# Watt-Tool-8B-IQ3_S.gguf - GGUF Internal File Dump - Endian: LITTLE endian ## Key Value Metadata Store There are 43 key-value pairs in this file | POS | TYPE | Count | Key | Value | |----:|:---------|-------:|:---------------------------------------|:--------------------------------------------------------------------| | 1 | UINT32 | 1 | GGUF.version | 3 | | 2 | UINT64 | 1 | GGUF.tensor_count | 292 | | 3 | UINT64 | 1 | GGUF.kv_count | 40 | | 4 | STRING | 1 | general.architecture | `llama` | | 5 | STRING | 1 | general.type | `model` | | 6 | STRING | 1 | general.name | `Watt Tool 8B GGUF` | | 7 | STRING | 1 | general.finetune | `GGUF` | | 8 | STRING | 1 | general.basename | `Watt-Tool` | | 9 | STRING | 1 | general.size_label | `8B` | | 10 | STRING | 1 | general.license | `apache-2.0` | | 11 | UINT32 | 1 | general.base_model.count | 1 | | 12 | STRING | 1 | general.base_model.0.name | `Llama 3.1 8B Instruct` | | 13 | STRING | 1 | general.base_model.0.organization | `Meta Llama` | | 14 | STRING | 1 | general.base_model.0.repo_url | `https://huggingface.co/meta-llama/Llama-3.1-8B-Instruct` | | 15 | [STRING] | 4 | general.tags | [ `function-calling`, `tool-use`, `llama`, `bfcl` ] | | 16 | [STRING] | 1 | general.languages | [ `en` ] | | 17 | UINT32 | 1 | llama.block_count | 32 | | 18 | UINT32 | 1 | llama.context_length | 131072 | | 19 | UINT32 | 1 | llama.embedding_length | 4096 | | 20 | UINT32 | 1 | llama.feed_forward_length | 14336 | | 21 | UINT32 | 1 | llama.attention.head_count | 32 | | 22 | UINT32 | 1 | llama.attention.head_count_kv | 8 | | 23 | FLOAT32 | 1 | llama.rope.freq_base | 500000.0 | | 24 | FLOAT32 | 1 | llama.attention.layer_norm_rms_epsilon | 1e-05 | | 25 | UINT32 | 1 | llama.attention.key_length | 128 | | 26 | UINT32 | 1 | llama.attention.value_length | 128 | | 27 | UINT32 | 1 | llama.vocab_size | 128256 | | 28 | UINT32 | 1 | llama.rope.dimension_count | 128 | | 29 | STRING | 1 | tokenizer.ggml.model | `gpt2` | | 30 | STRING | 1 | tokenizer.ggml.pre | `llama-bpe` | | 31 | [STRING] | 128256 | tokenizer.ggml.tokens | [ `!`, `"`, `#`, `$`, `%`, ... ] | | 32 | [INT32] | 128256 | tokenizer.ggml.token_type | [ 1, 1, 1, 1, 1, 1, 1, ... ] | | 33 | [STRING] | 280147 | tokenizer.ggml.merges | [ `Ġ Ġ`, `Ġ ĠĠĠ`, `ĠĠ ĠĠ`, `ĠĠĠ Ġ`, `i n`, ... ] | | 34 | UINT32 | 1 | tokenizer.ggml.bos_token_id | 128000 | | 35 | UINT32 | 1 | tokenizer.ggml.eos_token_id | 128009 | | 36 | UINT32 | 1 | tokenizer.ggml.padding_token_id | 128009 | | 37 | STRING | 1 | tokenizer.chat_template | `{{ '<|begin_of_text|>' }}{% if`...`d|>' }}{% endif %}{% endfor %}` | | 38 | UINT32 | 1 | general.quantization_version | 2 | | 39 | UINT32 | 1 | general.file_type | 26 | | 40 | STRING | 1 | quantize.imatrix.file | `./imatrix/imatrix-Watt-Tool-8B-small.dat` | | 41 | STRING | 1 | quantize.imatrix.dataset | `../../datasets/imatrix/calibration_eur_small.txt` | | 42 | INT32 | 1 | quantize.imatrix.entries_count | 225 | | 43 | INT32 | 1 | quantize.imatrix.chunks_count | 962 | ## Tensors Overview ~8B Elements Total number of elements in all tensors: 8030261312 Elements - [Watt-Tool-8B-IQ3\_S.gguf - GGUF Internal File Dump](#watt-tool-8b-iq3_sgguf---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 : ~1B Elements](#base-tensor-group--1b-elements) - [Block 0 Tensor Group : ~218M Elements](#block-0-tensor-group--218m-elements) - [Block 1 Tensor Group : ~218M Elements](#block-1-tensor-group--218m-elements) - [Block 2 Tensor Group : ~218M Elements](#block-2-tensor-group--218m-elements) - [Block 3 Tensor Group : ~218M Elements](#block-3-tensor-group--218m-elements) - [Block 4 Tensor Group : ~218M Elements](#block-4-tensor-group--218m-elements) - [Block 5 Tensor Group : ~218M Elements](#block-5-tensor-group--218m-elements) - [Block 6 Tensor Group : ~218M Elements](#block-6-tensor-group--218m-elements) - [Block 7 Tensor Group : ~218M Elements](#block-7-tensor-group--218m-elements) - [Block 8 Tensor Group : ~218M Elements](#block-8-tensor-group--218m-elements) - [Block 9 Tensor Group : ~218M Elements](#block-9-tensor-group--218m-elements) - [Block 10 Tensor Group : ~218M Elements](#block-10-tensor-group--218m-elements) - [Block 11 Tensor Group : ~218M Elements](#block-11-tensor-group--218m-elements) - [Block 12 Tensor Group : ~218M Elements](#block-12-tensor-group--218m-elements) - [Block 13 Tensor Group : ~218M Elements](#block-13-tensor-group--218m-elements) - [Block 14 Tensor Group : ~218M Elements](#block-14-tensor-group--218m-elements) - [Block 15 Tensor Group : ~218M Elements](#block-15-tensor-group--218m-elements) - [Block 16 Tensor Group : ~218M Elements](#block-16-tensor-group--218m-elements) - [Block 17 Tensor Group : ~218M Elements](#block-17-tensor-group--218m-elements) - [Block 18 Tensor Group : ~218M Elements](#block-18-tensor-group--218m-elements) - [Block 19 Tensor Group : ~218M Elements](#block-19-tensor-group--218m-elements) - [Block 20 Tensor Group : ~218M Elements](#block-20-tensor-group--218m-elements) - [Block 21 Tensor Group : ~218M Elements](#block-21-tensor-group--218m-elements) - [Block 22 Tensor Group : ~218M Elements](#block-22-tensor-group--218m-elements) - [Block 23 Tensor Group : ~218M Elements](#block-23-tensor-group--218m-elements) - [Block 24 Tensor Group : ~218M Elements](#block-24-tensor-group--218m-elements) - [Block 25 Tensor Group : ~218M Elements](#block-25-tensor-group--218m-elements) - [Block 26 Tensor Group : ~218M Elements](#block-26-tensor-group--218m-elements) - [Block 27 Tensor Group : ~218M Elements](#block-27-tensor-group--218m-elements) - [Block 28 Tensor Group : ~218M Elements](#block-28-tensor-group--218m-elements) - [Block 29 Tensor Group : ~218M Elements](#block-29-tensor-group--218m-elements) - [Block 30 Tensor Group : ~218M Elements](#block-30-tensor-group--218m-elements) - [Block 31 Tensor Group : ~218M Elements](#block-31-tensor-group--218m-elements) ### Tensor Data Offset This table contains the offset and data segment relative to start of file | T_ID | Tensor Layer Name | Data Offset (B) | Data Size (B) | |-----:|:--------------------------|-----------------:|-----------------:| | 0 | output.weight | 0x779620 | 0xbfca000 | | 1 | output_norm.weight | 0xc743620 | 0x4000 | | 2 | rope_freqs.weight | 0xc747620 | 0x100 | | 3 | token_embd.weight | 0xc747720 | 0xbfca000 | | 4 | blk.0.attn_k.weight | 0x18711720 | 0x188000 | | 5 | blk.0.attn_norm.weight | 0x18899720 | 0x4000 | | 6 | blk.0.attn_output.weight | 0x1889d720 | 0x6e0000 | | 7 | blk.0.attn_q.weight | 0x18f7d720 | 0x620000 | | 8 | blk.0.attn_v.weight | 0x1959d720 | 0x1b8000 | | 9 | blk.0.ffn_down.weight | 0x19755720 | 0x1810000 | | 10 | blk.0.ffn_gate.weight | 0x1af65720 | 0x1570000 | | 11 | blk.0.ffn_norm.weight | 0x1c4d5720 | 0x4000 | | 12 | blk.0.ffn_up.weight | 0x1c4d9720 | 0x1570000 | | 13 | blk.1.attn_k.weight | 0x1da49720 | 0x188000 | | 14 | blk.1.attn_norm.weight | 0x1dbd1720 | 0x4000 | | 15 | blk.1.attn_output.weight | 0x1dbd5720 | 0x6e0000 | | 16 | blk.1.attn_q.weight | 0x1e2b5720 | 0x620000 | | 17 | blk.1.attn_v.weight | 0x1e8d5720 | 0x1b8000 | | 18 | blk.1.ffn_down.weight | 0x1ea8d720 | 0x1f80000 | | 19 | blk.1.ffn_gate.weight | 0x20a0d720 | 0x1570000 | | 20 | blk.1.ffn_norm.weight | 0x21f7d720 | 0x4000 | | 21 | blk.1.ffn_up.weight | 0x21f81720 | 0x1570000 | | 22 | blk.2.attn_k.weight | 0x234f1720 | 0x188000 | | 23 | blk.2.attn_norm.weight | 0x23679720 | 0x4000 | | 24 | blk.2.attn_output.weight | 0x2367d720 | 0x6e0000 | | 25 | blk.2.attn_q.weight | 0x23d5d720 | 0x620000 | | 26 | blk.2.attn_v.weight | 0x2437d720 | 0x1b8000 | | 27 | blk.2.ffn_down.weight | 0x24535720 | 0x1810000 | | 28 | blk.2.ffn_gate.weight | 0x25d45720 | 0x1570000 | | 29 | blk.2.ffn_norm.weight | 0x272b5720 | 0x4000 | | 30 | blk.2.ffn_up.weight | 0x272b9720 | 0x1570000 | | 31 | blk.3.attn_k.weight | 0x28829720 | 0x188000 | | 32 | blk.3.attn_norm.weight | 0x289b1720 | 0x4000 | | 33 | blk.3.attn_output.weight | 0x289b5720 | 0x6e0000 | | 34 | blk.3.attn_q.weight | 0x29095720 | 0x620000 | | 35 | blk.3.attn_v.weight | 0x296b5720 | 0x1b8000 | | 36 | blk.3.ffn_down.weight | 0x2986d720 | 0x1810000 | | 37 | blk.3.ffn_gate.weight | 0x2b07d720 | 0x1570000 | | 38 | blk.3.ffn_norm.weight | 0x2c5ed720 | 0x4000 | | 39 | blk.3.ffn_up.weight | 0x2c5f1720 | 0x1570000 | | 40 | blk.4.attn_k.weight | 0x2db61720 | 0x188000 | | 41 | blk.4.attn_norm.weight | 0x2dce9720 | 0x4000 | | 42 | blk.4.attn_output.weight | 0x2dced720 | 0x6e0000 | | 43 | blk.4.attn_q.weight | 0x2e3cd720 | 0x620000 | | 44 | blk.4.attn_v.weight | 0x2e9ed720 | 0x1b8000 | | 45 | blk.4.ffn_down.weight | 0x2eba5720 | 0x1810000 | | 46 | blk.4.ffn_gate.weight | 0x303b5720 | 0x1570000 | | 47 | blk.4.ffn_norm.weight | 0x31925720 | 0x4000 | | 48 | blk.4.ffn_up.weight | 0x31929720 | 0x1570000 | | 49 | blk.5.attn_k.weight | 0x32e99720 | 0x188000 | | 50 | blk.5.attn_norm.weight | 0x33021720 | 0x4000 | | 51 | blk.5.attn_output.weight | 0x33025720 | 0x6e0000 | | 52 | blk.5.attn_q.weight | 0x33705720 | 0x620000 | | 53 | blk.5.attn_v.weight | 0x33d25720 | 0x1b8000 | | 54 | blk.5.ffn_down.weight | 0x33edd720 | 0x1810000 | | 55 | blk.5.ffn_gate.weight | 0x356ed720 | 0x1570000 | | 56 | blk.5.ffn_norm.weight | 0x36c5d720 | 0x4000 | | 57 | blk.5.ffn_up.weight | 0x36c61720 | 0x1570000 | | 58 | blk.6.attn_k.weight | 0x381d1720 | 0x188000 | | 59 | blk.6.attn_norm.weight | 0x38359720 | 0x4000 | | 60 | blk.6.attn_output.weight | 0x3835d720 | 0x6e0000 | | 61 | blk.6.attn_q.weight | 0x38a3d720 | 0x620000 | | 62 | blk.6.attn_v.weight | 0x3905d720 | 0x1b8000 | | 63 | blk.6.ffn_down.weight | 0x39215720 | 0x1810000 | | 64 | blk.6.ffn_gate.weight | 0x3aa25720 | 0x1570000 | | 65 | blk.6.ffn_norm.weight | 0x3bf95720 | 0x4000 | | 66 | blk.6.ffn_up.weight | 0x3bf99720 | 0x1570000 | | 67 | blk.7.attn_k.weight | 0x3d509720 | 0x188000 | | 68 | blk.7.attn_norm.weight | 0x3d691720 | 0x4000 | | 69 | blk.7.attn_output.weight | 0x3d695720 | 0x6e0000 | | 70 | blk.7.attn_q.weight | 0x3dd75720 | 0x620000 | | 71 | blk.7.attn_v.weight | 0x3e395720 | 0x1b8000 | | 72 | blk.7.ffn_down.weight | 0x3e54d720 | 0x1810000 | | 73 | blk.7.ffn_gate.weight | 0x3fd5d720 | 0x1570000 | | 74 | blk.7.ffn_norm.weight | 0x412cd720 | 0x4000 | | 75 | blk.7.ffn_up.weight | 0x412d1720 | 0x1570000 | | 76 | blk.8.attn_k.weight | 0x42841720 | 0x188000 | | 77 | blk.8.attn_norm.weight | 0x429c9720 | 0x4000 | | 78 | blk.8.attn_output.weight | 0x429cd720 | 0x6e0000 | | 79 | blk.8.attn_q.weight | 0x430ad720 | 0x620000 | | 80 | blk.8.attn_v.weight | 0x436cd720 | 0x1b8000 | | 81 | blk.8.ffn_down.weight | 0x43885720 | 0x1810000 | | 82 | blk.8.ffn_gate.weight | 0x45095720 | 0x1570000 | | 83 | blk.8.ffn_norm.weight | 0x46605720 | 0x4000 | | 84 | blk.8.ffn_up.weight | 0x46609720 | 0x1570000 | | 85 | blk.9.attn_k.weight | 0x47b79720 | 0x188000 | | 86 | blk.9.attn_norm.weight | 0x47d01720 | 0x4000 | | 87 | blk.9.attn_output.weight | 0x47d05720 | 0x6e0000 | | 88 | blk.9.attn_q.weight | 0x483e5720 | 0x620000 | | 89 | blk.9.attn_v.weight | 0x48a05720 | 0x1b8000 | | 90 | blk.9.ffn_down.weight | 0x48bbd720 | 0x1810000 | | 91 | blk.9.ffn_gate.weight | 0x4a3cd720 | 0x1570000 | | 92 | blk.9.ffn_norm.weight | 0x4b93d720 | 0x4000 | | 93 | blk.9.ffn_up.weight | 0x4b941720 | 0x1570000 | | 94 | blk.10.attn_k.weight | 0x4ceb1720 | 0x188000 | | 95 | blk.10.attn_norm.weight | 0x4d039720 | 0x4000 | | 96 | blk.10.attn_output.weight | 0x4d03d720 | 0x6e0000 | | 97 | blk.10.attn_q.weight | 0x4d71d720 | 0x620000 | | 98 | blk.10.attn_v.weight | 0x4dd3d720 | 0x1b8000 | | 99 | blk.10.ffn_down.weight | 0x4def5720 | 0x1810000 | | 100 | blk.10.ffn_gate.weight | 0x4f705720 | 0x1570000 | | 101 | blk.10.ffn_norm.weight | 0x50c75720 | 0x4000 | | 102 | blk.10.ffn_up.weight | 0x50c79720 | 0x1570000 | | 103 | blk.11.attn_k.weight | 0x521e9720 | 0x188000 | | 104 | blk.11.attn_norm.weight | 0x52371720 | 0x4000 | | 105 | blk.11.attn_output.weight | 0x52375720 | 0x6e0000 | | 106 | blk.11.attn_q.weight | 0x52a55720 | 0x620000 | | 107 | blk.11.attn_v.weight | 0x53075720 | 0x1b8000 | | 108 | blk.11.ffn_down.weight | 0x5322d720 | 0x1810000 | | 109 | blk.11.ffn_gate.weight | 0x54a3d720 | 0x1570000 | | 110 | blk.11.ffn_norm.weight | 0x55fad720 | 0x4000 | | 111 | blk.11.ffn_up.weight | 0x55fb1720 | 0x1570000 | | 112 | blk.12.attn_k.weight | 0x57521720 | 0x188000 | | 113 | blk.12.attn_norm.weight | 0x576a9720 | 0x4000 | | 114 | blk.12.attn_output.weight | 0x576ad720 | 0x6e0000 | | 115 | blk.12.attn_q.weight | 0x57d8d720 | 0x620000 | | 116 | blk.12.attn_v.weight | 0x583ad720 | 0x1b8000 | | 117 | blk.12.ffn_down.weight | 0x58565720 | 0x1810000 | | 118 | blk.12.ffn_gate.weight | 0x59d75720 | 0x1570000 | | 119 | blk.12.ffn_norm.weight | 0x5b2e5720 | 0x4000 | | 120 | blk.12.ffn_up.weight | 0x5b2e9720 | 0x1570000 | | 121 | blk.13.attn_k.weight | 0x5c859720 | 0x1b8000 | | 122 | blk.13.attn_norm.weight | 0x5ca11720 | 0x4000 | | 123 | blk.13.attn_output.weight | 0x5ca15720 | 0x6e0000 | | 124 | blk.13.attn_q.weight | 0x5d0f5720 | 0x6e0000 | | 125 | blk.13.attn_v.weight | 0x5d7d5720 | 0x1b8000 | | 126 | blk.13.ffn_down.weight | 0x5d98d720 | 0x1810000 | | 127 | blk.13.ffn_gate.weight | 0x5f19d720 | 0x1570000 | | 128 | blk.13.ffn_norm.weight | 0x6070d720 | 0x4000 | | 129 | blk.13.ffn_up.weight | 0x60711720 | 0x1570000 | | 130 | blk.14.attn_k.weight | 0x61c81720 | 0x1b8000 | | 131 | blk.14.attn_norm.weight | 0x61e39720 | 0x4000 | | 132 | blk.14.attn_output.weight | 0x61e3d720 | 0x6e0000 | | 133 | blk.14.attn_q.weight | 0x6251d720 | 0x6e0000 | | 134 | blk.14.attn_v.weight | 0x62bfd720 | 0x1b8000 | | 135 | blk.14.ffn_down.weight | 0x62db5720 | 0x1810000 | | 136 | blk.14.ffn_gate.weight | 0x645c5720 | 0x1570000 | | 137 | blk.14.ffn_norm.weight | 0x65b35720 | 0x4000 | | 138 | blk.14.ffn_up.weight | 0x65b39720 | 0x1570000 | | 139 | blk.15.attn_k.weight | 0x670a9720 | 0x188000 | | 140 | blk.15.attn_norm.weight | 0x67231720 | 0x4000 | | 141 | blk.15.attn_output.weight | 0x67235720 | 0x6e0000 | | 142 | blk.15.attn_q.weight | 0x67915720 | 0x620000 | | 143 | blk.15.attn_v.weight | 0x67f35720 | 0x1b8000 | | 144 | blk.15.ffn_down.weight | 0x680ed720 | 0x1810000 | | 145 | blk.15.ffn_gate.weight | 0x698fd720 | 0x1570000 | | 146 | blk.15.ffn_norm.weight | 0x6ae6d720 | 0x4000 | | 147 | blk.15.ffn_up.weight | 0x6ae71720 | 0x1570000 | | 148 | blk.16.attn_k.weight | 0x6c3e1720 | 0x1b8000 | | 149 | blk.16.attn_norm.weight | 0x6c599720 | 0x4000 | | 150 | blk.16.attn_output.weight | 0x6c59d720 | 0x6e0000 | | 151 | blk.16.attn_q.weight | 0x6cc7d720 | 0x6e0000 | | 152 | blk.16.attn_v.weight | 0x6d35d720 | 0x1b8000 | | 153 | blk.16.ffn_down.weight | 0x6d515720 | 0x1810000 | | 154 | blk.16.ffn_gate.weight | 0x6ed25720 | 0x1810000 | | 155 | blk.16.ffn_norm.weight | 0x70535720 | 0x4000 | | 156 | blk.16.ffn_up.weight | 0x70539720 | 0x1810000 | | 157 | blk.17.attn_k.weight | 0x71d49720 | 0x188000 | | 158 | blk.17.attn_norm.weight | 0x71ed1720 | 0x4000 | | 159 | blk.17.attn_output.weight | 0x71ed5720 | 0x6e0000 | | 160 | blk.17.attn_q.weight | 0x725b5720 | 0x620000 | | 161 | blk.17.attn_v.weight | 0x72bd5720 | 0x1b8000 | | 162 | blk.17.ffn_down.weight | 0x72d8d720 | 0x1f80000 | | 163 | blk.17.ffn_gate.weight | 0x74d0d720 | 0x1810000 | | 164 | blk.17.ffn_norm.weight | 0x7651d720 | 0x4000 | | 165 | blk.17.ffn_up.weight | 0x76521720 | 0x1810000 | | 166 | blk.18.attn_k.weight | 0x77d31720 | 0x1b8000 | | 167 | blk.18.attn_norm.weight | 0x77ee9720 | 0x4000 | | 168 | blk.18.attn_output.weight | 0x77eed720 | 0x6e0000 | | 169 | blk.18.attn_q.weight | 0x785cd720 | 0x6e0000 | | 170 | blk.18.attn_v.weight | 0x78cad720 | 0x1b8000 | | 171 | blk.18.ffn_down.weight | 0x78e65720 | 0x1f80000 | | 172 | blk.18.ffn_gate.weight | 0x7ade5720 | 0x1810000 | | 173 | blk.18.ffn_norm.weight | 0x7c5f5720 | 0x4000 | | 174 | blk.18.ffn_up.weight | 0x7c5f9720 | 0x1810000 | | 175 | blk.19.attn_k.weight | 0x7de09720 | 0x1b8000 | | 176 | blk.19.attn_norm.weight | 0x7dfc1720 | 0x4000 | | 177 | blk.19.attn_output.weight | 0x7dfc5720 | 0x6e0000 | | 178 | blk.19.attn_q.weight | 0x7e6a5720 | 0x6e0000 | | 179 | blk.19.attn_v.weight | 0x7ed85720 | 0x1b8000 | | 180 | blk.19.ffn_down.weight | 0x7ef3d720 | 0x1f80000 | | 181 | blk.19.ffn_gate.weight | 0x80ebd720 | 0x1810000 | | 182 | blk.19.ffn_norm.weight | 0x826cd720 | 0x4000 | | 183 | blk.19.ffn_up.weight | 0x826d1720 | 0x1810000 | | 184 | blk.20.attn_k.weight | 0x83ee1720 | 0x1b8000 | | 185 | blk.20.attn_norm.weight | 0x84099720 | 0x4000 | | 186 | blk.20.attn_output.weight | 0x8409d720 | 0x6e0000 | | 187 | blk.20.attn_q.weight | 0x8477d720 | 0x6e0000 | | 188 | blk.20.attn_v.weight | 0x84e5d720 | 0x1b8000 | | 189 | blk.20.ffn_down.weight | 0x85015720 | 0x1f80000 | | 190 | blk.20.ffn_gate.weight | 0x86f95720 | 0x1810000 | | 191 | blk.20.ffn_norm.weight | 0x887a5720 | 0x4000 | | 192 | blk.20.ffn_up.weight | 0x887a9720 | 0x1810000 | | 193 | blk.21.attn_k.weight | 0x89fb9720 | 0x1b8000 | | 194 | blk.21.attn_norm.weight | 0x8a171720 | 0x4000 | | 195 | blk.21.attn_output.weight | 0x8a175720 | 0x6e0000 | | 196 | blk.21.attn_q.weight | 0x8a855720 | 0x6e0000 | | 197 | blk.21.attn_v.weight | 0x8af35720 | 0x1b8000 | | 198 | blk.21.ffn_down.weight | 0x8b0ed720 | 0x1f80000 | | 199 | blk.21.ffn_gate.weight | 0x8d06d720 | 0x1810000 | | 200 | blk.21.ffn_norm.weight | 0x8e87d720 | 0x4000 | | 201 | blk.21.ffn_up.weight | 0x8e881720 | 0x1810000 | | 202 | blk.22.attn_k.weight | 0x90091720 | 0x1b8000 | | 203 | blk.22.attn_norm.weight | 0x90249720 | 0x4000 | | 204 | blk.22.attn_output.weight | 0x9024d720 | 0x6e0000 | | 205 | blk.22.attn_q.weight | 0x9092d720 | 0x6e0000 | | 206 | blk.22.attn_v.weight | 0x9100d720 | 0x1b8000 | | 207 | blk.22.ffn_down.weight | 0x911c5720 | 0x1f80000 | | 208 | blk.22.ffn_gate.weight | 0x93145720 | 0x1810000 | | 209 | blk.22.ffn_norm.weight | 0x94955720 | 0x4000 | | 210 | blk.22.ffn_up.weight | 0x94959720 | 0x1810000 | | 211 | blk.23.attn_k.weight | 0x96169720 | 0x1b8000 | | 212 | blk.23.attn_norm.weight | 0x96321720 | 0x4000 | | 213 | blk.23.attn_output.weight | 0x96325720 | 0x6e0000 | | 214 | blk.23.attn_q.weight | 0x96a05720 | 0x6e0000 | | 215 | blk.23.attn_v.weight | 0x970e5720 | 0x1b8000 | | 216 | blk.23.ffn_down.weight | 0x9729d720 | 0x1f80000 | | 217 | blk.23.ffn_gate.weight | 0x9921d720 | 0x1810000 | | 218 | blk.23.ffn_norm.weight | 0x9aa2d720 | 0x4000 | | 219 | blk.23.ffn_up.weight | 0x9aa31720 | 0x1810000 | | 220 | blk.24.attn_k.weight | 0x9c241720 | 0x1b8000 | | 221 | blk.24.attn_norm.weight | 0x9c3f9720 | 0x4000 | | 222 | blk.24.attn_output.weight | 0x9c3fd720 | 0x6e0000 | | 223 | blk.24.attn_q.weight | 0x9cadd720 | 0x6e0000 | | 224 | blk.24.attn_v.weight | 0x9d1bd720 | 0x1b8000 | | 225 | blk.24.ffn_down.weight | 0x9d375720 | 0x1f80000 | | 226 | blk.24.ffn_gate.weight | 0x9f2f5720 | 0x1810000 | | 227 | blk.24.ffn_norm.weight | 0xa0b05720 | 0x4000 | | 228 | blk.24.ffn_up.weight | 0xa0b09720 | 0x1810000 | | 229 | blk.25.attn_k.weight | 0xa2319720 | 0x1b8000 | | 230 | blk.25.attn_norm.weight | 0xa24d1720 | 0x4000 | | 231 | blk.25.attn_output.weight | 0xa24d5720 | 0x6e0000 | | 232 | blk.25.attn_q.weight | 0xa2bb5720 | 0x6e0000 | | 233 | blk.25.attn_v.weight | 0xa3295720 | 0x1b8000 | | 234 | blk.25.ffn_down.weight | 0xa344d720 | 0x1f80000 | | 235 | blk.25.ffn_gate.weight | 0xa53cd720 | 0x1810000 | | 236 | blk.25.ffn_norm.weight | 0xa6bdd720 | 0x4000 | | 237 | blk.25.ffn_up.weight | 0xa6be1720 | 0x1810000 | | 238 | blk.26.attn_k.weight | 0xa83f1720 | 0x1b8000 | | 239 | blk.26.attn_norm.weight | 0xa85a9720 | 0x4000 | | 240 | blk.26.attn_output.weight | 0xa85ad720 | 0x6e0000 | | 241 | blk.26.attn_q.weight | 0xa8c8d720 | 0x6e0000 | | 242 | blk.26.attn_v.weight | 0xa936d720 | 0x1b8000 | | 243 | blk.26.ffn_down.weight | 0xa9525720 | 0x1f80000 | | 244 | blk.26.ffn_gate.weight | 0xab4a5720 | 0x1810000 | | 245 | blk.26.ffn_norm.weight | 0xaccb5720 | 0x4000 | | 246 | blk.26.ffn_up.weight | 0xaccb9720 | 0x1810000 | | 247 | blk.27.attn_k.weight | 0xae4c9720 | 0x1b8000 | | 248 | blk.27.attn_norm.weight | 0xae681720 | 0x4000 | | 249 | blk.27.attn_output.weight | 0xae685720 | 0x6e0000 | | 250 | blk.27.attn_q.weight | 0xaed65720 | 0x6e0000 | | 251 | blk.27.attn_v.weight | 0xaf445720 | 0x1b8000 | | 252 | blk.27.ffn_down.weight | 0xaf5fd720 | 0x1f80000 | | 253 | blk.27.ffn_gate.weight | 0xb157d720 | 0x1810000 | | 254 | blk.27.ffn_norm.weight | 0xb2d8d720 | 0x4000 | | 255 | blk.27.ffn_up.weight | 0xb2d91720 | 0x1810000 | | 256 | blk.28.attn_k.weight | 0xb45a1720 | 0x1b8000 | | 257 | blk.28.attn_norm.weight | 0xb4759720 | 0x4000 | | 258 | blk.28.attn_output.weight | 0xb475d720 | 0x6e0000 | | 259 | blk.28.attn_q.weight | 0xb4e3d720 | 0x6e0000 | | 260 | blk.28.attn_v.weight | 0xb551d720 | 0x1b8000 | | 261 | blk.28.ffn_down.weight | 0xb56d5720 | 0x1f80000 | | 262 | blk.28.ffn_gate.weight | 0xb7655720 | 0x1810000 | | 263 | blk.28.ffn_norm.weight | 0xb8e65720 | 0x4000 | | 264 | blk.28.ffn_up.weight | 0xb8e69720 | 0x1810000 | | 265 | blk.29.attn_k.weight | 0xba679720 | 0x1b8000 | | 266 | blk.29.attn_norm.weight | 0xba831720 | 0x4000 | | 267 | blk.29.attn_output.weight | 0xba835720 | 0x6e0000 | | 268 | blk.29.attn_q.weight | 0xbaf15720 | 0x6e0000 | | 269 | blk.29.attn_v.weight | 0xbb5f5720 | 0x1b8000 | | 270 | blk.29.ffn_down.weight | 0xbb7ad720 | 0x1f80000 | | 271 | blk.29.ffn_gate.weight | 0xbd72d720 | 0x1810000 | | 272 | blk.29.ffn_norm.weight | 0xbef3d720 | 0x4000 | | 273 | blk.29.ffn_up.weight | 0xbef41720 | 0x1810000 | | 274 | blk.30.attn_k.weight | 0xc0751720 | 0x1b8000 | | 275 | blk.30.attn_norm.weight | 0xc0909720 | 0x4000 | | 276 | blk.30.attn_output.weight | 0xc090d720 | 0x6e0000 | | 277 | blk.30.attn_q.weight | 0xc0fed720 | 0x6e0000 | | 278 | blk.30.attn_v.weight | 0xc16cd720 | 0x1b8000 | | 279 | blk.30.ffn_down.weight | 0xc1885720 | 0x1f80000 | | 280 | blk.30.ffn_gate.weight | 0xc3805720 | 0x1810000 | | 281 | blk.30.ffn_norm.weight | 0xc5015720 | 0x4000 | | 282 | blk.30.ffn_up.weight | 0xc5019720 | 0x1810000 | | 283 | blk.31.attn_k.weight | 0xc6829720 | 0x188000 | | 284 | blk.31.attn_norm.weight | 0xc69b1720 | 0x4000 | | 285 | blk.31.attn_output.weight | 0xc69b5720 | 0x6e0000 | | 286 | blk.31.attn_q.weight | 0xc7095720 | 0x620000 | | 287 | blk.31.attn_v.weight | 0xc76b5720 | 0x1b8000 | | 288 | blk.31.ffn_down.weight | 0xc786d720 | 0x1f80000 | | 289 | blk.31.ffn_gate.weight | 0xc97ed720 | 0x1810000 | | 290 | blk.31.ffn_norm.weight | 0xcaffd720 | 0x4000 | | 291 | blk.31.ffn_up.weight | 0xcb001720 | 0x1810000 | ### Base Tensor Group : ~1B Elements | T_ID | Tensor Layer Name | Human Friendly Tensor Layer Name | Elements | Shape | Type | |-----:|:-------------------|:---------------------------------|:------------------|:----------------------|:--------| | 0 | output.weight | Output (W) | (~525M) 525336576 | 4096 x 128256 x 1 x 1 | IQ3_XXS | | 1 | output_norm.weight | Output Normalization (W) | ( ~4K) 4096 | 4096 x 1 x 1 x 1 | F32 | | 2 | rope_freqs.weight | Rope_Freqs (W) | ( 64) 64 | 64 x 1 x 1 x 1 | F32 | | 3 | token_embd.weight | Token Embedding (W) | (~525M) 525336576 | 4096 x 128256 x 1 x 1 | IQ3_XXS | - Total elements in base: ( ~1B) 1050677312 - Percentage of total elements: 13.08% ### Block 0 Tensor Group : ~218M Elements | T_ID | Tensor Layer Name | Human Friendly Tensor Layer Name | Elements | Shape | Type | |-----:|:-------------------------|:-----------------------------------------------|:----------------|:----------------------|:--------| | 4 | blk.0.attn_k.weight | Block 0 Attention Key (W) | ( ~4M) 4194304 | 4096 x 1024 x 1 x 1 | IQ3_XXS | | 5 | blk.0.attn_norm.weight | Block 0 Attention Normalization (W) | ( ~4K) 4096 | 4096 x 1 x 1 x 1 | F32 | | 6 | blk.0.attn_output.weight | Block 0 Attention Output (W) | (~17M) 16777216 | 4096 x 4096 x 1 x 1 | IQ3_S | | 7 | blk.0.attn_q.weight | Block 0 Attention Query (W) | (~17M) 16777216 | 4096 x 4096 x 1 x 1 | IQ3_XXS | | 8 | blk.0.attn_v.weight | Block 0 Attention Value (W) | ( ~4M) 4194304 | 4096 x 1024 x 1 x 1 | IQ3_S | | 9 | blk.0.ffn_down.weight | Block 0 Feed-Forward Network "Down" (W) | (~59M) 58720256 | 14336 x 4096 x 1 x 1 | IQ3_S | | 10 | blk.0.ffn_gate.weight | Block 0 Feed-Forward Network "Gate" (W) | (~59M) 58720256 | 4096 x 14336 x 1 x 1 | IQ3_XXS | | 11 | blk.0.ffn_norm.weight | Block 0 Feed-Forward Network Normalization (W) | ( ~4K) 4096 | 4096 x 1 x 1 x 1 | F32 | | 12 | blk.0.ffn_up.weight | Block 0 Feed-Forward Network "Up" (W) | (~59M) 58720256 | 4096 x 14336 x 1 x 1 | IQ3_XXS | - Total elements in blk.0: (~218M) 218112000 - Percentage of total elements: 2.72% ### Block 1 Tensor Group : ~218M Elements | T_ID | Tensor Layer Name | Human Friendly Tensor Layer Name | Elements | Shape | Type | |-----:|:-------------------------|:-----------------------------------------------|:----------------|:----------------------|:--------| | 13 | blk.1.attn_k.weight | Block 1 Attention Key (W) | ( ~4M) 4194304 | 4096 x 1024 x 1 x 1 | IQ3_XXS | | 14 | blk.1.attn_norm.weight | Block 1 Attention Normalization (W) | ( ~4K) 4096 | 4096 x 1 x 1 x 1 | F32 | | 15 | blk.1.attn_output.weight | Block 1 Attention Output (W) | (~17M) 16777216 | 4096 x 4096 x 1 x 1 | IQ3_S | | 16 | blk.1.attn_q.weight | Block 1 Attention Query (W) | (~17M) 16777216 | 4096 x 4096 x 1 x 1 | IQ3_XXS | | 17 | blk.1.attn_v.weight | Block 1 Attention Value (W) | ( ~4M) 4194304 | 4096 x 1024 x 1 x 1 | IQ3_S | | 18 | blk.1.ffn_down.weight | Block 1 Feed-Forward Network "Down" (W) | (~59M) 58720256 | 14336 x 4096 x 1 x 1 | IQ4_NL | | 19 | blk.1.ffn_gate.weight | Block 1 Feed-Forward Network "Gate" (W) | (~59M) 58720256 | 4096 x 14336 x 1 x 1 | IQ3_XXS | | 20 | blk.1.ffn_norm.weight | Block 1 Feed-Forward Network Normalization (W) | ( ~4K) 4096 | 4096 x 1 x 1 x 1 | F32 | | 21 | blk.1.ffn_up.weight | Block 1 Feed-Forward Network "Up" (W) | (~59M) 58720256 | 4096 x 14336 x 1 x 1 | IQ3_XXS | - Total elements in blk.1: (~218M) 218112000 - Percentage of total elements: 2.72% ### Block 2 Tensor Group : ~218M Elements | T_ID | Tensor Layer Name | Human Friendly Tensor Layer Name | Elements | Shape | Type | |-----:|:-------------------------|:-----------------------------------------------|:----------------|:----------------------|:--------| | 22 | blk.2.attn_k.weight | Block 2 Attention Key (W) | ( ~4M) 4194304 | 4096 x 1024 x 1 x 1 | IQ3_XXS | | 23 | blk.2.attn_norm.weight | Block 2 Attention Normalization (W) | ( ~4K) 4096 | 4096 x 1 x 1 x 1 | F32 | | 24 | blk.2.attn_output.weight | Block 2 Attention Output (W) | (~17M) 16777216 | 4096 x 4096 x 1 x 1 | IQ3_S | | 25 | blk.2.attn_q.weight | Block 2 Attention Query (W) | (~17M) 16777216 | 4096 x 4096 x 1 x 1 | IQ3_XXS | | 26 | blk.2.attn_v.weight | Block 2 Attention Value (W) | ( ~4M) 4194304 | 4096 x 1024 x 1 x 1 | IQ3_S | | 27 | blk.2.ffn_down.weight | Block 2 Feed-Forward Network "Down" (W) | (~59M) 58720256 | 14336 x 4096 x 1 x 1 | IQ3_S | | 28 | blk.2.ffn_gate.weight | Block 2 Feed-Forward Network "Gate" (W) | (~59M) 58720256 | 4096 x 14336 x 1 x 1 | IQ3_XXS | | 29 | blk.2.ffn_norm.weight | Block 2 Feed-Forward Network Normalization (W) | ( ~4K) 4096 | 4096 x 1 x 1 x 1 | F32 | | 30 | blk.2.ffn_up.weight | Block 2 Feed-Forward Network "Up" (W) | (~59M) 58720256 | 4096 x 14336 x 1 x 1 | IQ3_XXS | - Total elements in blk.2: (~218M) 218112000 - Percentage of total elements: 2.72% ### Block 3 Tensor Group : ~218M Elements | T_ID | Tensor Layer Name | Human Friendly Tensor Layer Name | Elements | Shape | Type | |-----:|:-------------------------|:-----------------------------------------------|:----------------|:----------------------|:--------| | 31 | blk.3.attn_k.weight | Block 3 Attention Key (W) | ( ~4M) 4194304 | 4096 x 1024 x 1 x 1 | IQ3_XXS | | 32 | blk.3.attn_norm.weight | Block 3 Attention Normalization (W) | ( ~4K) 4096 | 4096 x 1 x 1 x 1 | F32 | | 33 | blk.3.attn_output.weight | Block 3 Attention Output (W) | (~17M) 16777216 | 4096 x 4096 x 1 x 1 | IQ3_S | | 34 | blk.3.attn_q.weight | Block 3 Attention Query (W) | (~17M) 16777216 | 4096 x 4096 x 1 x 1 | IQ3_XXS | | 35 | blk.3.attn_v.weight | Block 3 Attention Value (W) | ( ~4M) 4194304 | 4096 x 1024 x 1 x 1 | IQ3_S | | 36 | blk.3.ffn_down.weight | Block 3 Feed-Forward Network "Down" (W) | (~59M) 58720256 | 14336 x 4096 x 1 x 1 | IQ3_S | | 37 | blk.3.ffn_gate.weight | Block 3 Feed-Forward Network "Gate" (W) | (~59M) 58720256 | 4096 x 14336 x 1 x 1 | IQ3_XXS | | 38 | blk.3.ffn_norm.weight | Block 3 Feed-Forward Network Normalization (W) | ( ~4K) 4096 | 4096 x 1 x 1 x 1 | F32 | | 39 | blk.3.ffn_up.weight | Block 3 Feed-Forward Network "Up" (W) | (~59M) 58720256 | 4096 x 14336 x 1 x 1 | IQ3_XXS | - Total elements in blk.3: (~218M) 218112000 - Percentage of total elements: 2.72% ### Block 4 Tensor Group : ~218M Elements | T_ID | Tensor Layer Name | Human Friendly Tensor Layer Name | Elements | Shape | Type | |-----:|:-------------------------|:-----------------------------------------------|:----------------|:----------------------|:--------| | 40 | blk.4.attn_k.weight | Block 4 Attention Key (W) | ( ~4M) 4194304 | 4096 x 1024 x 1 x 1 | IQ3_XXS | | 41 | blk.4.attn_norm.weight | Block 4 Attention Normalization (W) | ( ~4K) 4096 | 4096 x 1 x 1 x 1 | F32 | | 42 | blk.4.attn_output.weight | Block 4 Attention Output (W) | (~17M) 16777216 | 4096 x 4096 x 1 x 1 | IQ3_S | | 43 | blk.4.attn_q.weight | Block 4 Attention Query (W) | (~17M) 16777216 | 4096 x 4096 x 1 x 1 | IQ3_XXS | | 44 | blk.4.attn_v.weight | Block 4 Attention Value (W) | ( ~4M) 4194304 | 4096 x 1024 x 1 x 1 | IQ3_S | | 45 | blk.4.ffn_down.weight | Block 4 Feed-Forward Network "Down" (W) | (~59M) 58720256 | 14336 x 4096 x 1 x 1 | IQ3_S | | 46 | blk.4.ffn_gate.weight | Block 4 Feed-Forward Network "Gate" (W) | (~59M) 58720256 | 4096 x 14336 x 1 x 1 | IQ3_XXS | | 47 | blk.4.ffn_norm.weight | Block 4 Feed-Forward Network Normalization (W) | ( ~4K) 4096 | 4096 x 1 x 1 x 1 | F32 | | 48 | blk.4.ffn_up.weight | Block 4 Feed-Forward Network "Up" (W) | (~59M) 58720256 | 4096 x 14336 x 1 x 1 | IQ3_XXS | - Total elements in blk.4: (~218M) 218112000 - Percentage of total elements: 2.72% ### Block 5 Tensor Group : ~218M Elements | T_ID | Tensor Layer Name | Human Friendly Tensor Layer Name | Elements | Shape | Type | |-----:|:-------------------------|:-----------------------------------------------|:----------------|:----------------------|:--------| | 49 | blk.5.attn_k.weight | Block 5 Attention Key (W) | ( ~4M) 4194304 | 4096 x 1024 x 1 x 1 | IQ3_XXS | | 50 | blk.5.attn_norm.weight | Block 5 Attention Normalization (W) | ( ~4K) 4096 | 4096 x 1 x 1 x 1 | F32 | | 51 | blk.5.attn_output.weight | Block 5 Attention Output (W) | (~17M) 16777216 | 4096 x 4096 x 1 x 1 | IQ3_S | | 52 | blk.5.attn_q.weight | Block 5 Attention Query (W) | (~17M) 16777216 | 4096 x 4096 x 1 x 1 | IQ3_XXS | | 53 | blk.5.attn_v.weight | Block 5 Attention Value (W) | ( ~4M) 4194304 | 4096 x 1024 x 1 x 1 | IQ3_S | | 54 | blk.5.ffn_down.weight | Block 5 Feed-Forward Network "Down" (W) | (~59M) 58720256 | 14336 x 4096 x 1 x 1 | IQ3_S | | 55 | blk.5.ffn_gate.weight | Block 5 Feed-Forward Network "Gate" (W) | (~59M) 58720256 | 4096 x 14336 x 1 x 1 | IQ3_XXS | | 56 | blk.5.ffn_norm.weight | Block 5 Feed-Forward Network Normalization (W) | ( ~4K) 4096 | 4096 x 1 x 1 x 1 | F32 | | 57 | blk.5.ffn_up.weight | Block 5 Feed-Forward Network "Up" (W) | (~59M) 58720256 | 4096 x 14336 x 1 x 1 | IQ3_XXS | - Total elements in blk.5: (~218M) 218112000 - Percentage of total elements: 2.72% ### Block 6 Tensor Group : ~218M Elements | T_ID | Tensor Layer Name | Human Friendly Tensor Layer Name | Elements | Shape | Type | |-----:|:-------------------------|:-----------------------------------------------|:----------------|:----------------------|:--------| | 58 | blk.6.attn_k.weight | Block 6 Attention Key (W) | ( ~4M) 4194304 | 4096 x 1024 x 1 x 1 | IQ3_XXS | | 59 | blk.6.attn_norm.weight | Block 6 Attention Normalization (W) | ( ~4K) 4096 | 4096 x 1 x 1 x 1 | F32 | | 60 | blk.6.attn_output.weight | Block 6 Attention Output (W) | (~17M) 16777216 | 4096 x 4096 x 1 x 1 | IQ3_S | | 61 | blk.6.attn_q.weight | Block 6 Attention Query (W) | (~17M) 16777216 | 4096 x 4096 x 1 x 1 | IQ3_XXS | | 62 | blk.6.attn_v.weight | Block 6 Attention Value (W) | ( ~4M) 4194304 | 4096 x 1024 x 1 x 1 | IQ3_S | | 63 | blk.6.ffn_down.weight | Block 6 Feed-Forward Network "Down" (W) | (~59M) 58720256 | 14336 x 4096 x 1 x 1 | IQ3_S | | 64 | blk.6.ffn_gate.weight | Block 6 Feed-Forward Network "Gate" (W) | (~59M) 58720256 | 4096 x 14336 x 1 x 1 | IQ3_XXS | | 65 | blk.6.ffn_norm.weight | Block 6 Feed-Forward Network Normalization (W) | ( ~4K) 4096 | 4096 x 1 x 1 x 1 | F32 | | 66 | blk.6.ffn_up.weight | Block 6 Feed-Forward Network "Up" (W) | (~59M) 58720256 | 4096 x 14336 x 1 x 1 | IQ3_XXS | - Total elements in blk.6: (~218M) 218112000 - Percentage of total elements: 2.72% ### Block 7 Tensor Group : ~218M Elements | T_ID | Tensor Layer Name | Human Friendly Tensor Layer Name | Elements | Shape | Type | |-----:|:-------------------------|:-----------------------------------------------|:----------------|:----------------------|:--------| | 67 | blk.7.attn_k.weight | Block 7 Attention Key (W) | ( ~4M) 4194304 | 4096 x 1024 x 1 x 1 | IQ3_XXS | | 68 | blk.7.attn_norm.weight | Block 7 Attention Normalization (W) | ( ~4K) 4096 | 4096 x 1 x 1 x 1 | F32 | | 69 | blk.7.attn_output.weight | Block 7 Attention Output (W) | (~17M) 16777216 | 4096 x 4096 x 1 x 1 | IQ3_S | | 70 | blk.7.attn_q.weight | Block 7 Attention Query (W) | (~17M) 16777216 | 4096 x 4096 x 1 x 1 | IQ3_XXS | | 71 | blk.7.attn_v.weight | Block 7 Attention Value (W) | ( ~4M) 4194304 | 4096 x 1024 x 1 x 1 | IQ3_S | | 72 | blk.7.ffn_down.weight | Block 7 Feed-Forward Network "Down" (W) | (~59M) 58720256 | 14336 x 4096 x 1 x 1 | IQ3_S | | 73 | blk.7.ffn_gate.weight | Block 7 Feed-Forward Network "Gate" (W) | (~59M) 58720256 | 4096 x 14336 x 1 x 1 | IQ3_XXS | | 74 | blk.7.ffn_norm.weight | Block 7 Feed-Forward Network Normalization (W) | ( ~4K) 4096 | 4096 x 1 x 1 x 1 | F32 | | 75 | blk.7.ffn_up.weight | Block 7 Feed-Forward Network "Up" (W) | (~59M) 58720256 | 4096 x 14336 x 1 x 1 | IQ3_XXS | - Total elements in blk.7: (~218M) 218112000 - Percentage of total elements: 2.72% ### Block 8 Tensor Group : ~218M Elements | T_ID | Tensor Layer Name | Human Friendly Tensor Layer Name | Elements | Shape | Type | |-----:|:-------------------------|:-----------------------------------------------|:----------------|:----------------------|:--------| | 76 | blk.8.attn_k.weight | Block 8 Attention Key (W) | ( ~4M) 4194304 | 4096 x 1024 x 1 x 1 | IQ3_XXS | | 77 | blk.8.attn_norm.weight | Block 8 Attention Normalization (W) | ( ~4K) 4096 | 4096 x 1 x 1 x 1 | F32 | | 78 | blk.8.attn_output.weight | Block 8 Attention Output (W) | (~17M) 16777216 | 4096 x 4096 x 1 x 1 | IQ3_S | | 79 | blk.8.attn_q.weight | Block 8 Attention Query (W) | (~17M) 16777216 | 4096 x 4096 x 1 x 1 | IQ3_XXS | | 80 | blk.8.attn_v.weight | Block 8 Attention Value (W) | ( ~4M) 4194304 | 4096 x 1024 x 1 x 1 | IQ3_S | | 81 | blk.8.ffn_down.weight | Block 8 Feed-Forward Network "Down" (W) | (~59M) 58720256 | 14336 x 4096 x 1 x 1 | IQ3_S | | 82 | blk.8.ffn_gate.weight | Block 8 Feed-Forward Network "Gate" (W) | (~59M) 58720256 | 4096 x 14336 x 1 x 1 | IQ3_XXS | | 83 | blk.8.ffn_norm.weight | Block 8 Feed-Forward Network Normalization (W) | ( ~4K) 4096 | 4096 x 1 x 1 x 1 | F32 | | 84 | blk.8.ffn_up.weight | Block 8 Feed-Forward Network "Up" (W) | (~59M) 58720256 | 4096 x 14336 x 1 x 1 | IQ3_XXS | - Total elements in blk.8: (~218M) 218112000 - Percentage of total elements: 2.72% ### Block 9 Tensor Group : ~218M Elements | T_ID | Tensor Layer Name | Human Friendly Tensor Layer Name | Elements | Shape | Type | |-----:|:-------------------------|:-----------------------------------------------|:----------------|:----------------------|:--------| | 85 | blk.9.attn_k.weight | Block 9 Attention Key (W) | ( ~4M) 4194304 | 4096 x 1024 x 1 x 1 | IQ3_XXS | | 86 | blk.9.attn_norm.weight | Block 9 Attention Normalization (W) | ( ~4K) 4096 | 4096 x 1 x 1 x 1 | F32 | | 87 | blk.9.attn_output.weight | Block 9 Attention Output (W) | (~17M) 16777216 | 4096 x 4096 x 1 x 1 | IQ3_S | | 88 | blk.9.attn_q.weight | Block 9 Attention Query (W) | (~17M) 16777216 | 4096 x 4096 x 1 x 1 | IQ3_XXS | | 89 | blk.9.attn_v.weight | Block 9 Attention Value (W) | ( ~4M) 4194304 | 4096 x 1024 x 1 x 1 | IQ3_S | | 90 | blk.9.ffn_down.weight | Block 9 Feed-Forward Network "Down" (W) | (~59M) 58720256 | 14336 x 4096 x 1 x 1 | IQ3_S | | 91 | blk.9.ffn_gate.weight | Block 9 Feed-Forward Network "Gate" (W) | (~59M) 58720256 | 4096 x 14336 x 1 x 1 | IQ3_XXS | | 92 | blk.9.ffn_norm.weight | Block 9 Feed-Forward Network Normalization (W) | ( ~4K) 4096 | 4096 x 1 x 1 x 1 | F32 | | 93 | blk.9.ffn_up.weight | Block 9 Feed-Forward Network "Up" (W) | (~59M) 58720256 | 4096 x 14336 x 1 x 1 | IQ3_XXS | - Total elements in blk.9: (~218M) 218112000 - Percentage of total elements: 2.72% ### Block 10 Tensor Group : ~218M Elements | T_ID | Tensor Layer Name | Human Friendly Tensor Layer Name | Elements | Shape | Type | |-----:|:--------------------------|:------------------------------------------------|:----------------|:----------------------|:--------| | 94 | blk.10.attn_k.weight | Block 10 Attention Key (W) | ( ~4M) 4194304 | 4096 x 1024 x 1 x 1 | IQ3_XXS | | 95 | blk.10.attn_norm.weight | Block 10 Attention Normalization (W) | ( ~4K) 4096 | 4096 x 1 x 1 x 1 | F32 | | 96 | blk.10.attn_output.weight | Block 10 Attention Output (W) | (~17M) 16777216 | 4096 x 4096 x 1 x 1 | IQ3_S | | 97 | blk.10.attn_q.weight | Block 10 Attention Query (W) | (~17M) 16777216 | 4096 x 4096 x 1 x 1 | IQ3_XXS | | 98 | blk.10.attn_v.weight | Block 10 Attention Value (W) | ( ~4M) 4194304 | 4096 x 1024 x 1 x 1 | IQ3_S | | 99 | blk.10.ffn_down.weight | Block 10 Feed-Forward Network "Down" (W) | (~59M) 58720256 | 14336 x 4096 x 1 x 1 | IQ3_S | | 100 | blk.10.ffn_gate.weight | Block 10 Feed-Forward Network "Gate" (W) | (~59M) 58720256 | 4096 x 14336 x 1 x 1 | IQ3_XXS | | 101 | blk.10.ffn_norm.weight | Block 10 Feed-Forward Network Normalization (W) | ( ~4K) 4096 | 4096 x 1 x 1 x 1 | F32 | | 102 | blk.10.ffn_up.weight | Block 10 Feed-Forward Network "Up" (W) | (~59M) 58720256 | 4096 x 14336 x 1 x 1 | IQ3_XXS | - Total elements in blk.10: (~218M) 218112000 - Percentage of total elements: 2.72% ### Block 11 Tensor Group : ~218M Elements | T_ID | Tensor Layer Name | Human Friendly Tensor Layer Name | Elements | Shape | Type | |-----:|:--------------------------|:------------------------------------------------|:----------------|:----------------------|:--------| | 103 | blk.11.attn_k.weight | Block 11 Attention Key (W) | ( ~4M) 4194304 | 4096 x 1024 x 1 x 1 | IQ3_XXS | | 104 | blk.11.attn_norm.weight | Block 11 Attention Normalization (W) | ( ~4K) 4096 | 4096 x 1 x 1 x 1 | F32 | | 105 | blk.11.attn_output.weight | Block 11 Attention Output (W) | (~17M) 16777216 | 4096 x 4096 x 1 x 1 | IQ3_S | | 106 | blk.11.attn_q.weight | Block 11 Attention Query (W) | (~17M) 16777216 | 4096 x 4096 x 1 x 1 | IQ3_XXS | | 107 | blk.11.attn_v.weight | Block 11 Attention Value (W) | ( ~4M) 4194304 | 4096 x 1024 x 1 x 1 | IQ3_S | | 108 | blk.11.ffn_down.weight | Block 11 Feed-Forward Network "Down" (W) | (~59M) 58720256 | 14336 x 4096 x 1 x 1 | IQ3_S | | 109 | blk.11.ffn_gate.weight | Block 11 Feed-Forward Network "Gate" (W) | (~59M) 58720256 | 4096 x 14336 x 1 x 1 | IQ3_XXS | | 110 | blk.11.ffn_norm.weight | Block 11 Feed-Forward Network Normalization (W) | ( ~4K) 4096 | 4096 x 1 x 1 x 1 | F32 | | 111 | blk.11.ffn_up.weight | Block 11 Feed-Forward Network "Up" (W) | (~59M) 58720256 | 4096 x 14336 x 1 x 1 | IQ3_XXS | - Total elements in blk.11: (~218M) 218112000 - Percentage of total elements: 2.72% ### Block 12 Tensor Group : ~218M Elements | T_ID | Tensor Layer Name | Human Friendly Tensor Layer Name | Elements | Shape | Type | |-----:|:--------------------------|:------------------------------------------------|:----------------|:----------------------|:--------| | 112 | blk.12.attn_k.weight | Block 12 Attention Key (W) | ( ~4M) 4194304 | 4096 x 1024 x 1 x 1 | IQ3_XXS | | 113 | blk.12.attn_norm.weight | Block 12 Attention Normalization (W) | ( ~4K) 4096 | 4096 x 1 x 1 x 1 | F32 | | 114 | blk.12.attn_output.weight | Block 12 Attention Output (W) | (~17M) 16777216 | 4096 x 4096 x 1 x 1 | IQ3_S | | 115 | blk.12.attn_q.weight | Block 12 Attention Query (W) | (~17M) 16777216 | 4096 x 4096 x 1 x 1 | IQ3_XXS | | 116 | blk.12.attn_v.weight | Block 12 Attention Value (W) | ( ~4M) 4194304 | 4096 x 1024 x 1 x 1 | IQ3_S | | 117 | blk.12.ffn_down.weight | Block 12 Feed-Forward Network "Down" (W) | (~59M) 58720256 | 14336 x 4096 x 1 x 1 | IQ3_S | | 118 | blk.12.ffn_gate.weight | Block 12 Feed-Forward Network "Gate" (W) | (~59M) 58720256 | 4096 x 14336 x 1 x 1 | IQ3_XXS | | 119 | blk.12.ffn_norm.weight | Block 12 Feed-Forward Network Normalization (W) | ( ~4K) 4096 | 4096 x 1 x 1 x 1 | F32 | | 120 | blk.12.ffn_up.weight | Block 12 Feed-Forward Network "Up" (W) | (~59M) 58720256 | 4096 x 14336 x 1 x 1 | IQ3_XXS | - Total elements in blk.12: (~218M) 218112000 - Percentage of total elements: 2.72% ### Block 13 Tensor Group : ~218M Elements | T_ID | Tensor Layer Name | Human Friendly Tensor Layer Name | Elements | Shape | Type | |-----:|:--------------------------|:------------------------------------------------|:----------------|:----------------------|:--------| | 121 | blk.13.attn_k.weight | Block 13 Attention Key (W) | ( ~4M) 4194304 | 4096 x 1024 x 1 x 1 | IQ3_S | | 122 | blk.13.attn_norm.weight | Block 13 Attention Normalization (W) | ( ~4K) 4096 | 4096 x 1 x 1 x 1 | F32 | | 123 | blk.13.attn_output.weight | Block 13 Attention Output (W) | (~17M) 16777216 | 4096 x 4096 x 1 x 1 | IQ3_S | | 124 | blk.13.attn_q.weight | Block 13 Attention Query (W) | (~17M) 16777216 | 4096 x 4096 x 1 x 1 | IQ3_S | | 125 | blk.13.attn_v.weight | Block 13 Attention Value (W) | ( ~4M) 4194304 | 4096 x 1024 x 1 x 1 | IQ3_S | | 126 | blk.13.ffn_down.weight | Block 13 Feed-Forward Network "Down" (W) | (~59M) 58720256 | 14336 x 4096 x 1 x 1 | IQ3_S | | 127 | blk.13.ffn_gate.weight | Block 13 Feed-Forward Network "Gate" (W) | (~59M) 58720256 | 4096 x 14336 x 1 x 1 | IQ3_XXS | | 128 | blk.13.ffn_norm.weight | Block 13 Feed-Forward Network Normalization (W) | ( ~4K) 4096 | 4096 x 1 x 1 x 1 | F32 | | 129 | blk.13.ffn_up.weight | Block 13 Feed-Forward Network "Up" (W) | (~59M) 58720256 | 4096 x 14336 x 1 x 1 | IQ3_XXS | - Total elements in blk.13: (~218M) 218112000 - Percentage of total elements: 2.72% ### Block 14 Tensor Group : ~218M Elements | T_ID | Tensor Layer Name | Human Friendly Tensor Layer Name | Elements | Shape | Type | |-----:|:--------------------------|:------------------------------------------------|:----------------|:----------------------|:--------| | 130 | blk.14.attn_k.weight | Block 14 Attention Key (W) | ( ~4M) 4194304 | 4096 x 1024 x 1 x 1 | IQ3_S | | 131 | blk.14.attn_norm.weight | Block 14 Attention Normalization (W) | ( ~4K) 4096 | 4096 x 1 x 1 x 1 | F32 | | 132 | blk.14.attn_output.weight | Block 14 Attention Output (W) | (~17M) 16777216 | 4096 x 4096 x 1 x 1 | IQ3_S | | 133 | blk.14.attn_q.weight | Block 14 Attention Query (W) | (~17M) 16777216 | 4096 x 4096 x 1 x 1 | IQ3_S | | 134 | blk.14.attn_v.weight | Block 14 Attention Value (W) | ( ~4M) 4194304 | 4096 x 1024 x 1 x 1 | IQ3_S | | 135 | blk.14.ffn_down.weight | Block 14 Feed-Forward Network "Down" (W) | (~59M) 58720256 | 14336 x 4096 x 1 x 1 | IQ3_S | | 136 | blk.14.ffn_gate.weight | Block 14 Feed-Forward Network "Gate" (W) | (~59M) 58720256 | 4096 x 14336 x 1 x 1 | IQ3_XXS | | 137 | blk.14.ffn_norm.weight | Block 14 Feed-Forward Network Normalization (W) | ( ~4K) 4096 | 4096 x 1 x 1 x 1 | F32 | | 138 | blk.14.ffn_up.weight | Block 14 Feed-Forward Network "Up" (W) | (~59M) 58720256 | 4096 x 14336 x 1 x 1 | IQ3_XXS | - Total elements in blk.14: (~218M) 218112000 - Percentage of total elements: 2.72% ### Block 15 Tensor Group : ~218M Elements | T_ID | Tensor Layer Name | Human Friendly Tensor Layer Name | Elements | Shape | Type | |-----:|:--------------------------|:------------------------------------------------|:----------------|:----------------------|:--------| | 139 | blk.15.attn_k.weight | Block 15 Attention Key (W) | ( ~4M) 4194304 | 4096 x 1024 x 1 x 1 | IQ3_XXS | | 140 | blk.15.attn_norm.weight | Block 15 Attention Normalization (W) | ( ~4K) 4096 | 4096 x 1 x 1 x 1 | F32 | | 141 | blk.15.attn_output.weight | Block 15 Attention Output (W) | (~17M) 16777216 | 4096 x 4096 x 1 x 1 | IQ3_S | | 142 | blk.15.attn_q.weight | Block 15 Attention Query (W) | (~17M) 16777216 | 4096 x 4096 x 1 x 1 | IQ3_XXS | | 143 | blk.15.attn_v.weight | Block 15 Attention Value (W) | ( ~4M) 4194304 | 4096 x 1024 x 1 x 1 | IQ3_S | | 144 | blk.15.ffn_down.weight | Block 15 Feed-Forward Network "Down" (W) | (~59M) 58720256 | 14336 x 4096 x 1 x 1 | IQ3_S | | 145 | blk.15.ffn_gate.weight | Block 15 Feed-Forward Network "Gate" (W) | (~59M) 58720256 | 4096 x 14336 x 1 x 1 | IQ3_XXS | | 146 | blk.15.ffn_norm.weight | Block 15 Feed-Forward Network Normalization (W) | ( ~4K) 4096 | 4096 x 1 x 1 x 1 | F32 | | 147 | blk.15.ffn_up.weight | Block 15 Feed-Forward Network "Up" (W) | (~59M) 58720256 | 4096 x 14336 x 1 x 1 | IQ3_XXS | - Total elements in blk.15: (~218M) 218112000 - Percentage of total elements: 2.72% ### Block 16 Tensor Group : ~218M Elements | T_ID | Tensor Layer Name | Human Friendly Tensor Layer Name | Elements | Shape | Type | |-----:|:--------------------------|:------------------------------------------------|:----------------|:----------------------|:------| | 148 | blk.16.attn_k.weight | Block 16 Attention Key (W) | ( ~4M) 4194304 | 4096 x 1024 x 1 x 1 | IQ3_S | | 149 | blk.16.attn_norm.weight | Block 16 Attention Normalization (W) | ( ~4K) 4096 | 4096 x 1 x 1 x 1 | F32 | | 150 | blk.16.attn_output.weight | Block 16 Attention Output (W) | (~17M) 16777216 | 4096 x 4096 x 1 x 1 | IQ3_S | | 151 | blk.16.attn_q.weight | Block 16 Attention Query (W) | (~17M) 16777216 | 4096 x 4096 x 1 x 1 | IQ3_S | | 152 | blk.16.attn_v.weight | Block 16 Attention Value (W) | ( ~4M) 4194304 | 4096 x 1024 x 1 x 1 | IQ3_S | | 153 | blk.16.ffn_down.weight | Block 16 Feed-Forward Network "Down" (W) | (~59M) 58720256 | 14336 x 4096 x 1 x 1 | IQ3_S | | 154 | blk.16.ffn_gate.weight | Block 16 Feed-Forward Network "Gate" (W) | (~59M) 58720256 | 4096 x 14336 x 1 x 1 | IQ3_S | | 155 | blk.16.ffn_norm.weight | Block 16 Feed-Forward Network Normalization (W) | ( ~4K) 4096 | 4096 x 1 x 1 x 1 | F32 | | 156 | blk.16.ffn_up.weight | Block 16 Feed-Forward Network "Up" (W) | (~59M) 58720256 | 4096 x 14336 x 1 x 1 | IQ3_S | - Total elements in blk.16: (~218M) 218112000 - Percentage of total elements: 2.72% ### Block 17 Tensor Group : ~218M Elements | T_ID | Tensor Layer Name | Human Friendly Tensor Layer Name | Elements | Shape | Type | |-----:|:--------------------------|:------------------------------------------------|:----------------|:----------------------|:--------| | 157 | blk.17.attn_k.weight | Block 17 Attention Key (W) | ( ~4M) 4194304 | 4096 x 1024 x 1 x 1 | IQ3_XXS | | 158 | blk.17.attn_norm.weight | Block 17 Attention Normalization (W) | ( ~4K) 4096 | 4096 x 1 x 1 x 1 | F32 | | 159 | blk.17.attn_output.weight | Block 17 Attention Output (W) | (~17M) 16777216 | 4096 x 4096 x 1 x 1 | IQ3_S | | 160 | blk.17.attn_q.weight | Block 17 Attention Query (W) | (~17M) 16777216 | 4096 x 4096 x 1 x 1 | IQ3_XXS | | 161 | blk.17.attn_v.weight | Block 17 Attention Value (W) | ( ~4M) 4194304 | 4096 x 1024 x 1 x 1 | IQ3_S | | 162 | blk.17.ffn_down.weight | Block 17 Feed-Forward Network "Down" (W) | (~59M) 58720256 | 14336 x 4096 x 1 x 1 | IQ4_NL | | 163 | blk.17.ffn_gate.weight | Block 17 Feed-Forward Network "Gate" (W) | (~59M) 58720256 | 4096 x 14336 x 1 x 1 | IQ3_S | | 164 | blk.17.ffn_norm.weight | Block 17 Feed-Forward Network Normalization (W) | ( ~4K) 4096 | 4096 x 1 x 1 x 1 | F32 | | 165 | blk.17.ffn_up.weight | Block 17 Feed-Forward Network "Up" (W) | (~59M) 58720256 | 4096 x 14336 x 1 x 1 | IQ3_S | - Total elements in blk.17: (~218M) 218112000 - Percentage of total elements: 2.72% ### Block 18 Tensor Group : ~218M Elements | T_ID | Tensor Layer Name | Human Friendly Tensor Layer Name | Elements | Shape | Type | |-----:|:--------------------------|:------------------------------------------------|:----------------|:----------------------|:-------| | 166 | blk.18.attn_k.weight | Block 18 Attention Key (W) | ( ~4M) 4194304 | 4096 x 1024 x 1 x 1 | IQ3_S | | 167 | blk.18.attn_norm.weight | Block 18 Attention Normalization (W) | ( ~4K) 4096 | 4096 x 1 x 1 x 1 | F32 | | 168 | blk.18.attn_output.weight | Block 18 Attention Output (W) | (~17M) 16777216 | 4096 x 4096 x 1 x 1 | IQ3_S | | 169 | blk.18.attn_q.weight | Block 18 Attention Query (W) | (~17M) 16777216 | 4096 x 4096 x 1 x 1 | IQ3_S | | 170 | blk.18.attn_v.weight | Block 18 Attention Value (W) | ( ~4M) 4194304 | 4096 x 1024 x 1 x 1 | IQ3_S | | 171 | blk.18.ffn_down.weight | Block 18 Feed-Forward Network "Down" (W) | (~59M) 58720256 | 14336 x 4096 x 1 x 1 | IQ4_NL | | 172 | blk.18.ffn_gate.weight | Block 18 Feed-Forward Network "Gate" (W) | (~59M) 58720256 | 4096 x 14336 x 1 x 1 | IQ3_S | | 173 | blk.18.ffn_norm.weight | Block 18 Feed-Forward Network Normalization (W) | ( ~4K) 4096 | 4096 x 1 x 1 x 1 | F32 | | 174 | blk.18.ffn_up.weight | Block 18 Feed-Forward Network "Up" (W) | (~59M) 58720256 | 4096 x 14336 x 1 x 1 | IQ3_S | - Total elements in blk.18: (~218M) 218112000 - Percentage of total elements: 2.72% ### Block 19 Tensor Group : ~218M Elements | T_ID | Tensor Layer Name | Human Friendly Tensor Layer Name | Elements | Shape | Type | |-----:|:--------------------------|:------------------------------------------------|:----------------|:----------------------|:-------| | 175 | blk.19.attn_k.weight | Block 19 Attention Key (W) | ( ~4M) 4194304 | 4096 x 1024 x 1 x 1 | IQ3_S | | 176 | blk.19.attn_norm.weight | Block 19 Attention Normalization (W) | ( ~4K) 4096 | 4096 x 1 x 1 x 1 | F32 | | 177 | blk.19.attn_output.weight | Block 19 Attention Output (W) | (~17M) 16777216 | 4096 x 4096 x 1 x 1 | IQ3_S | | 178 | blk.19.attn_q.weight | Block 19 Attention Query (W) | (~17M) 16777216 | 4096 x 4096 x 1 x 1 | IQ3_S | | 179 | blk.19.attn_v.weight | Block 19 Attention Value (W) | ( ~4M) 4194304 | 4096 x 1024 x 1 x 1 | IQ3_S | | 180 | blk.19.ffn_down.weight | Block 19 Feed-Forward Network "Down" (W) | (~59M) 58720256 | 14336 x 4096 x 1 x 1 | IQ4_NL | | 181 | blk.19.ffn_gate.weight | Block 19 Feed-Forward Network "Gate" (W) | (~59M) 58720256 | 4096 x 14336 x 1 x 1 | IQ3_S | | 182 | blk.19.ffn_norm.weight | Block 19 Feed-Forward Network Normalization (W) | ( ~4K) 4096 | 4096 x 1 x 1 x 1 | F32 | | 183 | blk.19.ffn_up.weight | Block 19 Feed-Forward Network "Up" (W) | (~59M) 58720256 | 4096 x 14336 x 1 x 1 | IQ3_S | - Total elements in blk.19: (~218M) 218112000 - Percentage of total elements: 2.72% ### Block 20 Tensor Group : ~218M Elements | T_ID | Tensor Layer Name | Human Friendly Tensor Layer Name | Elements | Shape | Type | |-----:|:--------------------------|:------------------------------------------------|:----------------|:----------------------|:-------| | 184 | blk.20.attn_k.weight | Block 20 Attention Key (W) | ( ~4M) 4194304 | 4096 x 1024 x 1 x 1 | IQ3_S | | 185 | blk.20.attn_norm.weight | Block 20 Attention Normalization (W) | ( ~4K) 4096 | 4096 x 1 x 1 x 1 | F32 | | 186 | blk.20.attn_output.weight | Block 20 Attention Output (W) | (~17M) 16777216 | 4096 x 4096 x 1 x 1 | IQ3_S | | 187 | blk.20.attn_q.weight | Block 20 Attention Query (W) | (~17M) 16777216 | 4096 x 4096 x 1 x 1 | IQ3_S | | 188 | blk.20.attn_v.weight | Block 20 Attention Value (W) | ( ~4M) 4194304 | 4096 x 1024 x 1 x 1 | IQ3_S | | 189 | blk.20.ffn_down.weight | Block 20 Feed-Forward Network "Down" (W) | (~59M) 58720256 | 14336 x 4096 x 1 x 1 | IQ4_NL | | 190 | blk.20.ffn_gate.weight | Block 20 Feed-Forward Network "Gate" (W) | (~59M) 58720256 | 4096 x 14336 x 1 x 1 | IQ3_S | | 191 | blk.20.ffn_norm.weight | Block 20 Feed-Forward Network Normalization (W) | ( ~4K) 4096 | 4096 x 1 x 1 x 1 | F32 | | 192 | blk.20.ffn_up.weight | Block 20 Feed-Forward Network "Up" (W) | (~59M) 58720256 | 4096 x 14336 x 1 x 1 | IQ3_S | - Total elements in blk.20: (~218M) 218112000 - Percentage of total elements: 2.72% ### Block 21 Tensor Group : ~218M Elements | T_ID | Tensor Layer Name | Human Friendly Tensor Layer Name | Elements | Shape | Type | |-----:|:--------------------------|:------------------------------------------------|:----------------|:----------------------|:-------| | 193 | blk.21.attn_k.weight | Block 21 Attention Key (W) | ( ~4M) 4194304 | 4096 x 1024 x 1 x 1 | IQ3_S | | 194 | blk.21.attn_norm.weight | Block 21 Attention Normalization (W) | ( ~4K) 4096 | 4096 x 1 x 1 x 1 | F32 | | 195 | blk.21.attn_output.weight | Block 21 Attention Output (W) | (~17M) 16777216 | 4096 x 4096 x 1 x 1 | IQ3_S | | 196 | blk.21.attn_q.weight | Block 21 Attention Query (W) | (~17M) 16777216 | 4096 x 4096 x 1 x 1 | IQ3_S | | 197 | blk.21.attn_v.weight | Block 21 Attention Value (W) | ( ~4M) 4194304 | 4096 x 1024 x 1 x 1 | IQ3_S | | 198 | blk.21.ffn_down.weight | Block 21 Feed-Forward Network "Down" (W) | (~59M) 58720256 | 14336 x 4096 x 1 x 1 | IQ4_NL | | 199 | blk.21.ffn_gate.weight | Block 21 Feed-Forward Network "Gate" (W) | (~59M) 58720256 | 4096 x 14336 x 1 x 1 | IQ3_S | | 200 | blk.21.ffn_norm.weight | Block 21 Feed-Forward Network Normalization (W) | ( ~4K) 4096 | 4096 x 1 x 1 x 1 | F32 | | 201 | blk.21.ffn_up.weight | Block 21 Feed-Forward Network "Up" (W) | (~59M) 58720256 | 4096 x 14336 x 1 x 1 | IQ3_S | - Total elements in blk.21: (~218M) 218112000 - Percentage of total elements: 2.72% ### Block 22 Tensor Group : ~218M Elements | T_ID | Tensor Layer Name | Human Friendly Tensor Layer Name | Elements | Shape | Type | |-----:|:--------------------------|:------------------------------------------------|:----------------|:----------------------|:-------| | 202 | blk.22.attn_k.weight | Block 22 Attention Key (W) | ( ~4M) 4194304 | 4096 x 1024 x 1 x 1 | IQ3_S | | 203 | blk.22.attn_norm.weight | Block 22 Attention Normalization (W) | ( ~4K) 4096 | 4096 x 1 x 1 x 1 | F32 | | 204 | blk.22.attn_output.weight | Block 22 Attention Output (W) | (~17M) 16777216 | 4096 x 4096 x 1 x 1 | IQ3_S | | 205 | blk.22.attn_q.weight | Block 22 Attention Query (W) | (~17M) 16777216 | 4096 x 4096 x 1 x 1 | IQ3_S | | 206 | blk.22.attn_v.weight | Block 22 Attention Value (W) | ( ~4M) 4194304 | 4096 x 1024 x 1 x 1 | IQ3_S | | 207 | blk.22.ffn_down.weight | Block 22 Feed-Forward Network "Down" (W) | (~59M) 58720256 | 14336 x 4096 x 1 x 1 | IQ4_NL | | 208 | blk.22.ffn_gate.weight | Block 22 Feed-Forward Network "Gate" (W) | (~59M) 58720256 | 4096 x 14336 x 1 x 1 | IQ3_S | | 209 | blk.22.ffn_norm.weight | Block 22 Feed-Forward Network Normalization (W) | ( ~4K) 4096 | 4096 x 1 x 1 x 1 | F32 | | 210 | blk.22.ffn_up.weight | Block 22 Feed-Forward Network "Up" (W) | (~59M) 58720256 | 4096 x 14336 x 1 x 1 | IQ3_S | - Total elements in blk.22: (~218M) 218112000 - Percentage of total elements: 2.72% ### Block 23 Tensor Group : ~218M Elements | T_ID | Tensor Layer Name | Human Friendly Tensor Layer Name | Elements | Shape | Type | |-----:|:--------------------------|:------------------------------------------------|:----------------|:----------------------|:-------| | 211 | blk.23.attn_k.weight | Block 23 Attention Key (W) | ( ~4M) 4194304 | 4096 x 1024 x 1 x 1 | IQ3_S | | 212 | blk.23.attn_norm.weight | Block 23 Attention Normalization (W) | ( ~4K) 4096 | 4096 x 1 x 1 x 1 | F32 | | 213 | blk.23.attn_output.weight | Block 23 Attention Output (W) | (~17M) 16777216 | 4096 x 4096 x 1 x 1 | IQ3_S | | 214 | blk.23.attn_q.weight | Block 23 Attention Query (W) | (~17M) 16777216 | 4096 x 4096 x 1 x 1 | IQ3_S | | 215 | blk.23.attn_v.weight | Block 23 Attention Value (W) | ( ~4M) 4194304 | 4096 x 1024 x 1 x 1 | IQ3_S | | 216 | blk.23.ffn_down.weight | Block 23 Feed-Forward Network "Down" (W) | (~59M) 58720256 | 14336 x 4096 x 1 x 1 | IQ4_NL | | 217 | blk.23.ffn_gate.weight | Block 23 Feed-Forward Network "Gate" (W) | (~59M) 58720256 | 4096 x 14336 x 1 x 1 | IQ3_S | | 218 | blk.23.ffn_norm.weight | Block 23 Feed-Forward Network Normalization (W) | ( ~4K) 4096 | 4096 x 1 x 1 x 1 | F32 | | 219 | blk.23.ffn_up.weight | Block 23 Feed-Forward Network "Up" (W) | (~59M) 58720256 | 4096 x 14336 x 1 x 1 | IQ3_S | - Total elements in blk.23: (~218M) 218112000 - Percentage of total elements: 2.72% ### Block 24 Tensor Group : ~218M Elements | T_ID | Tensor Layer Name | Human Friendly Tensor Layer Name | Elements | Shape | Type | |-----:|:--------------------------|:------------------------------------------------|:----------------|:----------------------|:-------| | 220 | blk.24.attn_k.weight | Block 24 Attention Key (W) | ( ~4M) 4194304 | 4096 x 1024 x 1 x 1 | IQ3_S | | 221 | blk.24.attn_norm.weight | Block 24 Attention Normalization (W) | ( ~4K) 4096 | 4096 x 1 x 1 x 1 | F32 | | 222 | blk.24.attn_output.weight | Block 24 Attention Output (W) | (~17M) 16777216 | 4096 x 4096 x 1 x 1 | IQ3_S | | 223 | blk.24.attn_q.weight | Block 24 Attention Query (W) | (~17M) 16777216 | 4096 x 4096 x 1 x 1 | IQ3_S | | 224 | blk.24.attn_v.weight | Block 24 Attention Value (W) | ( ~4M) 4194304 | 4096 x 1024 x 1 x 1 | IQ3_S | | 225 | blk.24.ffn_down.weight | Block 24 Feed-Forward Network "Down" (W) | (~59M) 58720256 | 14336 x 4096 x 1 x 1 | IQ4_NL | | 226 | blk.24.ffn_gate.weight | Block 24 Feed-Forward Network "Gate" (W) | (~59M) 58720256 | 4096 x 14336 x 1 x 1 | IQ3_S | | 227 | blk.24.ffn_norm.weight | Block 24 Feed-Forward Network Normalization (W) | ( ~4K) 4096 | 4096 x 1 x 1 x 1 | F32 | | 228 | blk.24.ffn_up.weight | Block 24 Feed-Forward Network "Up" (W) | (~59M) 58720256 | 4096 x 14336 x 1 x 1 | IQ3_S | - Total elements in blk.24: (~218M) 218112000 - Percentage of total elements: 2.72% ### Block 25 Tensor Group : ~218M Elements | T_ID | Tensor Layer Name | Human Friendly Tensor Layer Name | Elements | Shape | Type | |-----:|:--------------------------|:------------------------------------------------|:----------------|:----------------------|:-------| | 229 | blk.25.attn_k.weight | Block 25 Attention Key (W) | ( ~4M) 4194304 | 4096 x 1024 x 1 x 1 | IQ3_S | | 230 | blk.25.attn_norm.weight | Block 25 Attention Normalization (W) | ( ~4K) 4096 | 4096 x 1 x 1 x 1 | F32 | | 231 | blk.25.attn_output.weight | Block 25 Attention Output (W) | (~17M) 16777216 | 4096 x 4096 x 1 x 1 | IQ3_S | | 232 | blk.25.attn_q.weight | Block 25 Attention Query (W) | (~17M) 16777216 | 4096 x 4096 x 1 x 1 | IQ3_S | | 233 | blk.25.attn_v.weight | Block 25 Attention Value (W) | ( ~4M) 4194304 | 4096 x 1024 x 1 x 1 | IQ3_S | | 234 | blk.25.ffn_down.weight | Block 25 Feed-Forward Network "Down" (W) | (~59M) 58720256 | 14336 x 4096 x 1 x 1 | IQ4_NL | | 235 | blk.25.ffn_gate.weight | Block 25 Feed-Forward Network "Gate" (W) | (~59M) 58720256 | 4096 x 14336 x 1 x 1 | IQ3_S | | 236 | blk.25.ffn_norm.weight | Block 25 Feed-Forward Network Normalization (W) | ( ~4K) 4096 | 4096 x 1 x 1 x 1 | F32 | | 237 | blk.25.ffn_up.weight | Block 25 Feed-Forward Network "Up" (W) | (~59M) 58720256 | 4096 x 14336 x 1 x 1 | IQ3_S | - Total elements in blk.25: (~218M) 218112000 - Percentage of total elements: 2.72% ### Block 26 Tensor Group : ~218M Elements | T_ID | Tensor Layer Name | Human Friendly Tensor Layer Name | Elements | Shape | Type | |-----:|:--------------------------|:------------------------------------------------|:----------------|:----------------------|:-------| | 238 | blk.26.attn_k.weight | Block 26 Attention Key (W) | ( ~4M) 4194304 | 4096 x 1024 x 1 x 1 | IQ3_S | | 239 | blk.26.attn_norm.weight | Block 26 Attention Normalization (W) | ( ~4K) 4096 | 4096 x 1 x 1 x 1 | F32 | | 240 | blk.26.attn_output.weight | Block 26 Attention Output (W) | (~17M) 16777216 | 4096 x 4096 x 1 x 1 | IQ3_S | | 241 | blk.26.attn_q.weight | Block 26 Attention Query (W) | (~17M) 16777216 | 4096 x 4096 x 1 x 1 | IQ3_S | | 242 | blk.26.attn_v.weight | Block 26 Attention Value (W) | ( ~4M) 4194304 | 4096 x 1024 x 1 x 1 | IQ3_S | | 243 | blk.26.ffn_down.weight | Block 26 Feed-Forward Network "Down" (W) | (~59M) 58720256 | 14336 x 4096 x 1 x 1 | IQ4_NL | | 244 | blk.26.ffn_gate.weight | Block 26 Feed-Forward Network "Gate" (W) | (~59M) 58720256 | 4096 x 14336 x 1 x 1 | IQ3_S | | 245 | blk.26.ffn_norm.weight | Block 26 Feed-Forward Network Normalization (W) | ( ~4K) 4096 | 4096 x 1 x 1 x 1 | F32 | | 246 | blk.26.ffn_up.weight | Block 26 Feed-Forward Network "Up" (W) | (~59M) 58720256 | 4096 x 14336 x 1 x 1 | IQ3_S | - Total elements in blk.26: (~218M) 218112000 - Percentage of total elements: 2.72% ### Block 27 Tensor Group : ~218M Elements | T_ID | Tensor Layer Name | Human Friendly Tensor Layer Name | Elements | Shape | Type | |-----:|:--------------------------|:------------------------------------------------|:----------------|:----------------------|:-------| | 247 | blk.27.attn_k.weight | Block 27 Attention Key (W) | ( ~4M) 4194304 | 4096 x 1024 x 1 x 1 | IQ3_S | | 248 | blk.27.attn_norm.weight | Block 27 Attention Normalization (W) | ( ~4K) 4096 | 4096 x 1 x 1 x 1 | F32 | | 249 | blk.27.attn_output.weight | Block 27 Attention Output (W) | (~17M) 16777216 | 4096 x 4096 x 1 x 1 | IQ3_S | | 250 | blk.27.attn_q.weight | Block 27 Attention Query (W) | (~17M) 16777216 | 4096 x 4096 x 1 x 1 | IQ3_S | | 251 | blk.27.attn_v.weight | Block 27 Attention Value (W) | ( ~4M) 4194304 | 4096 x 1024 x 1 x 1 | IQ3_S | | 252 | blk.27.ffn_down.weight | Block 27 Feed-Forward Network "Down" (W) | (~59M) 58720256 | 14336 x 4096 x 1 x 1 | IQ4_NL | | 253 | blk.27.ffn_gate.weight | Block 27 Feed-Forward Network "Gate" (W) | (~59M) 58720256 | 4096 x 14336 x 1 x 1 | IQ3_S | | 254 | blk.27.ffn_norm.weight | Block 27 Feed-Forward Network Normalization (W) | ( ~4K) 4096 | 4096 x 1 x 1 x 1 | F32 | | 255 | blk.27.ffn_up.weight | Block 27 Feed-Forward Network "Up" (W) | (~59M) 58720256 | 4096 x 14336 x 1 x 1 | IQ3_S | - Total elements in blk.27: (~218M) 218112000 - Percentage of total elements: 2.72% ### Block 28 Tensor Group : ~218M Elements | T_ID | Tensor Layer Name | Human Friendly Tensor Layer Name | Elements | Shape | Type | |-----:|:--------------------------|:------------------------------------------------|:----------------|:----------------------|:-------| | 256 | blk.28.attn_k.weight | Block 28 Attention Key (W) | ( ~4M) 4194304 | 4096 x 1024 x 1 x 1 | IQ3_S | | 257 | blk.28.attn_norm.weight | Block 28 Attention Normalization (W) | ( ~4K) 4096 | 4096 x 1 x 1 x 1 | F32 | | 258 | blk.28.attn_output.weight | Block 28 Attention Output (W) | (~17M) 16777216 | 4096 x 4096 x 1 x 1 | IQ3_S | | 259 | blk.28.attn_q.weight | Block 28 Attention Query (W) | (~17M) 16777216 | 4096 x 4096 x 1 x 1 | IQ3_S | | 260 | blk.28.attn_v.weight | Block 28 Attention Value (W) | ( ~4M) 4194304 | 4096 x 1024 x 1 x 1 | IQ3_S | | 261 | blk.28.ffn_down.weight | Block 28 Feed-Forward Network "Down" (W) | (~59M) 58720256 | 14336 x 4096 x 1 x 1 | IQ4_NL | | 262 | blk.28.ffn_gate.weight | Block 28 Feed-Forward Network "Gate" (W) | (~59M) 58720256 | 4096 x 14336 x 1 x 1 | IQ3_S | | 263 | blk.28.ffn_norm.weight | Block 28 Feed-Forward Network Normalization (W) | ( ~4K) 4096 | 4096 x 1 x 1 x 1 | F32 | | 264 | blk.28.ffn_up.weight | Block 28 Feed-Forward Network "Up" (W) | (~59M) 58720256 | 4096 x 14336 x 1 x 1 | IQ3_S | - Total elements in blk.28: (~218M) 218112000 - Percentage of total elements: 2.72% ### Block 29 Tensor Group : ~218M Elements | T_ID | Tensor Layer Name | Human Friendly Tensor Layer Name | Elements | Shape | Type | |-----:|:--------------------------|:------------------------------------------------|:----------------|:----------------------|:-------| | 265 | blk.29.attn_k.weight | Block 29 Attention Key (W) | ( ~4M) 4194304 | 4096 x 1024 x 1 x 1 | IQ3_S | | 266 | blk.29.attn_norm.weight | Block 29 Attention Normalization (W) | ( ~4K) 4096 | 4096 x 1 x 1 x 1 | F32 | | 267 | blk.29.attn_output.weight | Block 29 Attention Output (W) | (~17M) 16777216 | 4096 x 4096 x 1 x 1 | IQ3_S | | 268 | blk.29.attn_q.weight | Block 29 Attention Query (W) | (~17M) 16777216 | 4096 x 4096 x 1 x 1 | IQ3_S | | 269 | blk.29.attn_v.weight | Block 29 Attention Value (W) | ( ~4M) 4194304 | 4096 x 1024 x 1 x 1 | IQ3_S | | 270 | blk.29.ffn_down.weight | Block 29 Feed-Forward Network "Down" (W) | (~59M) 58720256 | 14336 x 4096 x 1 x 1 | IQ4_NL | | 271 | blk.29.ffn_gate.weight | Block 29 Feed-Forward Network "Gate" (W) | (~59M) 58720256 | 4096 x 14336 x 1 x 1 | IQ3_S | | 272 | blk.29.ffn_norm.weight | Block 29 Feed-Forward Network Normalization (W) | ( ~4K) 4096 | 4096 x 1 x 1 x 1 | F32 | | 273 | blk.29.ffn_up.weight | Block 29 Feed-Forward Network "Up" (W) | (~59M) 58720256 | 4096 x 14336 x 1 x 1 | IQ3_S | - Total elements in blk.29: (~218M) 218112000 - Percentage of total elements: 2.72% ### Block 30 Tensor Group : ~218M Elements | T_ID | Tensor Layer Name | Human Friendly Tensor Layer Name | Elements | Shape | Type | |-----:|:--------------------------|:------------------------------------------------|:----------------|:----------------------|:-------| | 274 | blk.30.attn_k.weight | Block 30 Attention Key (W) | ( ~4M) 4194304 | 4096 x 1024 x 1 x 1 | IQ3_S | | 275 | blk.30.attn_norm.weight | Block 30 Attention Normalization (W) | ( ~4K) 4096 | 4096 x 1 x 1 x 1 | F32 | | 276 | blk.30.attn_output.weight | Block 30 Attention Output (W) | (~17M) 16777216 | 4096 x 4096 x 1 x 1 | IQ3_S | | 277 | blk.30.attn_q.weight | Block 30 Attention Query (W) | (~17M) 16777216 | 4096 x 4096 x 1 x 1 | IQ3_S | | 278 | blk.30.attn_v.weight | Block 30 Attention Value (W) | ( ~4M) 4194304 | 4096 x 1024 x 1 x 1 | IQ3_S | | 279 | blk.30.ffn_down.weight | Block 30 Feed-Forward Network "Down" (W) | (~59M) 58720256 | 14336 x 4096 x 1 x 1 | IQ4_NL | | 280 | blk.30.ffn_gate.weight | Block 30 Feed-Forward Network "Gate" (W) | (~59M) 58720256 | 4096 x 14336 x 1 x 1 | IQ3_S | | 281 | blk.30.ffn_norm.weight | Block 30 Feed-Forward Network Normalization (W) | ( ~4K) 4096 | 4096 x 1 x 1 x 1 | F32 | | 282 | blk.30.ffn_up.weight | Block 30 Feed-Forward Network "Up" (W) | (~59M) 58720256 | 4096 x 14336 x 1 x 1 | IQ3_S | - Total elements in blk.30: (~218M) 218112000 - Percentage of total elements: 2.72% ### Block 31 Tensor Group : ~218M Elements | T_ID | Tensor Layer Name | Human Friendly Tensor Layer Name | Elements | Shape | Type | |-----:|:--------------------------|:------------------------------------------------|:----------------|:----------------------|:--------| | 283 | blk.31.attn_k.weight | Block 31 Attention Key (W) | ( ~4M) 4194304 | 4096 x 1024 x 1 x 1 | IQ3_XXS | | 284 | blk.31.attn_norm.weight | Block 31 Attention Normalization (W) | ( ~4K) 4096 | 4096 x 1 x 1 x 1 | F32 | | 285 | blk.31.attn_output.weight | Block 31 Attention Output (W) | (~17M) 16777216 | 4096 x 4096 x 1 x 1 | IQ3_S | | 286 | blk.31.attn_q.weight | Block 31 Attention Query (W) | (~17M) 16777216 | 4096 x 4096 x 1 x 1 | IQ3_XXS | | 287 | blk.31.attn_v.weight | Block 31 Attention Value (W) | ( ~4M) 4194304 | 4096 x 1024 x 1 x 1 | IQ3_S | | 288 | blk.31.ffn_down.weight | Block 31 Feed-Forward Network "Down" (W) | (~59M) 58720256 | 14336 x 4096 x 1 x 1 | IQ4_NL | | 289 | blk.31.ffn_gate.weight | Block 31 Feed-Forward Network "Gate" (W) | (~59M) 58720256 | 4096 x 14336 x 1 x 1 | IQ3_S | | 290 | blk.31.ffn_norm.weight | Block 31 Feed-Forward Network Normalization (W) | ( ~4K) 4096 | 4096 x 1 x 1 x 1 | F32 | | 291 | blk.31.ffn_up.weight | Block 31 Feed-Forward Network "Up" (W) | (~59M) 58720256 | 4096 x 14336 x 1 x 1 | IQ3_S | - Total elements in blk.31: (~218M) 218112000 - Percentage of total elements: 2.72%