 37 Tensor Group : ~93M Elements | T_ID | Tensor Layer Name | Human Friendly Tensor Layer Name | Elements | Shape | Type | BPW | | ---: | :-------------------------------- | :---------------------------------------------- | :--------------- | :-------------------- | :------ | ------: | | 635 | blk.37.attn_k.weight | Block 37 Attention Key (W) | ( ~1M) 1310720 | 2560 x 512 x 1 x 1 | Q3_K | 3.4375 | | 636 | blk.37.attn_k_norm.weight | Block 37 Attn_K_Norm (W) | ( 256) 256 | 256 x 1 x 1 x 1 | F32 | 32.0000 | | 637 | blk.37.attn_norm.weight | Block 37 Attention Normalization (W) | ( ~3K) 2560 | 2560 x 1 x 1 x 1 | F32 | 32.0000 | | 638 | blk.37.attn_output.weight | Block 37 Attention Output (W) | ( ~5M) 5242880 | 2048 x 2560 x 1 x 1 | IQ3_XXS | 3.0625 | | 639 | blk.37.attn_q.weight | Block 37 Attention Query (W) | ( ~5M) 5242880 | 2560 x 2048 x 1 x 1 | IQ2_XS | 2.3125 | | 640 | blk.37.attn_q_norm.weight | Block 37 Attn_Q_Norm (W) | ( 256) 256 | 256 x 1 x 1 x 1 | F32 | 32.0000 | | 641 | blk.37.attn_v.weight | Block 37 Attention Value (W) | ( ~1M) 1310720 | 2560 x 512 x 1 x 1 | Q2_K | 2.6250 | | 642 | blk.37.ffn_down.weight | Block 37 Feed-Forward Network "Down" (W) | ( ~26M) 26214400 | 10240 x 2560 x 1 x 1 | Q2_K | 2.6250 | | 643 | blk.37.ffn_gate.weight | Block 37 Feed-Forward Network "Gate" (W) | ( ~26M) 26214400 | 2560 x 10240 x 1 x 1 | IQ2_XXS | 2.0625 | | 644 | blk.37.ffn_norm.weight | Block 37 Feed-Forward Network Normalization (W) | ( ~3K) 2560 | 2560 x 1 x 1 x 1 | F32 | 32.0000 | | 645 | blk.37.ffn_up.weight | Block 37 Feed-Forward Network "Up" (W) | ( ~26M) 26214400 | 2560 x 10240 x 1 x 1 | IQ2_XXS | 2.0625 | | 646 | blk.37.inp_gate.weight | Block 37 Inp_Gate (W) | (~655K) 655360 | 2560 x 256 x 1 x 1 | IQ2_XXS | 2.0625 | | 647 | blk.37.layer_output_scale.weight | Block 37 Layer_Output_Scale (W) | ( 1) 1 | 1 x 1 x 1 x 1 | F32 | 32.0000 | | 648 | blk.37.post_attention_norm.weight | Block 37 Post_Attention_Norm (W) | ( ~3K) 2560 | 2560 x 1 x 1 x 1 | F32 | 32.0000 | | 649 | blk.37.post_ffw_norm.weight | Block 37 Post_Ffw_Norm (W) | ( ~3K) 2560 | 2560 x 1 x 1 x 1 | F32 | 32.0000 | | 650 | blk.37.post_norm.weight | Block 37 Post_Norm (W) | ( ~3K) 2560 | 2560 x 1 x 1 x 1 | F32 | 32.0000 | | 651 | blk.37.proj.weight | Block 37 Proj (W) | (~655K) 655360 | 256 x 2560 x 1 x 1 | Q4_K | 4.5000 | - Total elements in blk.37: (~93M) 93074433 - Percentage of total elements: 1.24% - Bits per Weight (BPW) for blk.37: 2.3401 bits ### Block 38 Tensor Group : ~93M Elements | T_ID | Tensor Layer Name | Human Friendly Tensor Layer Name | Elements | Shape | Type | BPW | | ---: | :-------------------------------- | :---------------------------------------------- | :--------------- | :-------------------- | :------ | ------: | | 652 | blk.38.attn_k.weight | Block 38 Attention Key (W) | ( ~1M) 1310720 | 2560 x 512 x 1 x 1 | Q3_K | 3.4375 | | 653 | blk.38.attn_k_norm.weight | Block 38 Attn_K_Norm (W) | ( 256) 256 | 256 x 1 x 1 x 1 | F32 | 32.0000 | | 654 | blk.38.attn_norm.weight | Block 38 Attention Normalization (W) | ( ~3K) 2560 | 2560 x 1 x 1 x 1 | F32 | 32.0000 | | 655 | blk.38.attn_output.weight | Block 38 Attention Output (W) | ( ~5M) 5242880 | 2048 x 2560 x 1 x 1 | IQ3_XXS | 3.0625 | | 656 | blk.38.attn_q.weight | Block 38 Attention Query (W) | ( ~5M) 5242880 | 2560 x 2048 x 1 x 1 | IQ2_XS | 2.3125 | | 657 | blk.38.attn_q_norm.weight | Block 38 Attn_Q_Norm (W) | ( 256) 256 | 256 x 1 x 1 x 1 | F32 | 32.0000 | | 658 | blk.38.attn_v.weight | Block 38 Attention Value (W) | ( ~1M) 1310720 | 2560 x 512 x 1 x 1 | Q2_K | 2.6250 | | 659 | blk.38.ffn_down.weight | Block 38 Feed-Forward Network "Down" (W) | ( ~26M) 26214400 | 10240 x 2560 x 1 x 1 | Q2_K | 2.6250 | | 660 | blk.38.ffn_gate.weight | Block 38 Feed-Forward Network "Gate" (W) | ( ~26M) 26214400 | 2560 x 10240 x 1 x 1 | IQ2_XXS | 2.0625 | | 661 | blk.38.ffn_norm.weight | Block 38 Feed-Forward Network Normalization (W) | ( ~3K) 2560 | 2560 x 1 x 1 x 1 | F32 | 32.0000 | | 662 | blk.38.ffn_up.weight | Block 38 Feed-Forward Network "Up" (W) | ( ~26M) 26214400 | 2560 x 10240 x 1 x 1 | IQ2_XXS | 2.0625 | | 663 | blk.38.inp_gate.weight | Block 38 Inp_Gate (W) | (~655K) 655360 | 2560 x 256 x 1 x 1 | IQ2_XXS | 2.0625 | | 664 | blk.38.layer_output_scale.weight | Block 38 Layer_Output_Scale (W) | ( 1) 1 | 1 x 1 x 1 x 1 | F32 | 32.0000 | | 665 | blk.38.post_attention_norm.weight | Block 38 Post_Attention_Norm (W) | ( ~3K) 2560 | 2560 x 1 x 1 x 1 | F32 | 32.0000 | | 666 | blk.38.post_ffw_norm.weight | Block 38 Post_Ffw_Norm (W) | ( ~3K) 2560 | 2560 x 1 x 1 x 1 | F32 | 32.0000 | | 667 | blk.38.post_norm.weight | Block 38 Post_Norm (W) | ( ~3K) 2560 | 2560 x 1 x 1 x 1 | F32 | 32.0000 | | 668 | blk.38.proj.weight | Block 38 Proj (W) | (~655K) 655360 | 256 x 2560 x 1 x 1 | Q4_K | 4.5000 | - Total elements in blk.38: (~93M) 93074433 - Percentage of total elements: 1.24% - Bits per Weight (BPW) for blk.38: 2.3401 bits ### Block 39 Tensor Group : ~93M Elements | T_ID | Tensor Layer Name | Human Friendly Tensor Layer Name | Elements | Shape | Type | BPW | | ---: | :-------------------------------- | :---------------------------------------------- | :--------------- | :-------------------- | :------ | ------: | | 669 | blk.39.attn_k.weight | Block 39 Attention Key (W) | ( ~1M) 1310720 | 2560 x 512 x 1 x 1 | Q3_K | 3.4375 | | 670 | blk.39.attn_k_norm.weight | Block 39 Attn_K_Norm (W) | ( 256) 256 | 256 x 1 x 1 x 1 | F32 | 32.0000 | | 671 | blk.39.attn_norm.weight | Block 39 Attention Normalization (W) | ( ~3K) 2560 | 2560 x 1 x 1 x 1 | F32 | 32.0000 | | 672 | blk.39.attn_output.weight | Block 39 Attention Output (W) | ( ~5M) 5242880 | 2048 x 2560 x 1 x 1 | IQ3_XXS | 3.0625 | | 673 | blk.39.attn_q.weight | Block 39 Attention Query (W) | ( ~5M) 5242880 | 2560 x 2048 x 1 x 1 | IQ2_XS | 2.3125 | | 674 | blk.39.attn_q_norm.weight | Block 39 Attn_Q_Norm (W) | ( 256) 256 | 256 x 1 x 1 x 1 | F32 | 32.0000 | | 675 | blk.39.attn_v.weight | Block 39 Attention Value (W) | ( ~1M) 1310720 | 2560 x 512 x 1 x 1 | Q2_K | 2.6250 | | 676 | blk.39.ffn_down.weight | Block 39 Feed-Forward Network "Down" (W) | ( ~26M) 26214400 | 10240 x 2560 x 1 x 1 | Q2_K | 2.6250 | | 677 | blk.39.ffn_gate.weight | Block 39 Feed-Forward Network "Gate" (W) | ( ~26M) 26214400 | 2560 x 10240 x 1 x 1 | IQ2_XXS | 2.0625 | | 678 | blk.39.ffn_norm.weight | Block 39 Feed-Forward Network Normalization (W) | ( ~3K) 2560 | 2560 x 1 x 1 x 1 | F32 | 32.0000 | | 679 | blk.39.ffn_up.weight | Block 39 Feed-Forward Network "Up" (W) | ( ~26M) 26214400 | 2560 x 10240 x 1 x 1 | IQ2_XXS | 2.0625 | | 680 | blk.39.inp_gate.weight | Block 39 Inp_Gate (W) | (~655K) 655360 | 2560 x 256 x 1 x 1 | IQ2_XXS | 2.0625 | | 681 | blk.39.layer_output_scale.weight | Block 39 Layer_Output_Scale (W) | ( 1) 1 | 1 x 1 x 1 x 1 | F32 | 32.0000 | | 682 | blk.39.post_attention_norm.weight | Block 39 Post_Attention_Norm (W) | ( ~3K) 2560 | 2560 x 1 x 1 x 1 | F32 | 32.0000 | | 683 | blk.39.post_ffw_norm.weight | Block 39 Post_Ffw_Norm (W) | ( ~3K) 2560 | 2560 x 1 x 1 x 1 | F32 | 32.0000 | | 684 | blk.39.post_norm.weight | Block 39 Post_Norm (W) | ( ~3K) 2560 | 2560 x 1 x 1 x 1 | F32 | 32.0000 | | 685 | blk.39.proj.weight | Block 39 Proj (W) | (~655K) 655360 | 256 x 2560 x 1 x 1 | Q4_K | 4.5000 | - Total elements in blk.39: (~93M) 93074433 - Percentage of total elements: 1.24% - Bits per Weight (BPW) for blk.39: 2.3401 bits ### Block 40 Tensor Group : ~93M Elements | T_ID | Tensor Layer Name | Human Friendly Tensor Layer Name | Elements | Shape | Type | BPW | | ---: | :-------------------------------- | :---------------------------------------------- | :--------------- | :-------------------- | :------ | ------: | | 686 | blk.40.attn_k.weight | Block 40 Attention Key (W) | ( ~1M) 1310720 | 2560 x 512 x 1 x 1 | Q3_K | 3.4375 | | 687 | blk.40.attn_k_norm.weight | Block 40 Attn_K_Norm (W) | ( 256) 256 | 256 x 1 x 1 x 1 | F32 | 32.0000 | | 688 | blk.40.attn_norm.weight | Block 40 Attention Normalization (W) | ( ~3K) 2560 | 2560 x 1 x 1 x 1 | F32 | 32.0000 | | 689 | blk.40.attn_output.weight | Block 40 Attention Output (W) | ( ~5M) 5242880 | 2048 x 2560 x 1 x 1 | IQ3_XXS | 3.0625 | | 690 | blk.40.attn_q.weight | Block 40 Attention Query (W) | ( ~5M) 5242880 | 2560 x 2048 x 1 x 1 | IQ2_XS | 2.3125 | | 691 | blk.40.attn_q_norm.weight | Block 40 Attn_Q_Norm (W) | ( 256) 256 | 256 x 1 x 1 x 1 | F32 | 32.0000 | | 692 | blk.40.attn_v.weight | Block 40 Attention Value (W) | ( ~1M) 1310720 | 2560 x 512 x 1 x 1 | Q2_K | 2.6250 | | 693 | blk.40.ffn_down.weight | Block 40 Feed-Forward Network "Down" (W) | ( ~26M) 26214400 | 10240 x 2560 x 1 x 1 | IQ2_XXS | 2.0625 | | 694 | blk.40.ffn_gate.weight | Block 40 Feed-Forward Network "Gate" (W) | ( ~26M) 26214400 | 2560 x 10240 x 1 x 1 | Q2_K | 2.6250 | | 695 | blk.40.ffn_norm.weight | Block 40 Feed-Forward Network Normalization (W) | ( ~3K) 2560 | 2560 x 1 x 1 x 1 | F32 | 32.0000 | | 696 | blk.40.ffn_up.weight | Block 40 Feed-Forward Network "Up" (W) | ( ~26M) 26214400 | 2560 x 10240 x 1 x 1 | Q2_K | 2.6250 | | 697 | blk.40.inp_gate.weight | Block 40 Inp_Gate (W) | (~655K) 655360 | 2560 x 256 x 1 x 1 | IQ1_M | 1.7500 | | 698 | blk.40.layer_output_scale.weight | Block 40 Layer_Output_Scale (W) | ( 1) 1 | 1 x 1 x 1 x 1 | F32 | 32.0000 | | 699 | blk.40.post_attention_norm.weight | Block 40 Post_Attention_Norm (W) | ( ~3K) 2560 | 2560 x 1 x 1 x 1 | F32 | 32.0000 | | 700 | blk.40.post_ffw_norm.weight | Block 40 Post_Ffw_Norm (W) | ( ~3K) 2560 | 2560 x 1 x 1 x 1 | F32 | 32.0000 | | 701 | blk.40.post_norm.weight | Block 40 Post_Norm (W) | ( ~3K) 2560 | 2560 x 1 x 1 x 1 | F32 | 32.0000 | | 702 | blk.40.proj.weight | Block 40 Proj (W) | (~655K) 655360 | 256 x 2560 x 1 x 1 | Q4_1 | 5.0000 | - Total elements in blk.40: (~93M) 93074433 - Percentage of total elements: 1.24% - Bits per Weight (BPW) for blk.40: 2.4998 bits ### Block 41 Tensor Group : ~106M Elements | T_ID | Tensor Layer Name | Human Friendly Tensor Layer Name | Elements | Shape | Type | BPW | | ---: | :-------------------------------- | :---------------------------------------------- | :--------------- | :-------------------- | :------ | ------: | | 703 | blk.41.attn_k.weight | Block 41 Attention Key (W) | ( ~3M) 2621440 | 2560 x 1024 x 1 x 1 | Q3_K | 3.4375 | | 704 | blk.41.attn_k_norm.weight | Block 41 Attn_K_Norm (W) | ( 512) 512 | 512 x 1 x 1 x 1 | F32 | 32.0000 | | 705 | blk.41.attn_norm.weight | Block 41 Attention Normalization (W) | ( ~3K) 2560 | 2560 x 1 x 1 x 1 | F32 | 32.0000 | | 706 | blk.41.attn_output.weight | Block 41 Attention Output (W) | ( ~10M) 10485760 | 4096 x 2560 x 1 x 1 | Q2_K | 2.6250 | | 707 | blk.41.attn_q.weight | Block 41 Attention Query (W) | ( ~10M) 10485760 | 2560 x 4096 x 1 x 1 | IQ2_XS | 2.3125 | | 708 | blk.41.attn_q_norm.weight | Block 41 Attn_Q_Norm (W) | ( 512) 512 | 512 x 1 x 1 x 1 | F32 | 32.0000 | | 709 | blk.41.attn_v.weight | Block 41 Attention Value (W) | ( ~3M) 2621440 | 2560 x 1024 x 1 x 1 | Q2_K | 2.6250 | | 710 | blk.41.ffn_down.weight | Block 41 Feed-Forward Network "Down" (W) | ( ~26M) 26214400 | 10240 x 2560 x 1 x 1 | IQ2_XXS | 2.0625 | | 711 | blk.41.ffn_gate.weight | Block 41 Feed-Forward Network "Gate" (W) | ( ~26M) 26214400 | 2560 x 10240 x 1 x 1 | IQ2_XXS | 2.0625 | | 712 | blk.41.ffn_norm.weight | Block 41 Feed-Forward Network Normalization (W) | ( ~3K) 2560 | 2560 x 1 x 1 x 1 | F32 | 32.0000 | | 713 | blk.41.ffn_up.weight | Block 41 Feed-Forward Network "Up" (W) | ( ~26M) 26214400 | 2560 x 10240 x 1 x 1 | IQ2_XXS | 2.0625 | | 714 | blk.41.inp_gate.weight | Block 41 Inp_Gate (W) | (~655K) 655360 | 2560 x 256 x 1 x 1 | IQ1_M | 1.7500 | | 715 | blk.41.layer_output_scale.weight | Block 41 Layer_Output_Scale (W) | ( 1) 1 | 1 x 1 x 1 x 1 | F32 | 32.0000 | | 716 | blk.41.post_attention_norm.weight | Block 41 Post_Attention_Norm (W) | ( ~3K) 2560 | 2560 x 1 x 1 x 1 | F32 | 32.0000 | | 717 | blk.41.post_ffw_norm.weight | Block 41 Post_Ffw_Norm (W) | ( ~3K) 2560 | 2560 x 1 x 1 x 1 | F32 | 32.0000 | | 718 | blk.41.post_norm.weight | Block 41 Post_Norm (W) | ( ~3K) 2560 | 2560 x 1 x 1 x 1 | F32 | 32.0000 | | 719 | blk.41.proj.weight | Block 41 Proj (W) | (~655K) 655360 | 256 x 2560 x 1 x 1 | Q4_K | 4.5000 | - Total elements in blk.41: (~106M) 106182145 - Percentage of total elements: 1.41% - Bits per Weight (BPW) for blk.41: 2.2076 bits Total BPW for gemma-4-E4B-it-Q2_K.gguf: 2.5000 bits