# Qwen3-30B-A3B-F16.gguf - GGUF Internal File Dump
- Endian: LITTLE endian
## Key Value Metadata Store
There are 40 key-value pairs in this file
| POS | TYPE | Count | Key | Value |
|----:|:---------|-------:|:------------------------------------------|:--------------------------------------------------------------------|
| 1 | UINT32 | 1 | GGUF.version | 3 |
| 2 | UINT64 | 1 | GGUF.tensor_count | 579 |
| 3 | UINT64 | 1 | GGUF.kv_count | 37 |
| 4 | STRING | 1 | general.architecture | `qwen3moe` |
| 5 | STRING | 1 | general.type | `model` |
| 6 | STRING | 1 | general.name | `Qwen3 30B A3B` |
| 7 | STRING | 1 | general.basename | `Qwen3` |
| 8 | STRING | 1 | general.size_label | `30B-A3B` |
| 9 | STRING | 1 | general.license | `apache-2.0` |
| 10 | STRING | 1 | general.license.link | `https://huggingface.co/Qwen/Qwen3-30B-A3B/blob/main/LICENSE` |
| 11 | UINT32 | 1 | general.base_model.count | 1 |
| 12 | STRING | 1 | general.base_model.0.name | `Qwen3 30B A3B Base` |
| 13 | STRING | 1 | general.base_model.0.organization | `Qwen` |
| 14 | STRING | 1 | general.base_model.0.repo_url | `https://huggingface.co/Qwen/Qwen3-30B-A3B-Base` |
| 15 | [STRING] | 1 | general.tags | [ `text-generation` ] |
| 16 | UINT32 | 1 | qwen3moe.block_count | 48 |
| 17 | UINT32 | 1 | qwen3moe.context_length | 40960 |
| 18 | UINT32 | 1 | qwen3moe.embedding_length | 2048 |
| 19 | UINT32 | 1 | qwen3moe.feed_forward_length | 6144 |
| 20 | UINT32 | 1 | qwen3moe.attention.head_count | 32 |
| 21 | UINT32 | 1 | qwen3moe.attention.head_count_kv | 4 |
| 22 | FLOAT32 | 1 | qwen3moe.rope.freq_base | 1000000.0 |
| 23 | FLOAT32 | 1 | qwen3moe.attention.layer_norm_rms_epsilon | 1e-06 |
| 24 | UINT32 | 1 | qwen3moe.expert_used_count | 8 |
| 25 | UINT32 | 1 | qwen3moe.attention.key_length | 128 |
| 26 | UINT32 | 1 | qwen3moe.attention.value_length | 128 |
| 27 | UINT32 | 1 | general.file_type | 1 |
| 28 | UINT32 | 1 | qwen3moe.expert_count | 128 |
| 29 | UINT32 | 1 | qwen3moe.expert_feed_forward_length | 768 |
| 30 | UINT32 | 1 | general.quantization_version | 2 |
| 31 | STRING | 1 | tokenizer.ggml.model | `gpt2` |
| 32 | STRING | 1 | tokenizer.ggml.pre | `qwen2` |
| 33 | [STRING] | 151936 | tokenizer.ggml.tokens | [ `!`, `"`, `#`, `$`, `%`, ... ] |
| 34 | [INT32] | 151936 | tokenizer.ggml.token_type | [ 1, 1, 1, 1, 1, 1, 1, ... ] |
| 35 | [STRING] | 151387 | tokenizer.ggml.merges | [ `Ġ Ġ`, `ĠĠ ĠĠ`, `i n`, `Ġ t`, `ĠĠĠĠ ĠĠĠĠ`, ... ] |
| 36 | UINT32 | 1 | tokenizer.ggml.eos_token_id | 151645 |
| 37 | UINT32 | 1 | tokenizer.ggml.padding_token_id | 151643 |
| 38 | UINT32 | 1 | tokenizer.ggml.bos_token_id | 151643 |
| 39 | BOOL | 1 | tokenizer.ggml.add_bos_token | False |
| 40 | STRING | 1 | tokenizer.chat_template | `{%- if tools %}{{- '<|im_`...`{%- endif %}{%- endif %}` |
## Tensors Overview ~31B Elements
Total number of elements in all tensors: 30532122624 Elements
- [Qwen3-30B-A3B-F16.gguf - GGUF Internal File Dump](#qwen3-30b-a3b-f16gguf---gguf-internal-file-dump)
- [Key Value Metadata Store](#key-value-metadata-store)
- [Tensors Overview ~31B Elements](#tensors-overview-31b-elements)
- [Tensor Data Offset](#tensor-data-offset)
- [Base Tensor Group : ~622M Elements](#base-tensor-group--622m-elements)
- [Block 0 Tensor Group : ~623M Elements](#block-0-tensor-group--623m-elements)
- [Block 1 Tensor Group : ~623M Elements](#block-1-tensor-group--623m-elements)
- [Block 2 Tensor Group : ~623M Elements](#block-2-tensor-group--623m-elements)
- [Block 3 Tensor Group : ~623M Elements](#block-3-tensor-group--623m-elements)
- [Block 4 Tensor Group : ~623M Elements](#block-4-tensor-group--623m-elements)
- [Block 5 Tensor Group : ~623M Elements](#block-5-tensor-group--623m-elements)
- [Block 6 Tensor Group : ~623M Elements](#block-6-tensor-group--623m-elements)
- [Block 7 Tensor Group : ~623M Elements](#block-7-tensor-group--623m-elements)
- [Block 8 Tensor Group : ~623M Elements](#block-8-tensor-group--623m-elements)
- [Block 9 Tensor Group : ~623M Elements](#block-9-tensor-group--623m-elements)
- [Block 10 Tensor Group : ~623M Elements](#block-10-tensor-group--623m-elements)
- [Block 11 Tensor Group : ~623M Elements](#block-11-tensor-group--623m-elements)
- [Block 12 Tensor Group : ~623M Elements](#block-12-tensor-group--623m-elements)
- [Block 13 Tensor Group : ~623M Elements](#block-13-tensor-group--623m-elements)
- [Block 14 Tensor Group : ~623M Elements](#block-14-tensor-group--623m-elements)
- [Block 15 Tensor Group : ~623M Elements](#block-15-tensor-group--623m-elements)
- [Block 16 Tensor Group : ~623M Elements](#block-16-tensor-group--623m-elements)
- [Block 17 Tensor Group : ~623M Elements](#block-17-tensor-group--623m-elements)
- [Block 18 Tensor Group : ~623M Elements](#block-18-tensor-group--623m-elements)
- [Block 19 Tensor Group : ~623M Elements](#block-19-tensor-group--623m-elements)
- [Block 20 Tensor Group : ~623M Elements](#block-20-tensor-group--623m-elements)
- [Block 21 Tensor Group : ~623M Elements](#block-21-tensor-group--623m-elements)
- [Block 22 Tensor Group : ~623M Elements](#block-22-tensor-group--623m-elements)
- [Block 23 Tensor Group : ~623M Elements](#block-23-tensor-group--623m-elements)
- [Block 24 Tensor Group : ~623M Elements](#block-24-tensor-group--623m-elements)
- [Block 25 Tensor Group : ~623M Elements](#block-25-tensor-group--623m-elements)
- [Block 26 Tensor Group : ~623M Elements](#block-26-tensor-group--623m-elements)
- [Block 27 Tensor Group : ~623M Elements](#block-27-tensor-group--623m-elements)
- [Block 28 Tensor Group : ~623M Elements](#block-28-tensor-group--623m-elements)
- [Block 29 Tensor Group : ~623M Elements](#block-29-tensor-group--623m-elements)
- [Block 30 Tensor Group : ~623M Elements](#block-30-tensor-group--623m-elements)
- [Block 31 Tensor Group : ~623M Elements](#block-31-tensor-group--623m-elements)
- [Block 32 Tensor Group : ~623M Elements](#block-32-tensor-group--623m-elements)
- [Block 33 Tensor Group : ~623M Elements](#block-33-tensor-group--623m-elements)
- [Block 34 Tensor Group : ~623M Elements](#block-34-tensor-group--623m-elements)
- [Block 35 Tensor Group : ~623M Elements](#block-35-tensor-group--623m-elements)
- [Block 36 Tensor Group : ~623M Elements](#block-36-tensor-group--623m-elements)
- [Block 37 Tensor Group : ~623M Elements](#block-37-tensor-group--623m-elements)
- [Block 38 Tensor Group : ~623M Elements](#block-38-tensor-group--623m-elements)
- [Block 39 Tensor Group : ~623M Elements](#block-39-tensor-group--623m-elements)
- [Block 40 Tensor Group : ~623M Elements](#block-40-tensor-group--623m-elements)
- [Block 41 Tensor Group : ~623M Elements](#block-41-tensor-group--623m-elements)
- [Block 42 Tensor Group : ~623M Elements](#block-42-tensor-group--623m-elements)
- [Block 43 Tensor Group : ~623M Elements](#block-43-tensor-group--623m-elements)
- [Block 44 Tensor Group : ~623M Elements](#block-44-tensor-group--623m-elements)
- [Block 45 Tensor Group : ~623M Elements](#block-45-tensor-group--623m-elements)
- [Block 46 Tensor Group : ~623M Elements](#block-46-tensor-group--623m-elements)
- [Block 47 Tensor Group : ~623M Elements](#block-47-tensor-group--623m-elements)
### Tensor Data Offset
This table contains the offset and data segment relative to start of file
| T_ID | Tensor Layer Name | Data Offset (B) | Data Size (B) |
|-----:|:----------------------------|-----------------:|-----------------:|
| 0 | token_embd.weight | 0x5b17a0 | 0x25180000 |
| 1 | blk.0.attn_norm.weight | 0x257317a0 | 0x2000 |
| 2 | blk.0.ffn_down_exps.weight | 0x257337a0 | 0x18000000 |
| 3 | blk.0.ffn_gate_exps.weight | 0x3d7337a0 | 0x18000000 |
| 4 | blk.0.ffn_up_exps.weight | 0x557337a0 | 0x18000000 |
| 5 | blk.0.ffn_gate_inp.weight | 0x6d7337a0 | 0x100000 |
| 6 | blk.0.ffn_norm.weight | 0x6d8337a0 | 0x2000 |
| 7 | blk.0.attn_k_norm.weight | 0x6d8357a0 | 0x200 |
| 8 | blk.0.attn_k.weight | 0x6d8359a0 | 0x200000 |
| 9 | blk.0.attn_output.weight | 0x6da359a0 | 0x1000000 |
| 10 | blk.0.attn_q_norm.weight | 0x6ea359a0 | 0x200 |
| 11 | blk.0.attn_q.weight | 0x6ea35ba0 | 0x1000000 |
| 12 | blk.0.attn_v.weight | 0x6fa35ba0 | 0x200000 |
| 13 | blk.1.attn_norm.weight | 0x6fc35ba0 | 0x2000 |
| 14 | blk.1.ffn_down_exps.weight | 0x6fc37ba0 | 0x18000000 |
| 15 | blk.1.ffn_gate_exps.weight | 0x87c37ba0 | 0x18000000 |
| 16 | blk.1.ffn_up_exps.weight | 0x9fc37ba0 | 0x18000000 |
| 17 | blk.1.ffn_gate_inp.weight | 0xb7c37ba0 | 0x100000 |
| 18 | blk.1.ffn_norm.weight | 0xb7d37ba0 | 0x2000 |
| 19 | blk.1.attn_k_norm.weight | 0xb7d39ba0 | 0x200 |
| 20 | blk.1.attn_k.weight | 0xb7d39da0 | 0x200000 |
| 21 | blk.1.attn_output.weight | 0xb7f39da0 | 0x1000000 |
| 22 | blk.1.attn_q_norm.weight | 0xb8f39da0 | 0x200 |
| 23 | blk.1.attn_q.weight | 0xb8f39fa0 | 0x1000000 |
| 24 | blk.1.attn_v.weight | 0xb9f39fa0 | 0x200000 |
| 25 | blk.2.ffn_gate_inp.weight | 0xba139fa0 | 0x100000 |
| 26 | blk.2.attn_k_norm.weight | 0xba239fa0 | 0x200 |
| 27 | blk.2.attn_k.weight | 0xba23a1a0 | 0x200000 |
| 28 | blk.2.attn_output.weight | 0xba43a1a0 | 0x1000000 |
| 29 | blk.2.attn_q_norm.weight | 0xbb43a1a0 | 0x200 |
| 30 | blk.2.attn_q.weight | 0xbb43a3a0 | 0x1000000 |
| 31 | blk.2.attn_v.weight | 0xbc43a3a0 | 0x200000 |
| 32 | blk.2.attn_norm.weight | 0xbc63a3a0 | 0x2000 |
| 33 | blk.2.ffn_down_exps.weight | 0xbc63c3a0 | 0x18000000 |
| 34 | blk.2.ffn_gate_exps.weight | 0xd463c3a0 | 0x18000000 |
| 35 | blk.2.ffn_up_exps.weight | 0xec63c3a0 | 0x18000000 |
| 36 | blk.2.ffn_norm.weight | 0x10463c3a0 | 0x2000 |
| 37 | blk.3.attn_norm.weight | 0x10463e3a0 | 0x2000 |
| 38 | blk.3.ffn_down_exps.weight | 0x1046403a0 | 0x18000000 |
| 39 | blk.3.ffn_gate_exps.weight | 0x11c6403a0 | 0x18000000 |
| 40 | blk.3.ffn_up_exps.weight | 0x1346403a0 | 0x18000000 |
| 41 | blk.3.ffn_gate_inp.weight | 0x14c6403a0 | 0x100000 |
| 42 | blk.3.ffn_norm.weight | 0x14c7403a0 | 0x2000 |
| 43 | blk.3.attn_k_norm.weight | 0x14c7423a0 | 0x200 |
| 44 | blk.3.attn_k.weight | 0x14c7425a0 | 0x200000 |
| 45 | blk.3.attn_output.weight | 0x14c9425a0 | 0x1000000 |
| 46 | blk.3.attn_q_norm.weight | 0x14d9425a0 | 0x200 |
| 47 | blk.3.attn_q.weight | 0x14d9427a0 | 0x1000000 |
| 48 | blk.3.attn_v.weight | 0x14e9427a0 | 0x200000 |
| 49 | blk.4.attn_norm.weight | 0x14eb427a0 | 0x2000 |
| 50 | blk.4.ffn_down_exps.weight | 0x14eb447a0 | 0x18000000 |
| 51 | blk.4.ffn_gate_exps.weight | 0x166b447a0 | 0x18000000 |
| 52 | blk.4.ffn_up_exps.weight | 0x17eb447a0 | 0x18000000 |
| 53 | blk.4.ffn_gate_inp.weight | 0x196b447a0 | 0x100000 |
| 54 | blk.4.ffn_norm.weight | 0x196c447a0 | 0x2000 |
| 55 | blk.4.attn_k_norm.weight | 0x196c467a0 | 0x200 |
| 56 | blk.4.attn_k.weight | 0x196c469a0 | 0x200000 |
| 57 | blk.4.attn_output.weight | 0x196e469a0 | 0x1000000 |
| 58 | blk.4.attn_q_norm.weight | 0x197e469a0 | 0x200 |
| 59 | blk.4.attn_q.weight | 0x197e46ba0 | 0x1000000 |
| 60 | blk.4.attn_v.weight | 0x198e46ba0 | 0x200000 |
| 61 | blk.5.ffn_gate_inp.weight | 0x199046ba0 | 0x100000 |
| 62 | blk.5.attn_k_norm.weight | 0x199146ba0 | 0x200 |
| 63 | blk.5.attn_k.weight | 0x199146da0 | 0x200000 |
| 64 | blk.5.attn_output.weight | 0x199346da0 | 0x1000000 |
| 65 | blk.5.attn_q_norm.weight | 0x19a346da0 | 0x200 |
| 66 | blk.5.attn_q.weight | 0x19a346fa0 | 0x1000000 |
| 67 | blk.5.attn_v.weight | 0x19b346fa0 | 0x200000 |
| 68 | blk.5.attn_norm.weight | 0x19b546fa0 | 0x2000 |
| 69 | blk.5.ffn_down_exps.weight | 0x19b548fa0 | 0x18000000 |
| 70 | blk.5.ffn_gate_exps.weight | 0x1b3548fa0 | 0x18000000 |
| 71 | blk.5.ffn_up_exps.weight | 0x1cb548fa0 | 0x18000000 |
| 72 | blk.5.ffn_norm.weight | 0x1e3548fa0 | 0x2000 |
| 73 | blk.6.attn_norm.weight | 0x1e354afa0 | 0x2000 |
| 74 | blk.6.ffn_down_exps.weight | 0x1e354cfa0 | 0x18000000 |
| 75 | blk.6.ffn_gate_exps.weight | 0x1fb54cfa0 | 0x18000000 |
| 76 | blk.6.ffn_up_exps.weight | 0x21354cfa0 | 0x18000000 |
| 77 | blk.6.ffn_gate_inp.weight | 0x22b54cfa0 | 0x100000 |
| 78 | blk.6.ffn_norm.weight | 0x22b64cfa0 | 0x2000 |
| 79 | blk.6.attn_k_norm.weight | 0x22b64efa0 | 0x200 |
| 80 | blk.6.attn_k.weight | 0x22b64f1a0 | 0x200000 |
| 81 | blk.6.attn_output.weight | 0x22b84f1a0 | 0x1000000 |
| 82 | blk.6.attn_q_norm.weight | 0x22c84f1a0 | 0x200 |
| 83 | blk.6.attn_q.weight | 0x22c84f3a0 | 0x1000000 |
| 84 | blk.6.attn_v.weight | 0x22d84f3a0 | 0x200000 |
| 85 | blk.7.attn_norm.weight | 0x22da4f3a0 | 0x2000 |
| 86 | blk.7.ffn_down_exps.weight | 0x22da513a0 | 0x18000000 |
| 87 | blk.7.ffn_gate_exps.weight | 0x245a513a0 | 0x18000000 |
| 88 | blk.7.ffn_up_exps.weight | 0x25da513a0 | 0x18000000 |
| 89 | blk.7.ffn_gate_inp.weight | 0x275a513a0 | 0x100000 |
| 90 | blk.7.ffn_norm.weight | 0x275b513a0 | 0x2000 |
| 91 | blk.7.attn_k_norm.weight | 0x275b533a0 | 0x200 |
| 92 | blk.7.attn_k.weight | 0x275b535a0 | 0x200000 |
| 93 | blk.7.attn_output.weight | 0x275d535a0 | 0x1000000 |
| 94 | blk.7.attn_q_norm.weight | 0x276d535a0 | 0x200 |
| 95 | blk.7.attn_q.weight | 0x276d537a0 | 0x1000000 |
| 96 | blk.7.attn_v.weight | 0x277d537a0 | 0x200000 |
| 97 | blk.8.attn_norm.weight | 0x277f537a0 | 0x2000 |
| 98 | blk.8.ffn_down_exps.weight | 0x277f557a0 | 0x18000000 |
| 99 | blk.8.ffn_gate_exps.weight | 0x28ff557a0 | 0x18000000 |
| 100 | blk.8.ffn_up_exps.weight | 0x2a7f557a0 | 0x18000000 |
| 101 | blk.8.ffn_gate_inp.weight | 0x2bff557a0 | 0x100000 |
| 102 | blk.8.ffn_norm.weight | 0x2c00557a0 | 0x2000 |
| 103 | blk.8.attn_k_norm.weight | 0x2c00577a0 | 0x200 |
| 104 | blk.8.attn_k.weight | 0x2c00579a0 | 0x200000 |
| 105 | blk.8.attn_output.weight | 0x2c02579a0 | 0x1000000 |
| 106 | blk.8.attn_q_norm.weight | 0x2c12579a0 | 0x200 |
| 107 | blk.8.attn_q.weight | 0x2c1257ba0 | 0x1000000 |
| 108 | blk.8.attn_v.weight | 0x2c2257ba0 | 0x200000 |
| 109 | blk.9.ffn_gate_inp.weight | 0x2c2457ba0 | 0x100000 |
| 110 | blk.9.attn_k_norm.weight | 0x2c2557ba0 | 0x200 |
| 111 | blk.9.attn_k.weight | 0x2c2557da0 | 0x200000 |
| 112 | blk.9.attn_output.weight | 0x2c2757da0 | 0x1000000 |
| 113 | blk.9.attn_q_norm.weight | 0x2c3757da0 | 0x200 |
| 114 | blk.9.attn_q.weight | 0x2c3757fa0 | 0x1000000 |
| 115 | blk.9.attn_v.weight | 0x2c4757fa0 | 0x200000 |
| 116 | blk.10.attn_norm.weight | 0x2c4957fa0 | 0x2000 |
| 117 | blk.10.ffn_down_exps.weight | 0x2c4959fa0 | 0x18000000 |
| 118 | blk.10.ffn_gate_exps.weight | 0x2dc959fa0 | 0x18000000 |
| 119 | blk.10.ffn_up_exps.weight | 0x2f4959fa0 | 0x18000000 |
| 120 | blk.10.ffn_gate_inp.weight | 0x30c959fa0 | 0x100000 |
| 121 | blk.10.ffn_norm.weight | 0x30ca59fa0 | 0x2000 |
| 122 | blk.10.attn_k_norm.weight | 0x30ca5bfa0 | 0x200 |
| 123 | blk.10.attn_k.weight | 0x30ca5c1a0 | 0x200000 |
| 124 | blk.10.attn_output.weight | 0x30cc5c1a0 | 0x1000000 |
| 125 | blk.10.attn_q_norm.weight | 0x30dc5c1a0 | 0x200 |
| 126 | blk.10.attn_q.weight | 0x30dc5c3a0 | 0x1000000 |
| 127 | blk.10.attn_v.weight | 0x30ec5c3a0 | 0x200000 |
| 128 | blk.11.attn_norm.weight | 0x30ee5c3a0 | 0x2000 |
| 129 | blk.11.ffn_down_exps.weight | 0x30ee5e3a0 | 0x18000000 |
| 130 | blk.11.ffn_gate_exps.weight | 0x326e5e3a0 | 0x18000000 |
| 131 | blk.11.ffn_up_exps.weight | 0x33ee5e3a0 | 0x18000000 |
| 132 | blk.11.ffn_gate_inp.weight | 0x356e5e3a0 | 0x100000 |
| 133 | blk.11.ffn_norm.weight | 0x356f5e3a0 | 0x2000 |
| 134 | blk.11.attn_k_norm.weight | 0x356f603a0 | 0x200 |
| 135 | blk.11.attn_k.weight | 0x356f605a0 | 0x200000 |
| 136 | blk.11.attn_output.weight | 0x3571605a0 | 0x1000000 |
| 137 | blk.11.attn_q_norm.weight | 0x3581605a0 | 0x200 |
| 138 | blk.11.attn_q.weight | 0x3581607a0 | 0x1000000 |
| 139 | blk.11.attn_v.weight | 0x3591607a0 | 0x200000 |
| 140 | blk.12.ffn_gate_inp.weight | 0x3593607a0 | 0x100000 |
| 141 | blk.12.attn_k_norm.weight | 0x3594607a0 | 0x200 |
| 142 | blk.12.attn_k.weight | 0x3594609a0 | 0x200000 |
| 143 | blk.12.attn_output.weight | 0x3596609a0 | 0x1000000 |
| 144 | blk.12.attn_q_norm.weight | 0x35a6609a0 | 0x200 |
| 145 | blk.12.attn_q.weight | 0x35a660ba0 | 0x1000000 |
| 146 | blk.12.attn_v.weight | 0x35b660ba0 | 0x200000 |
| 147 | blk.9.attn_norm.weight | 0x35b860ba0 | 0x2000 |
| 148 | blk.9.ffn_down_exps.weight | 0x35b862ba0 | 0x18000000 |
| 149 | blk.9.ffn_gate_exps.weight | 0x373862ba0 | 0x18000000 |
| 150 | blk.9.ffn_up_exps.weight | 0x38b862ba0 | 0x18000000 |
| 151 | blk.9.ffn_norm.weight | 0x3a3862ba0 | 0x2000 |
| 152 | blk.12.attn_norm.weight | 0x3a3864ba0 | 0x2000 |
| 153 | blk.12.ffn_down_exps.weight | 0x3a3866ba0 | 0x18000000 |
| 154 | blk.12.ffn_gate_exps.weight | 0x3bb866ba0 | 0x18000000 |
| 155 | blk.12.ffn_up_exps.weight | 0x3d3866ba0 | 0x18000000 |
| 156 | blk.12.ffn_norm.weight | 0x3eb866ba0 | 0x2000 |
| 157 | blk.13.attn_norm.weight | 0x3eb868ba0 | 0x2000 |
| 158 | blk.13.ffn_down_exps.weight | 0x3eb86aba0 | 0x18000000 |
| 159 | blk.13.ffn_gate_exps.weight | 0x40386aba0 | 0x18000000 |
| 160 | blk.13.ffn_up_exps.weight | 0x41b86aba0 | 0x18000000 |
| 161 | blk.13.ffn_gate_inp.weight | 0x43386aba0 | 0x100000 |
| 162 | blk.13.ffn_norm.weight | 0x43396aba0 | 0x2000 |
| 163 | blk.13.attn_k_norm.weight | 0x43396cba0 | 0x200 |
| 164 | blk.13.attn_k.weight | 0x43396cda0 | 0x200000 |
| 165 | blk.13.attn_output.weight | 0x433b6cda0 | 0x1000000 |
| 166 | blk.13.attn_q_norm.weight | 0x434b6cda0 | 0x200 |
| 167 | blk.13.attn_q.weight | 0x434b6cfa0 | 0x1000000 |
| 168 | blk.13.attn_v.weight | 0x435b6cfa0 | 0x200000 |
| 169 | blk.14.attn_norm.weight | 0x435d6cfa0 | 0x2000 |
| 170 | blk.14.ffn_down_exps.weight | 0x435d6efa0 | 0x18000000 |
| 171 | blk.14.ffn_gate_exps.weight | 0x44dd6efa0 | 0x18000000 |
| 172 | blk.14.ffn_up_exps.weight | 0x465d6efa0 | 0x18000000 |
| 173 | blk.14.ffn_gate_inp.weight | 0x47dd6efa0 | 0x100000 |
| 174 | blk.14.ffn_norm.weight | 0x47de6efa0 | 0x2000 |
| 175 | blk.14.attn_k_norm.weight | 0x47de70fa0 | 0x200 |
| 176 | blk.14.attn_k.weight | 0x47de711a0 | 0x200000 |
| 177 | blk.14.attn_output.weight | 0x47e0711a0 | 0x1000000 |
| 178 | blk.14.attn_q_norm.weight | 0x47f0711a0 | 0x200 |
| 179 | blk.14.attn_q.weight | 0x47f0713a0 | 0x1000000 |
| 180 | blk.14.attn_v.weight | 0x4800713a0 | 0x200000 |
| 181 | blk.15.ffn_gate_inp.weight | 0x4802713a0 | 0x100000 |
| 182 | blk.15.attn_k_norm.weight | 0x4803713a0 | 0x200 |
| 183 | blk.15.attn_k.weight | 0x4803715a0 | 0x200000 |
| 184 | blk.15.attn_output.weight | 0x4805715a0 | 0x1000000 |
| 185 | blk.15.attn_q_norm.weight | 0x4815715a0 | 0x200 |
| 186 | blk.15.attn_q.weight | 0x4815717a0 | 0x1000000 |
| 187 | blk.15.attn_v.weight | 0x4825717a0 | 0x200000 |
| 188 | blk.15.attn_norm.weight | 0x4827717a0 | 0x2000 |
| 189 | blk.15.ffn_down_exps.weight | 0x4827737a0 | 0x18000000 |
| 190 | blk.15.ffn_gate_exps.weight | 0x49a7737a0 | 0x18000000 |
| 191 | blk.15.ffn_up_exps.weight | 0x4b27737a0 | 0x18000000 |
| 192 | blk.15.ffn_norm.weight | 0x4ca7737a0 | 0x2000 |
| 193 | blk.16.attn_norm.weight | 0x4ca7757a0 | 0x2000 |
| 194 | blk.16.ffn_down_exps.weight | 0x4ca7777a0 | 0x18000000 |
| 195 | blk.16.ffn_gate_exps.weight | 0x4e27777a0 | 0x18000000 |
| 196 | blk.16.ffn_up_exps.weight | 0x4fa7777a0 | 0x18000000 |
| 197 | blk.16.ffn_gate_inp.weight | 0x5127777a0 | 0x100000 |
| 198 | blk.16.ffn_norm.weight | 0x5128777a0 | 0x2000 |
| 199 | blk.16.attn_k_norm.weight | 0x5128797a0 | 0x200 |
| 200 | blk.16.attn_k.weight | 0x5128799a0 | 0x200000 |
| 201 | blk.16.attn_output.weight | 0x512a799a0 | 0x1000000 |
| 202 | blk.16.attn_q_norm.weight | 0x513a799a0 | 0x200 |
| 203 | blk.16.attn_q.weight | 0x513a79ba0 | 0x1000000 |
| 204 | blk.16.attn_v.weight | 0x514a79ba0 | 0x200000 |
| 205 | blk.17.attn_norm.weight | 0x514c79ba0 | 0x2000 |
| 206 | blk.17.ffn_down_exps.weight | 0x514c7bba0 | 0x18000000 |
| 207 | blk.17.ffn_gate_exps.weight | 0x52cc7bba0 | 0x18000000 |
| 208 | blk.17.ffn_up_exps.weight | 0x544c7bba0 | 0x18000000 |
| 209 | blk.17.ffn_gate_inp.weight | 0x55cc7bba0 | 0x100000 |
| 210 | blk.17.ffn_norm.weight | 0x55cd7bba0 | 0x2000 |
| 211 | blk.17.attn_k_norm.weight | 0x55cd7dba0 | 0x200 |
| 212 | blk.17.attn_k.weight | 0x55cd7dda0 | 0x200000 |
| 213 | blk.17.attn_output.weight | 0x55cf7dda0 | 0x1000000 |
| 214 | blk.17.attn_q_norm.weight | 0x55df7dda0 | 0x200 |
| 215 | blk.17.attn_q.weight | 0x55df7dfa0 | 0x1000000 |
| 216 | blk.17.attn_v.weight | 0x55ef7dfa0 | 0x200000 |
| 217 | blk.18.ffn_gate_inp.weight | 0x55f17dfa0 | 0x100000 |
| 218 | blk.18.attn_k_norm.weight | 0x55f27dfa0 | 0x200 |
| 219 | blk.18.attn_k.weight | 0x55f27e1a0 | 0x200000 |
| 220 | blk.18.attn_output.weight | 0x55f47e1a0 | 0x1000000 |
| 221 | blk.18.attn_q_norm.weight | 0x56047e1a0 | 0x200 |
| 222 | blk.18.attn_q.weight | 0x56047e3a0 | 0x1000000 |
| 223 | blk.18.attn_v.weight | 0x56147e3a0 | 0x200000 |
| 224 | blk.18.attn_norm.weight | 0x56167e3a0 | 0x2000 |
| 225 | blk.18.ffn_down_exps.weight | 0x5616803a0 | 0x18000000 |
| 226 | blk.18.ffn_gate_exps.weight | 0x5796803a0 | 0x18000000 |
| 227 | blk.18.ffn_up_exps.weight | 0x5916803a0 | 0x18000000 |
| 228 | blk.18.ffn_norm.weight | 0x5a96803a0 | 0x2000 |
| 229 | blk.19.attn_norm.weight | 0x5a96823a0 | 0x2000 |
| 230 | blk.19.ffn_down_exps.weight | 0x5a96843a0 | 0x18000000 |
| 231 | blk.19.ffn_gate_exps.weight | 0x5c16843a0 | 0x18000000 |
| 232 | blk.19.ffn_up_exps.weight | 0x5d96843a0 | 0x18000000 |
| 233 | blk.19.ffn_gate_inp.weight | 0x5f16843a0 | 0x100000 |
| 234 | blk.19.ffn_norm.weight | 0x5f17843a0 | 0x2000 |
| 235 | blk.19.attn_k_norm.weight | 0x5f17863a0 | 0x200 |
| 236 | blk.19.attn_k.weight | 0x5f17865a0 | 0x200000 |
| 237 | blk.19.attn_output.weight | 0x5f19865a0 | 0x1000000 |
| 238 | blk.19.attn_q_norm.weight | 0x5f29865a0 | 0x200 |
| 239 | blk.19.attn_q.weight | 0x5f29867a0 | 0x1000000 |
| 240 | blk.19.attn_v.weight | 0x5f39867a0 | 0x200000 |
| 241 | blk.20.attn_norm.weight | 0x5f3b867a0 | 0x2000 |
| 242 | blk.20.ffn_down_exps.weight | 0x5f3b887a0 | 0x18000000 |
| 243 | blk.20.ffn_gate_exps.weight | 0x60bb887a0 | 0x18000000 |
| 244 | blk.20.ffn_up_exps.weight | 0x623b887a0 | 0x18000000 |
| 245 | blk.20.ffn_gate_inp.weight | 0x63bb887a0 | 0x100000 |
| 246 | blk.20.ffn_norm.weight | 0x63bc887a0 | 0x2000 |
| 247 | blk.20.attn_k_norm.weight | 0x63bc8a7a0 | 0x200 |
| 248 | blk.20.attn_k.weight | 0x63bc8a9a0 | 0x200000 |
| 249 | blk.20.attn_output.weight | 0x63be8a9a0 | 0x1000000 |
| 250 | blk.20.attn_q_norm.weight | 0x63ce8a9a0 | 0x200 |
| 251 | blk.20.attn_q.weight | 0x63ce8aba0 | 0x1000000 |
| 252 | blk.20.attn_v.weight | 0x63de8aba0 | 0x200000 |
| 253 | blk.21.ffn_gate_inp.weight | 0x63e08aba0 | 0x100000 |
| 254 | blk.21.attn_k_norm.weight | 0x63e18aba0 | 0x200 |
| 255 | blk.21.attn_k.weight | 0x63e18ada0 | 0x200000 |
| 256 | blk.21.attn_output.weight | 0x63e38ada0 | 0x1000000 |
| 257 | blk.21.attn_q_norm.weight | 0x63f38ada0 | 0x200 |
| 258 | blk.21.attn_q.weight | 0x63f38afa0 | 0x1000000 |
| 259 | blk.21.attn_v.weight | 0x64038afa0 | 0x200000 |
| 260 | blk.21.attn_norm.weight | 0x64058afa0 | 0x2000 |
| 261 | blk.21.ffn_down_exps.weight | 0x64058cfa0 | 0x18000000 |
| 262 | blk.21.ffn_gate_exps.weight | 0x65858cfa0 | 0x18000000 |
| 263 | blk.21.ffn_up_exps.weight | 0x67058cfa0 | 0x18000000 |
| 264 | blk.21.ffn_norm.weight | 0x68858cfa0 | 0x2000 |
| 265 | blk.22.attn_norm.weight | 0x68858efa0 | 0x2000 |
| 266 | blk.22.ffn_down_exps.weight | 0x688590fa0 | 0x18000000 |
| 267 | blk.22.ffn_gate_exps.weight | 0x6a0590fa0 | 0x18000000 |
| 268 | blk.22.ffn_up_exps.weight | 0x6b8590fa0 | 0x18000000 |
| 269 | blk.22.ffn_gate_inp.weight | 0x6d0590fa0 | 0x100000 |
| 270 | blk.22.ffn_norm.weight | 0x6d0690fa0 | 0x2000 |
| 271 | blk.22.attn_k_norm.weight | 0x6d0692fa0 | 0x200 |
| 272 | blk.22.attn_k.weight | 0x6d06931a0 | 0x200000 |
| 273 | blk.22.attn_output.weight | 0x6d08931a0 | 0x1000000 |
| 274 | blk.22.attn_q_norm.weight | 0x6d18931a0 | 0x200 |
| 275 | blk.22.attn_q.weight | 0x6d18933a0 | 0x1000000 |
| 276 | blk.22.attn_v.weight | 0x6d28933a0 | 0x200000 |
| 277 | blk.23.attn_norm.weight | 0x6d2a933a0 | 0x2000 |
| 278 | blk.23.ffn_down_exps.weight | 0x6d2a953a0 | 0x18000000 |
| 279 | blk.23.ffn_gate_exps.weight | 0x6eaa953a0 | 0x18000000 |
| 280 | blk.23.ffn_up_exps.weight | 0x702a953a0 | 0x18000000 |
| 281 | blk.23.ffn_gate_inp.weight | 0x71aa953a0 | 0x100000 |
| 282 | blk.23.ffn_norm.weight | 0x71ab953a0 | 0x2000 |
| 283 | blk.23.attn_k_norm.weight | 0x71ab973a0 | 0x200 |
| 284 | blk.23.attn_k.weight | 0x71ab975a0 | 0x200000 |
| 285 | blk.23.attn_output.weight | 0x71ad975a0 | 0x1000000 |
| 286 | blk.23.attn_q_norm.weight | 0x71bd975a0 | 0x200 |
| 287 | blk.23.attn_q.weight | 0x71bd977a0 | 0x1000000 |
| 288 | blk.23.attn_v.weight | 0x71cd977a0 | 0x200000 |
| 289 | blk.24.attn_norm.weight | 0x71cf977a0 | 0x2000 |
| 290 | blk.24.ffn_down_exps.weight | 0x71cf997a0 | 0x18000000 |
| 291 | blk.24.ffn_gate_exps.weight | 0x734f997a0 | 0x18000000 |
| 292 | blk.24.ffn_up_exps.weight | 0x74cf997a0 | 0x18000000 |
| 293 | blk.24.ffn_gate_inp.weight | 0x764f997a0 | 0x100000 |
| 294 | blk.24.ffn_norm.weight | 0x7650997a0 | 0x2000 |
| 295 | blk.24.attn_k_norm.weight | 0x76509b7a0 | 0x200 |
| 296 | blk.24.attn_k.weight | 0x76509b9a0 | 0x200000 |
| 297 | blk.24.attn_output.weight | 0x76529b9a0 | 0x1000000 |
| 298 | blk.24.attn_q_norm.weight | 0x76629b9a0 | 0x200 |
| 299 | blk.24.attn_q.weight | 0x76629bba0 | 0x1000000 |
| 300 | blk.24.attn_v.weight | 0x76729bba0 | 0x200000 |
| 301 | blk.25.ffn_gate_inp.weight | 0x76749bba0 | 0x100000 |
| 302 | blk.25.attn_k_norm.weight | 0x76759bba0 | 0x200 |
| 303 | blk.25.attn_k.weight | 0x76759bda0 | 0x200000 |
| 304 | blk.25.attn_output.weight | 0x76779bda0 | 0x1000000 |
| 305 | blk.25.attn_q_norm.weight | 0x76879bda0 | 0x200 |
| 306 | blk.25.attn_q.weight | 0x76879bfa0 | 0x1000000 |
| 307 | blk.25.attn_v.weight | 0x76979bfa0 | 0x200000 |
| 308 | blk.25.attn_norm.weight | 0x76999bfa0 | 0x2000 |
| 309 | blk.25.ffn_down_exps.weight | 0x76999dfa0 | 0x18000000 |
| 310 | blk.25.ffn_gate_exps.weight | 0x78199dfa0 | 0x18000000 |
| 311 | blk.25.ffn_up_exps.weight | 0x79999dfa0 | 0x18000000 |
| 312 | blk.25.ffn_norm.weight | 0x7b199dfa0 | 0x2000 |
| 313 | blk.26.attn_norm.weight | 0x7b199ffa0 | 0x2000 |
| 314 | blk.26.ffn_down_exps.weight | 0x7b19a1fa0 | 0x18000000 |
| 315 | blk.26.ffn_gate_exps.weight | 0x7c99a1fa0 | 0x18000000 |
| 316 | blk.26.ffn_up_exps.weight | 0x7e19a1fa0 | 0x18000000 |
| 317 | blk.26.ffn_gate_inp.weight | 0x7f99a1fa0 | 0x100000 |
| 318 | blk.26.ffn_norm.weight | 0x7f9aa1fa0 | 0x2000 |
| 319 | blk.26.attn_k_norm.weight | 0x7f9aa3fa0 | 0x200 |
| 320 | blk.26.attn_k.weight | 0x7f9aa41a0 | 0x200000 |
| 321 | blk.26.attn_output.weight | 0x7f9ca41a0 | 0x1000000 |
| 322 | blk.26.attn_q_norm.weight | 0x7faca41a0 | 0x200 |
| 323 | blk.26.attn_q.weight | 0x7faca43a0 | 0x1000000 |
| 324 | blk.26.attn_v.weight | 0x7fbca43a0 | 0x200000 |
| 325 | blk.27.attn_norm.weight | 0x7fbea43a0 | 0x2000 |
| 326 | blk.27.ffn_down_exps.weight | 0x7fbea63a0 | 0x18000000 |
| 327 | blk.27.ffn_gate_exps.weight | 0x813ea63a0 | 0x18000000 |
| 328 | blk.27.ffn_up_exps.weight | 0x82bea63a0 | 0x18000000 |
| 329 | blk.27.ffn_gate_inp.weight | 0x843ea63a0 | 0x100000 |
| 330 | blk.27.ffn_norm.weight | 0x843fa63a0 | 0x2000 |
| 331 | blk.27.attn_k_norm.weight | 0x843fa83a0 | 0x200 |
| 332 | blk.27.attn_k.weight | 0x843fa85a0 | 0x200000 |
| 333 | blk.27.attn_output.weight | 0x8441a85a0 | 0x1000000 |
| 334 | blk.27.attn_q_norm.weight | 0x8451a85a0 | 0x200 |
| 335 | blk.27.attn_q.weight | 0x8451a87a0 | 0x1000000 |
| 336 | blk.27.attn_v.weight | 0x8461a87a0 | 0x200000 |
| 337 | blk.28.ffn_gate_inp.weight | 0x8463a87a0 | 0x100000 |
| 338 | blk.28.attn_k_norm.weight | 0x8464a87a0 | 0x200 |
| 339 | blk.28.attn_k.weight | 0x8464a89a0 | 0x200000 |
| 340 | blk.28.attn_output.weight | 0x8466a89a0 | 0x1000000 |
| 341 | blk.28.attn_q_norm.weight | 0x8476a89a0 | 0x200 |
| 342 | blk.28.attn_q.weight | 0x8476a8ba0 | 0x1000000 |
| 343 | blk.28.attn_v.weight | 0x8486a8ba0 | 0x200000 |
| 344 | blk.28.attn_norm.weight | 0x8488a8ba0 | 0x2000 |
| 345 | blk.28.ffn_down_exps.weight | 0x8488aaba0 | 0x18000000 |
| 346 | blk.28.ffn_gate_exps.weight | 0x8608aaba0 | 0x18000000 |
| 347 | blk.28.ffn_up_exps.weight | 0x8788aaba0 | 0x18000000 |
| 348 | blk.28.ffn_norm.weight | 0x8908aaba0 | 0x2000 |
| 349 | blk.29.attn_norm.weight | 0x8908acba0 | 0x2000 |
| 350 | blk.29.ffn_down_exps.weight | 0x8908aeba0 | 0x18000000 |
| 351 | blk.29.ffn_gate_exps.weight | 0x8a88aeba0 | 0x18000000 |
| 352 | blk.29.ffn_up_exps.weight | 0x8c08aeba0 | 0x18000000 |
| 353 | blk.29.ffn_gate_inp.weight | 0x8d88aeba0 | 0x100000 |
| 354 | blk.29.ffn_norm.weight | 0x8d89aeba0 | 0x2000 |
| 355 | blk.29.attn_k_norm.weight | 0x8d89b0ba0 | 0x200 |
| 356 | blk.29.attn_k.weight | 0x8d89b0da0 | 0x200000 |
| 357 | blk.29.attn_output.weight | 0x8d8bb0da0 | 0x1000000 |
| 358 | blk.29.attn_q_norm.weight | 0x8d9bb0da0 | 0x200 |
| 359 | blk.29.attn_q.weight | 0x8d9bb0fa0 | 0x1000000 |
| 360 | blk.29.attn_v.weight | 0x8dabb0fa0 | 0x200000 |
| 361 | blk.30.attn_norm.weight | 0x8dadb0fa0 | 0x2000 |
| 362 | blk.30.ffn_down_exps.weight | 0x8dadb2fa0 | 0x18000000 |
| 363 | blk.30.ffn_gate_exps.weight | 0x8f2db2fa0 | 0x18000000 |
| 364 | blk.30.ffn_up_exps.weight | 0x90adb2fa0 | 0x18000000 |
| 365 | blk.30.ffn_gate_inp.weight | 0x922db2fa0 | 0x100000 |
| 366 | blk.30.ffn_norm.weight | 0x922eb2fa0 | 0x2000 |
| 367 | blk.30.attn_k_norm.weight | 0x922eb4fa0 | 0x200 |
| 368 | blk.30.attn_k.weight | 0x922eb51a0 | 0x200000 |
| 369 | blk.30.attn_output.weight | 0x9230b51a0 | 0x1000000 |
| 370 | blk.30.attn_q_norm.weight | 0x9240b51a0 | 0x200 |
| 371 | blk.30.attn_q.weight | 0x9240b53a0 | 0x1000000 |
| 372 | blk.30.attn_v.weight | 0x9250b53a0 | 0x200000 |
| 373 | blk.31.ffn_gate_inp.weight | 0x9252b53a0 | 0x100000 |
| 374 | blk.31.attn_k_norm.weight | 0x9253b53a0 | 0x200 |
| 375 | blk.31.attn_k.weight | 0x9253b55a0 | 0x200000 |
| 376 | blk.31.attn_output.weight | 0x9255b55a0 | 0x1000000 |
| 377 | blk.31.attn_q_norm.weight | 0x9265b55a0 | 0x200 |
| 378 | blk.31.attn_q.weight | 0x9265b57a0 | 0x1000000 |
| 379 | blk.31.attn_v.weight | 0x9275b57a0 | 0x200000 |
| 380 | blk.31.attn_norm.weight | 0x9277b57a0 | 0x2000 |
| 381 | blk.31.ffn_down_exps.weight | 0x9277b77a0 | 0x18000000 |
| 382 | blk.31.ffn_gate_exps.weight | 0x93f7b77a0 | 0x18000000 |
| 383 | blk.31.ffn_up_exps.weight | 0x9577b77a0 | 0x18000000 |
| 384 | blk.31.ffn_norm.weight | 0x96f7b77a0 | 0x2000 |
| 385 | blk.32.attn_norm.weight | 0x96f7b97a0 | 0x2000 |
| 386 | blk.32.ffn_down_exps.weight | 0x96f7bb7a0 | 0x18000000 |
| 387 | blk.32.ffn_gate_exps.weight | 0x9877bb7a0 | 0x18000000 |
| 388 | blk.32.ffn_up_exps.weight | 0x99f7bb7a0 | 0x18000000 |
| 389 | blk.32.ffn_gate_inp.weight | 0x9b77bb7a0 | 0x100000 |
| 390 | blk.32.ffn_norm.weight | 0x9b78bb7a0 | 0x2000 |
| 391 | blk.32.attn_k_norm.weight | 0x9b78bd7a0 | 0x200 |
| 392 | blk.32.attn_k.weight | 0x9b78bd9a0 | 0x200000 |
| 393 | blk.32.attn_output.weight | 0x9b7abd9a0 | 0x1000000 |
| 394 | blk.32.attn_q_norm.weight | 0x9b8abd9a0 | 0x200 |
| 395 | blk.32.attn_q.weight | 0x9b8abdba0 | 0x1000000 |
| 396 | blk.32.attn_v.weight | 0x9b9abdba0 | 0x200000 |
| 397 | blk.33.attn_norm.weight | 0x9b9cbdba0 | 0x2000 |
| 398 | blk.33.ffn_down_exps.weight | 0x9b9cbfba0 | 0x18000000 |
| 399 | blk.33.ffn_gate_exps.weight | 0x9d1cbfba0 | 0x18000000 |
| 400 | blk.33.ffn_up_exps.weight | 0x9e9cbfba0 | 0x18000000 |
| 401 | blk.33.ffn_gate_inp.weight | 0xa01cbfba0 | 0x100000 |
| 402 | blk.33.ffn_norm.weight | 0xa01dbfba0 | 0x2000 |
| 403 | blk.33.attn_k_norm.weight | 0xa01dc1ba0 | 0x200 |
| 404 | blk.33.attn_k.weight | 0xa01dc1da0 | 0x200000 |
| 405 | blk.33.attn_output.weight | 0xa01fc1da0 | 0x1000000 |
| 406 | blk.33.attn_q_norm.weight | 0xa02fc1da0 | 0x200 |
| 407 | blk.33.attn_q.weight | 0xa02fc1fa0 | 0x1000000 |
| 408 | blk.33.attn_v.weight | 0xa03fc1fa0 | 0x200000 |
| 409 | blk.34.ffn_gate_inp.weight | 0xa041c1fa0 | 0x100000 |
| 410 | blk.34.attn_k_norm.weight | 0xa042c1fa0 | 0x200 |
| 411 | blk.34.attn_k.weight | 0xa042c21a0 | 0x200000 |
| 412 | blk.34.attn_output.weight | 0xa044c21a0 | 0x1000000 |
| 413 | blk.34.attn_q_norm.weight | 0xa054c21a0 | 0x200 |
| 414 | blk.34.attn_q.weight | 0xa054c23a0 | 0x1000000 |
| 415 | blk.34.attn_v.weight | 0xa064c23a0 | 0x200000 |
| 416 | blk.34.attn_norm.weight | 0xa066c23a0 | 0x2000 |
| 417 | blk.34.ffn_down_exps.weight | 0xa066c43a0 | 0x18000000 |
| 418 | blk.34.ffn_gate_exps.weight | 0xa1e6c43a0 | 0x18000000 |
| 419 | blk.34.ffn_up_exps.weight | 0xa366c43a0 | 0x18000000 |
| 420 | blk.34.ffn_norm.weight | 0xa4e6c43a0 | 0x2000 |
| 421 | blk.35.attn_norm.weight | 0xa4e6c63a0 | 0x2000 |
| 422 | blk.35.ffn_down_exps.weight | 0xa4e6c83a0 | 0x18000000 |
| 423 | blk.35.ffn_gate_exps.weight | 0xa666c83a0 | 0x18000000 |
| 424 | blk.35.ffn_up_exps.weight | 0xa7e6c83a0 | 0x18000000 |
| 425 | blk.35.ffn_gate_inp.weight | 0xa966c83a0 | 0x100000 |
| 426 | blk.35.ffn_norm.weight | 0xa967c83a0 | 0x2000 |
| 427 | blk.35.attn_k_norm.weight | 0xa967ca3a0 | 0x200 |
| 428 | blk.35.attn_k.weight | 0xa967ca5a0 | 0x200000 |
| 429 | blk.35.attn_output.weight | 0xa969ca5a0 | 0x1000000 |
| 430 | blk.35.attn_q_norm.weight | 0xa979ca5a0 | 0x200 |
| 431 | blk.35.attn_q.weight | 0xa979ca7a0 | 0x1000000 |
| 432 | blk.35.attn_v.weight | 0xa989ca7a0 | 0x200000 |
| 433 | blk.36.attn_norm.weight | 0xa98bca7a0 | 0x2000 |
| 434 | blk.36.ffn_down_exps.weight | 0xa98bcc7a0 | 0x18000000 |
| 435 | blk.36.ffn_gate_exps.weight | 0xab0bcc7a0 | 0x18000000 |
| 436 | blk.36.ffn_up_exps.weight | 0xac8bcc7a0 | 0x18000000 |
| 437 | blk.36.ffn_gate_inp.weight | 0xae0bcc7a0 | 0x100000 |
| 438 | blk.36.ffn_norm.weight | 0xae0ccc7a0 | 0x2000 |
| 439 | blk.36.attn_k_norm.weight | 0xae0cce7a0 | 0x200 |
| 440 | blk.36.attn_k.weight | 0xae0cce9a0 | 0x200000 |
| 441 | blk.36.attn_output.weight | 0xae0ece9a0 | 0x1000000 |
| 442 | blk.36.attn_q_norm.weight | 0xae1ece9a0 | 0x200 |
| 443 | blk.36.attn_q.weight | 0xae1eceba0 | 0x1000000 |
| 444 | blk.36.attn_v.weight | 0xae2eceba0 | 0x200000 |
| 445 | blk.37.attn_norm.weight | 0xae30ceba0 | 0x2000 |
| 446 | blk.37.ffn_down_exps.weight | 0xae30d0ba0 | 0x18000000 |
| 447 | blk.37.ffn_gate_exps.weight | 0xafb0d0ba0 | 0x18000000 |
| 448 | blk.37.ffn_up_exps.weight | 0xb130d0ba0 | 0x18000000 |
| 449 | blk.37.ffn_gate_inp.weight | 0xb2b0d0ba0 | 0x100000 |
| 450 | blk.37.ffn_norm.weight | 0xb2b1d0ba0 | 0x2000 |
| 451 | blk.37.attn_k_norm.weight | 0xb2b1d2ba0 | 0x200 |
| 452 | blk.37.attn_k.weight | 0xb2b1d2da0 | 0x200000 |
| 453 | blk.37.attn_output.weight | 0xb2b3d2da0 | 0x1000000 |
| 454 | blk.37.attn_q_norm.weight | 0xb2c3d2da0 | 0x200 |
| 455 | blk.37.attn_q.weight | 0xb2c3d2fa0 | 0x1000000 |
| 456 | blk.37.attn_v.weight | 0xb2d3d2fa0 | 0x200000 |
| 457 | blk.38.attn_norm.weight | 0xb2d5d2fa0 | 0x2000 |
| 458 | blk.38.ffn_down_exps.weight | 0xb2d5d4fa0 | 0x18000000 |
| 459 | blk.38.ffn_gate_exps.weight | 0xb455d4fa0 | 0x18000000 |
| 460 | blk.38.ffn_up_exps.weight | 0xb5d5d4fa0 | 0x18000000 |
| 461 | blk.38.ffn_gate_inp.weight | 0xb755d4fa0 | 0x100000 |
| 462 | blk.38.ffn_norm.weight | 0xb756d4fa0 | 0x2000 |
| 463 | blk.38.attn_k_norm.weight | 0xb756d6fa0 | 0x200 |
| 464 | blk.38.attn_k.weight | 0xb756d71a0 | 0x200000 |
| 465 | blk.38.attn_output.weight | 0xb758d71a0 | 0x1000000 |
| 466 | blk.38.attn_q_norm.weight | 0xb768d71a0 | 0x200 |
| 467 | blk.38.attn_q.weight | 0xb768d73a0 | 0x1000000 |
| 468 | blk.38.attn_v.weight | 0xb778d73a0 | 0x200000 |
| 469 | blk.39.attn_norm.weight | 0xb77ad73a0 | 0x2000 |
| 470 | blk.39.ffn_down_exps.weight | 0xb77ad93a0 | 0x18000000 |
| 471 | blk.39.ffn_gate_exps.weight | 0xb8fad93a0 | 0x18000000 |
| 472 | blk.39.ffn_up_exps.weight | 0xba7ad93a0 | 0x18000000 |
| 473 | blk.39.ffn_gate_inp.weight | 0xbbfad93a0 | 0x100000 |
| 474 | blk.39.ffn_norm.weight | 0xbbfbd93a0 | 0x2000 |
| 475 | blk.39.attn_k_norm.weight | 0xbbfbdb3a0 | 0x200 |
| 476 | blk.39.attn_k.weight | 0xbbfbdb5a0 | 0x200000 |
| 477 | blk.39.attn_output.weight | 0xbbfddb5a0 | 0x1000000 |
| 478 | blk.39.attn_q_norm.weight | 0xbc0ddb5a0 | 0x200 |
| 479 | blk.39.attn_q.weight | 0xbc0ddb7a0 | 0x1000000 |
| 480 | blk.39.attn_v.weight | 0xbc1ddb7a0 | 0x200000 |
| 481 | blk.40.attn_norm.weight | 0xbc1fdb7a0 | 0x2000 |
| 482 | blk.40.ffn_down_exps.weight | 0xbc1fdd7a0 | 0x18000000 |
| 483 | blk.40.ffn_gate_exps.weight | 0xbd9fdd7a0 | 0x18000000 |
| 484 | blk.40.ffn_up_exps.weight | 0xbf1fdd7a0 | 0x18000000 |
| 485 | blk.40.ffn_gate_inp.weight | 0xc09fdd7a0 | 0x100000 |
| 486 | blk.40.ffn_norm.weight | 0xc0a0dd7a0 | 0x2000 |
| 487 | blk.40.attn_k_norm.weight | 0xc0a0df7a0 | 0x200 |
| 488 | blk.40.attn_k.weight | 0xc0a0df9a0 | 0x200000 |
| 489 | blk.40.attn_output.weight | 0xc0a2df9a0 | 0x1000000 |
| 490 | blk.40.attn_q_norm.weight | 0xc0b2df9a0 | 0x200 |
| 491 | blk.40.attn_q.weight | 0xc0b2dfba0 | 0x1000000 |
| 492 | blk.40.attn_v.weight | 0xc0c2dfba0 | 0x200000 |
| 493 | blk.41.ffn_gate_inp.weight | 0xc0c4dfba0 | 0x100000 |
| 494 | blk.41.attn_k_norm.weight | 0xc0c5dfba0 | 0x200 |
| 495 | blk.41.attn_k.weight | 0xc0c5dfda0 | 0x200000 |
| 496 | blk.41.attn_output.weight | 0xc0c7dfda0 | 0x1000000 |
| 497 | blk.41.attn_q_norm.weight | 0xc0d7dfda0 | 0x200 |
| 498 | blk.41.attn_q.weight | 0xc0d7dffa0 | 0x1000000 |
| 499 | blk.41.attn_v.weight | 0xc0e7dffa0 | 0x200000 |
| 500 | blk.41.attn_norm.weight | 0xc0e9dffa0 | 0x2000 |
| 501 | blk.41.ffn_down_exps.weight | 0xc0e9e1fa0 | 0x18000000 |
| 502 | blk.41.ffn_gate_exps.weight | 0xc269e1fa0 | 0x18000000 |
| 503 | blk.41.ffn_up_exps.weight | 0xc3e9e1fa0 | 0x18000000 |
| 504 | blk.41.ffn_norm.weight | 0xc569e1fa0 | 0x2000 |
| 505 | blk.42.attn_norm.weight | 0xc569e3fa0 | 0x2000 |
| 506 | blk.42.ffn_down_exps.weight | 0xc569e5fa0 | 0x18000000 |
| 507 | blk.42.ffn_gate_exps.weight | 0xc6e9e5fa0 | 0x18000000 |
| 508 | blk.42.ffn_up_exps.weight | 0xc869e5fa0 | 0x18000000 |
| 509 | blk.42.ffn_gate_inp.weight | 0xc9e9e5fa0 | 0x100000 |
| 510 | blk.42.ffn_norm.weight | 0xc9eae5fa0 | 0x2000 |
| 511 | blk.42.attn_k_norm.weight | 0xc9eae7fa0 | 0x200 |
| 512 | blk.42.attn_k.weight | 0xc9eae81a0 | 0x200000 |
| 513 | blk.42.attn_output.weight | 0xc9ece81a0 | 0x1000000 |
| 514 | blk.42.attn_q_norm.weight | 0xc9fce81a0 | 0x200 |
| 515 | blk.42.attn_q.weight | 0xc9fce83a0 | 0x1000000 |
| 516 | blk.42.attn_v.weight | 0xca0ce83a0 | 0x200000 |
| 517 | blk.43.attn_norm.weight | 0xca0ee83a0 | 0x2000 |
| 518 | blk.43.ffn_down_exps.weight | 0xca0eea3a0 | 0x18000000 |
| 519 | blk.43.ffn_gate_exps.weight | 0xcb8eea3a0 | 0x18000000 |
| 520 | blk.43.ffn_up_exps.weight | 0xcd0eea3a0 | 0x18000000 |
| 521 | blk.43.ffn_gate_inp.weight | 0xce8eea3a0 | 0x100000 |
| 522 | blk.43.ffn_norm.weight | 0xce8fea3a0 | 0x2000 |
| 523 | blk.43.attn_k_norm.weight | 0xce8fec3a0 | 0x200 |
| 524 | blk.43.attn_k.weight | 0xce8fec5a0 | 0x200000 |
| 525 | blk.43.attn_output.weight | 0xce91ec5a0 | 0x1000000 |
| 526 | blk.43.attn_q_norm.weight | 0xcea1ec5a0 | 0x200 |
| 527 | blk.43.attn_q.weight | 0xcea1ec7a0 | 0x1000000 |
| 528 | blk.43.attn_v.weight | 0xceb1ec7a0 | 0x200000 |
| 529 | blk.44.ffn_gate_inp.weight | 0xceb3ec7a0 | 0x100000 |
| 530 | blk.44.attn_k_norm.weight | 0xceb4ec7a0 | 0x200 |
| 531 | blk.44.attn_k.weight | 0xceb4ec9a0 | 0x200000 |
| 532 | blk.44.attn_output.weight | 0xceb6ec9a0 | 0x1000000 |
| 533 | blk.44.attn_q_norm.weight | 0xcec6ec9a0 | 0x200 |
| 534 | blk.44.attn_q.weight | 0xcec6ecba0 | 0x1000000 |
| 535 | blk.44.attn_v.weight | 0xced6ecba0 | 0x200000 |
| 536 | blk.44.attn_norm.weight | 0xced8ecba0 | 0x2000 |
| 537 | blk.44.ffn_down_exps.weight | 0xced8eeba0 | 0x18000000 |
| 538 | blk.44.ffn_gate_exps.weight | 0xd058eeba0 | 0x18000000 |
| 539 | blk.44.ffn_up_exps.weight | 0xd1d8eeba0 | 0x18000000 |
| 540 | blk.44.ffn_norm.weight | 0xd358eeba0 | 0x2000 |
| 541 | blk.45.attn_norm.weight | 0xd358f0ba0 | 0x2000 |
| 542 | blk.45.ffn_down_exps.weight | 0xd358f2ba0 | 0x18000000 |
| 543 | blk.45.ffn_gate_exps.weight | 0xd4d8f2ba0 | 0x18000000 |
| 544 | blk.45.ffn_up_exps.weight | 0xd658f2ba0 | 0x18000000 |
| 545 | blk.45.ffn_gate_inp.weight | 0xd7d8f2ba0 | 0x100000 |
| 546 | blk.45.ffn_norm.weight | 0xd7d9f2ba0 | 0x2000 |
| 547 | blk.45.attn_k_norm.weight | 0xd7d9f4ba0 | 0x200 |
| 548 | blk.45.attn_k.weight | 0xd7d9f4da0 | 0x200000 |
| 549 | blk.45.attn_output.weight | 0xd7dbf4da0 | 0x1000000 |
| 550 | blk.45.attn_q_norm.weight | 0xd7ebf4da0 | 0x200 |
| 551 | blk.45.attn_q.weight | 0xd7ebf4fa0 | 0x1000000 |
| 552 | blk.45.attn_v.weight | 0xd7fbf4fa0 | 0x200000 |
| 553 | blk.46.attn_norm.weight | 0xd7fdf4fa0 | 0x2000 |
| 554 | blk.46.ffn_down_exps.weight | 0xd7fdf6fa0 | 0x18000000 |
| 555 | blk.46.ffn_gate_exps.weight | 0xd97df6fa0 | 0x18000000 |
| 556 | blk.46.ffn_up_exps.weight | 0xdafdf6fa0 | 0x18000000 |
| 557 | blk.46.ffn_gate_inp.weight | 0xdc7df6fa0 | 0x100000 |
| 558 | blk.46.ffn_norm.weight | 0xdc7ef6fa0 | 0x2000 |
| 559 | blk.46.attn_k_norm.weight | 0xdc7ef8fa0 | 0x200 |
| 560 | blk.46.attn_k.weight | 0xdc7ef91a0 | 0x200000 |
| 561 | blk.46.attn_output.weight | 0xdc80f91a0 | 0x1000000 |
| 562 | blk.46.attn_q_norm.weight | 0xdc90f91a0 | 0x200 |
| 563 | blk.46.attn_q.weight | 0xdc90f93a0 | 0x1000000 |
| 564 | blk.46.attn_v.weight | 0xdca0f93a0 | 0x200000 |
| 565 | blk.47.ffn_gate_inp.weight | 0xdca2f93a0 | 0x100000 |
| 566 | blk.47.attn_k_norm.weight | 0xdca3f93a0 | 0x200 |
| 567 | blk.47.attn_k.weight | 0xdca3f95a0 | 0x200000 |
| 568 | blk.47.attn_output.weight | 0xdca5f95a0 | 0x1000000 |
| 569 | blk.47.attn_q_norm.weight | 0xdcb5f95a0 | 0x200 |
| 570 | blk.47.attn_q.weight | 0xdcb5f97a0 | 0x1000000 |
| 571 | blk.47.attn_v.weight | 0xdcc5f97a0 | 0x200000 |
| 572 | output.weight | 0xdcc7f97a0 | 0x25180000 |
| 573 | blk.47.attn_norm.weight | 0xdf19797a0 | 0x2000 |
| 574 | blk.47.ffn_down_exps.weight | 0xdf197b7a0 | 0x18000000 |
| 575 | blk.47.ffn_gate_exps.weight | 0xe0997b7a0 | 0x18000000 |
| 576 | blk.47.ffn_up_exps.weight | 0xe2197b7a0 | 0x18000000 |
| 577 | blk.47.ffn_norm.weight | 0xe3997b7a0 | 0x2000 |
| 578 | output_norm.weight | 0xe3997d7a0 | 0x2000 |
### Base Tensor Group : ~622M Elements
| T_ID | Tensor Layer Name | Human Friendly Tensor Layer Name | Elements | Shape | Type |
|-----:|:-------------------|:---------------------------------|:------------------|:----------------------|:-----|
| 0 | token_embd.weight | Token Embedding (W) | (~311M) 311164928 | 2048 x 151936 x 1 x 1 | F16 |
| 572 | output.weight | Output (W) | (~311M) 311164928 | 2048 x 151936 x 1 x 1 | F16 |
| 578 | output_norm.weight | Output Normalization (W) | ( ~2K) 2048 | 2048 x 1 x 1 x 1 | F32 |
- Total elements in base: (~622M) 622331904
- Percentage of total elements: 2.04%
### Block 0 Tensor Group : ~623M Elements
| T_ID | Tensor Layer Name | Human Friendly Tensor Layer Name | Elements | Shape | Type |
|-----:|:---------------------------|:------------------------------------------------------------------------------------------|:------------------|:----------------------|:-----|
| 1 | blk.0.attn_norm.weight | Block 0 Attention Normalization (W) | ( ~2K) 2048 | 2048 x 1 x 1 x 1 | F32 |
| 2 | blk.0.ffn_down_exps.weight | Block 0 Ffn_Down_Exps (W) | (~201M) 201326592 | 768 x 2048 x 128 x 1 | F16 |
| 3 | blk.0.ffn_gate_exps.weight | Block 0 Ffn_Gate_Exps (W) | (~201M) 201326592 | 2048 x 768 x 128 x 1 | F16 |
| 4 | blk.0.ffn_up_exps.weight | Block 0 Ffn_Up_Exps (W) | (~201M) 201326592 | 2048 x 768 x 128 x 1 | F16 |
| 5 | blk.0.ffn_gate_inp.weight | Block 0 Expert-Routing Layer For The Feed-Forward Network In Mixture Of Expert Models (W) | (~262K) 262144 | 2048 x 128 x 1 x 1 | F32 |
| 6 | blk.0.ffn_norm.weight | Block 0 Feed-Forward Network Normalization (W) | ( ~2K) 2048 | 2048 x 1 x 1 x 1 | F32 |
| 7 | blk.0.attn_k_norm.weight | Block 0 Attn_K_Norm (W) | ( 128) 128 | 128 x 1 x 1 x 1 | F32 |
| 8 | blk.0.attn_k.weight | Block 0 Attention Key (W) | ( ~1M) 1048576 | 2048 x 512 x 1 x 1 | F16 |
| 9 | blk.0.attn_output.weight | Block 0 Attention Output (W) | ( ~8M) 8388608 | 4096 x 2048 x 1 x 1 | F16 |
| 10 | blk.0.attn_q_norm.weight | Block 0 Attn_Q_Norm (W) | ( 128) 128 | 128 x 1 x 1 x 1 | F32 |
| 11 | blk.0.attn_q.weight | Block 0 Attention Query (W) | ( ~8M) 8388608 | 2048 x 4096 x 1 x 1 | F16 |
| 12 | blk.0.attn_v.weight | Block 0 Attention Value (W) | ( ~1M) 1048576 | 2048 x 512 x 1 x 1 | F16 |
- Total elements in blk.0: (~623M) 623120640
- Percentage of total elements: 2.04%
### Block 1 Tensor Group : ~623M Elements
| T_ID | Tensor Layer Name | Human Friendly Tensor Layer Name | Elements | Shape | Type |
|-----:|:---------------------------|:------------------------------------------------------------------------------------------|:------------------|:----------------------|:-----|
| 13 | blk.1.attn_norm.weight | Block 1 Attention Normalization (W) | ( ~2K) 2048 | 2048 x 1 x 1 x 1 | F32 |
| 14 | blk.1.ffn_down_exps.weight | Block 1 Ffn_Down_Exps (W) | (~201M) 201326592 | 768 x 2048 x 128 x 1 | F16 |
| 15 | blk.1.ffn_gate_exps.weight | Block 1 Ffn_Gate_Exps (W) | (~201M) 201326592 | 2048 x 768 x 128 x 1 | F16 |
| 16 | blk.1.ffn_up_exps.weight | Block 1 Ffn_Up_Exps (W) | (~201M) 201326592 | 2048 x 768 x 128 x 1 | F16 |
| 17 | blk.1.ffn_gate_inp.weight | Block 1 Expert-Routing Layer For The Feed-Forward Network In Mixture Of Expert Models (W) | (~262K) 262144 | 2048 x 128 x 1 x 1 | F32 |
| 18 | blk.1.ffn_norm.weight | Block 1 Feed-Forward Network Normalization (W) | ( ~2K) 2048 | 2048 x 1 x 1 x 1 | F32 |
| 19 | blk.1.attn_k_norm.weight | Block 1 Attn_K_Norm (W) | ( 128) 128 | 128 x 1 x 1 x 1 | F32 |
| 20 | blk.1.attn_k.weight | Block 1 Attention Key (W) | ( ~1M) 1048576 | 2048 x 512 x 1 x 1 | F16 |
| 21 | blk.1.attn_output.weight | Block 1 Attention Output (W) | ( ~8M) 8388608 | 4096 x 2048 x 1 x 1 | F16 |
| 22 | blk.1.attn_q_norm.weight | Block 1 Attn_Q_Norm (W) | ( 128) 128 | 128 x 1 x 1 x 1 | F32 |
| 23 | blk.1.attn_q.weight | Block 1 Attention Query (W) | ( ~8M) 8388608 | 2048 x 4096 x 1 x 1 | F16 |
| 24 | blk.1.attn_v.weight | Block 1 Attention Value (W) | ( ~1M) 1048576 | 2048 x 512 x 1 x 1 | F16 |
- Total elements in blk.1: (~623M) 623120640
- Percentage of total elements: 2.04%
### Block 2 Tensor Group : ~623M Elements
| T_ID | Tensor Layer Name | Human Friendly Tensor Layer Name | Elements | Shape | Type |
|-----:|:---------------------------|:------------------------------------------------------------------------------------------|:------------------|:----------------------|:-----|
| 25 | blk.2.ffn_gate_inp.weight | Block 2 Expert-Routing Layer For The Feed-Forward Network In Mixture Of Expert Models (W) | (~262K) 262144 | 2048 x 128 x 1 x 1 | F32 |
| 26 | blk.2.attn_k_norm.weight | Block 2 Attn_K_Norm (W) | ( 128) 128 | 128 x 1 x 1 x 1 | F32 |
| 27 | blk.2.attn_k.weight | Block 2 Attention Key (W) | ( ~1M) 1048576 | 2048 x 512 x 1 x 1 | F16 |
| 28 | blk.2.attn_output.weight | Block 2 Attention Output (W) | ( ~8M) 8388608 | 4096 x 2048 x 1 x 1 | F16 |
| 29 | blk.2.attn_q_norm.weight | Block 2 Attn_Q_Norm (W) | ( 128) 128 | 128 x 1 x 1 x 1 | F32 |
| 30 | blk.2.attn_q.weight | Block 2 Attention Query (W) | ( ~8M) 8388608 | 2048 x 4096 x 1 x 1 | F16 |
| 31 | blk.2.attn_v.weight | Block 2 Attention Value (W) | ( ~1M) 1048576 | 2048 x 512 x 1 x 1 | F16 |
| 32 | blk.2.attn_norm.weight | Block 2 Attention Normalization (W) | ( ~2K) 2048 | 2048 x 1 x 1 x 1 | F32 |
| 33 | blk.2.ffn_down_exps.weight | Block 2 Ffn_Down_Exps (W) | (~201M) 201326592 | 768 x 2048 x 128 x 1 | F16 |
| 34 | blk.2.ffn_gate_exps.weight | Block 2 Ffn_Gate_Exps (W) | (~201M) 201326592 | 2048 x 768 x 128 x 1 | F16 |
| 35 | blk.2.ffn_up_exps.weight | Block 2 Ffn_Up_Exps (W) | (~201M) 201326592 | 2048 x 768 x 128 x 1 | F16 |
| 36 | blk.2.ffn_norm.weight | Block 2 Feed-Forward Network Normalization (W) | ( ~2K) 2048 | 2048 x 1 x 1 x 1 | F32 |
- Total elements in blk.2: (~623M) 623120640
- Percentage of total elements: 2.04%
### Block 3 Tensor Group : ~623M Elements
| T_ID | Tensor Layer Name | Human Friendly Tensor Layer Name | Elements | Shape | Type |
|-----:|:---------------------------|:------------------------------------------------------------------------------------------|:------------------|:----------------------|:-----|
| 37 | blk.3.attn_norm.weight | Block 3 Attention Normalization (W) | ( ~2K) 2048 | 2048 x 1 x 1 x 1 | F32 |
| 38 | blk.3.ffn_down_exps.weight | Block 3 Ffn_Down_Exps (W) | (~201M) 201326592 | 768 x 2048 x 128 x 1 | F16 |
| 39 | blk.3.ffn_gate_exps.weight | Block 3 Ffn_Gate_Exps (W) | (~201M) 201326592 | 2048 x 768 x 128 x 1 | F16 |
| 40 | blk.3.ffn_up_exps.weight | Block 3 Ffn_Up_Exps (W) | (~201M) 201326592 | 2048 x 768 x 128 x 1 | F16 |
| 41 | blk.3.ffn_gate_inp.weight | Block 3 Expert-Routing Layer For The Feed-Forward Network In Mixture Of Expert Models (W) | (~262K) 262144 | 2048 x 128 x 1 x 1 | F32 |
| 42 | blk.3.ffn_norm.weight | Block 3 Feed-Forward Network Normalization (W) | ( ~2K) 2048 | 2048 x 1 x 1 x 1 | F32 |
| 43 | blk.3.attn_k_norm.weight | Block 3 Attn_K_Norm (W) | ( 128) 128 | 128 x 1 x 1 x 1 | F32 |
| 44 | blk.3.attn_k.weight | Block 3 Attention Key (W) | ( ~1M) 1048576 | 2048 x 512 x 1 x 1 | F16 |
| 45 | blk.3.attn_output.weight | Block 3 Attention Output (W) | ( ~8M) 8388608 | 4096 x 2048 x 1 x 1 | F16 |
| 46 | blk.3.attn_q_norm.weight | Block 3 Attn_Q_Norm (W) | ( 128) 128 | 128 x 1 x 1 x 1 | F32 |
| 47 | blk.3.attn_q.weight | Block 3 Attention Query (W) | ( ~8M) 8388608 | 2048 x 4096 x 1 x 1 | F16 |
| 48 | blk.3.attn_v.weight | Block 3 Attention Value (W) | ( ~1M) 1048576 | 2048 x 512 x 1 x 1 | F16 |
- Total elements in blk.3: (~623M) 623120640
- Percentage of total elements: 2.04%
### Block 4 Tensor Group : ~623M Elements
| T_ID | Tensor Layer Name | Human Friendly Tensor Layer Name | Elements | Shape | Type |
|-----:|:---------------------------|:------------------------------------------------------------------------------------------|:------------------|:----------------------|:-----|
| 49 | blk.4.attn_norm.weight | Block 4 Attention Normalization (W) | ( ~2K) 2048 | 2048 x 1 x 1 x 1 | F32 |
| 50 | blk.4.ffn_down_exps.weight | Block 4 Ffn_Down_Exps (W) | (~201M) 201326592 | 768 x 2048 x 128 x 1 | F16 |
| 51 | blk.4.ffn_gate_exps.weight | Block 4 Ffn_Gate_Exps (W) | (~201M) 201326592 | 2048 x 768 x 128 x 1 | F16 |
| 52 | blk.4.ffn_up_exps.weight | Block 4 Ffn_Up_Exps (W) | (~201M) 201326592 | 2048 x 768 x 128 x 1 | F16 |
| 53 | blk.4.ffn_gate_inp.weight | Block 4 Expert-Routing Layer For The Feed-Forward Network In Mixture Of Expert Models (W) | (~262K) 262144 | 2048 x 128 x 1 x 1 | F32 |
| 54 | blk.4.ffn_norm.weight | Block 4 Feed-Forward Network Normalization (W) | ( ~2K) 2048 | 2048 x 1 x 1 x 1 | F32 |
| 55 | blk.4.attn_k_norm.weight | Block 4 Attn_K_Norm (W) | ( 128) 128 | 128 x 1 x 1 x 1 | F32 |
| 56 | blk.4.attn_k.weight | Block 4 Attention Key (W) | ( ~1M) 1048576 | 2048 x 512 x 1 x 1 | F16 |
| 57 | blk.4.attn_output.weight | Block 4 Attention Output (W) | ( ~8M) 8388608 | 4096 x 2048 x 1 x 1 | F16 |
| 58 | blk.4.attn_q_norm.weight | Block 4 Attn_Q_Norm (W) | ( 128) 128 | 128 x 1 x 1 x 1 | F32 |
| 59 | blk.4.attn_q.weight | Block 4 Attention Query (W) | ( ~8M) 8388608 | 2048 x 4096 x 1 x 1 | F16 |
| 60 | blk.4.attn_v.weight | Block 4 Attention Value (W) | ( ~1M) 1048576 | 2048 x 512 x 1 x 1 | F16 |
- Total elements in blk.4: (~623M) 623120640
- Percentage of total elements: 2.04%
### Block 5 Tensor Group : ~623M Elements
| T_ID | Tensor Layer Name | Human Friendly Tensor Layer Name | Elements | Shape | Type |
|-----:|:---------------------------|:------------------------------------------------------------------------------------------|:------------------|:----------------------|:-----|
| 61 | blk.5.ffn_gate_inp.weight | Block 5 Expert-Routing Layer For The Feed-Forward Network In Mixture Of Expert Models (W) | (~262K) 262144 | 2048 x 128 x 1 x 1 | F32 |
| 62 | blk.5.attn_k_norm.weight | Block 5 Attn_K_Norm (W) | ( 128) 128 | 128 x 1 x 1 x 1 | F32 |
| 63 | blk.5.attn_k.weight | Block 5 Attention Key (W) | ( ~1M) 1048576 | 2048 x 512 x 1 x 1 | F16 |
| 64 | blk.5.attn_output.weight | Block 5 Attention Output (W) | ( ~8M) 8388608 | 4096 x 2048 x 1 x 1 | F16 |
| 65 | blk.5.attn_q_norm.weight | Block 5 Attn_Q_Norm (W) | ( 128) 128 | 128 x 1 x 1 x 1 | F32 |
| 66 | blk.5.attn_q.weight | Block 5 Attention Query (W) | ( ~8M) 8388608 | 2048 x 4096 x 1 x 1 | F16 |
| 67 | blk.5.attn_v.weight | Block 5 Attention Value (W) | ( ~1M) 1048576 | 2048 x 512 x 1 x 1 | F16 |
| 68 | blk.5.attn_norm.weight | Block 5 Attention Normalization (W) | ( ~2K) 2048 | 2048 x 1 x 1 x 1 | F32 |
| 69 | blk.5.ffn_down_exps.weight | Block 5 Ffn_Down_Exps (W) | (~201M) 201326592 | 768 x 2048 x 128 x 1 | F16 |
| 70 | blk.5.ffn_gate_exps.weight | Block 5 Ffn_Gate_Exps (W) | (~201M) 201326592 | 2048 x 768 x 128 x 1 | F16 |
| 71 | blk.5.ffn_up_exps.weight | Block 5 Ffn_Up_Exps (W) | (~201M) 201326592 | 2048 x 768 x 128 x 1 | F16 |
| 72 | blk.5.ffn_norm.weight | Block 5 Feed-Forward Network Normalization (W) | ( ~2K) 2048 | 2048 x 1 x 1 x 1 | F32 |
- Total elements in blk.5: (~623M) 623120640
- Percentage of total elements: 2.04%
### Block 6 Tensor Group : ~623M Elements
| T_ID | Tensor Layer Name | Human Friendly Tensor Layer Name | Elements | Shape | Type |
|-----:|:---------------------------|:------------------------------------------------------------------------------------------|:------------------|:----------------------|:-----|
| 73 | blk.6.attn_norm.weight | Block 6 Attention Normalization (W) | ( ~2K) 2048 | 2048 x 1 x 1 x 1 | F32 |
| 74 | blk.6.ffn_down_exps.weight | Block 6 Ffn_Down_Exps (W) | (~201M) 201326592 | 768 x 2048 x 128 x 1 | F16 |
| 75 | blk.6.ffn_gate_exps.weight | Block 6 Ffn_Gate_Exps (W) | (~201M) 201326592 | 2048 x 768 x 128 x 1 | F16 |
| 76 | blk.6.ffn_up_exps.weight | Block 6 Ffn_Up_Exps (W) | (~201M) 201326592 | 2048 x 768 x 128 x 1 | F16 |
| 77 | blk.6.ffn_gate_inp.weight | Block 6 Expert-Routing Layer For The Feed-Forward Network In Mixture Of Expert Models (W) | (~262K) 262144 | 2048 x 128 x 1 x 1 | F32 |
| 78 | blk.6.ffn_norm.weight | Block 6 Feed-Forward Network Normalization (W) | ( ~2K) 2048 | 2048 x 1 x 1 x 1 | F32 |
| 79 | blk.6.attn_k_norm.weight | Block 6 Attn_K_Norm (W) | ( 128) 128 | 128 x 1 x 1 x 1 | F32 |
| 80 | blk.6.attn_k.weight | Block 6 Attention Key (W) | ( ~1M) 1048576 | 2048 x 512 x 1 x 1 | F16 |
| 81 | blk.6.attn_output.weight | Block 6 Attention Output (W) | ( ~8M) 8388608 | 4096 x 2048 x 1 x 1 | F16 |
| 82 | blk.6.attn_q_norm.weight | Block 6 Attn_Q_Norm (W) | ( 128) 128 | 128 x 1 x 1 x 1 | F32 |
| 83 | blk.6.attn_q.weight | Block 6 Attention Query (W) | ( ~8M) 8388608 | 2048 x 4096 x 1 x 1 | F16 |
| 84 | blk.6.attn_v.weight | Block 6 Attention Value (W) | ( ~1M) 1048576 | 2048 x 512 x 1 x 1 | F16 |
- Total elements in blk.6: (~623M) 623120640
- Percentage of total elements: 2.04%
### Block 7 Tensor Group : ~623M Elements
| T_ID | Tensor Layer Name | Human Friendly Tensor Layer Name | Elements | Shape | Type |
|-----:|:---------------------------|:------------------------------------------------------------------------------------------|:------------------|:----------------------|:-----|
| 85 | blk.7.attn_norm.weight | Block 7 Attention Normalization (W) | ( ~2K) 2048 | 2048 x 1 x 1 x 1 | F32 |
| 86 | blk.7.ffn_down_exps.weight | Block 7 Ffn_Down_Exps (W) | (~201M) 201326592 | 768 x 2048 x 128 x 1 | F16 |
| 87 | blk.7.ffn_gate_exps.weight | Block 7 Ffn_Gate_Exps (W) | (~201M) 201326592 | 2048 x 768 x 128 x 1 | F16 |
| 88 | blk.7.ffn_up_exps.weight | Block 7 Ffn_Up_Exps (W) | (~201M) 201326592 | 2048 x 768 x 128 x 1 | F16 |
| 89 | blk.7.ffn_gate_inp.weight | Block 7 Expert-Routing Layer For The Feed-Forward Network In Mixture Of Expert Models (W) | (~262K) 262144 | 2048 x 128 x 1 x 1 | F32 |
| 90 | blk.7.ffn_norm.weight | Block 7 Feed-Forward Network Normalization (W) | ( ~2K) 2048 | 2048 x 1 x 1 x 1 | F32 |
| 91 | blk.7.attn_k_norm.weight | Block 7 Attn_K_Norm (W) | ( 128) 128 | 128 x 1 x 1 x 1 | F32 |
| 92 | blk.7.attn_k.weight | Block 7 Attention Key (W) | ( ~1M) 1048576 | 2048 x 512 x 1 x 1 | F16 |
| 93 | blk.7.attn_output.weight | Block 7 Attention Output (W) | ( ~8M) 8388608 | 4096 x 2048 x 1 x 1 | F16 |
| 94 | blk.7.attn_q_norm.weight | Block 7 Attn_Q_Norm (W) | ( 128) 128 | 128 x 1 x 1 x 1 | F32 |
| 95 | blk.7.attn_q.weight | Block 7 Attention Query (W) | ( ~8M) 8388608 | 2048 x 4096 x 1 x 1 | F16 |
| 96 | blk.7.attn_v.weight | Block 7 Attention Value (W) | ( ~1M) 1048576 | 2048 x 512 x 1 x 1 | F16 |
- Total elements in blk.7: (~623M) 623120640
- Percentage of total elements: 2.04%
### Block 8 Tensor Group : ~623M Elements
| T_ID | Tensor Layer Name | Human Friendly Tensor Layer Name | Elements | Shape | Type |
|-----:|:---------------------------|:------------------------------------------------------------------------------------------|:------------------|:----------------------|:-----|
| 97 | blk.8.attn_norm.weight | Block 8 Attention Normalization (W) | ( ~2K) 2048 | 2048 x 1 x 1 x 1 | F32 |
| 98 | blk.8.ffn_down_exps.weight | Block 8 Ffn_Down_Exps (W) | (~201M) 201326592 | 768 x 2048 x 128 x 1 | F16 |
| 99 | blk.8.ffn_gate_exps.weight | Block 8 Ffn_Gate_Exps (W) | (~201M) 201326592 | 2048 x 768 x 128 x 1 | F16 |
| 100 | blk.8.ffn_up_exps.weight | Block 8 Ffn_Up_Exps (W) | (~201M) 201326592 | 2048 x 768 x 128 x 1 | F16 |
| 101 | blk.8.ffn_gate_inp.weight | Block 8 Expert-Routing Layer For The Feed-Forward Network In Mixture Of Expert Models (W) | (~262K) 262144 | 2048 x 128 x 1 x 1 | F32 |
| 102 | blk.8.ffn_norm.weight | Block 8 Feed-Forward Network Normalization (W) | ( ~2K) 2048 | 2048 x 1 x 1 x 1 | F32 |
| 103 | blk.8.attn_k_norm.weight | Block 8 Attn_K_Norm (W) | ( 128) 128 | 128 x 1 x 1 x 1 | F32 |
| 104 | blk.8.attn_k.weight | Block 8 Attention Key (W) | ( ~1M) 1048576 | 2048 x 512 x 1 x 1 | F16 |
| 105 | blk.8.attn_output.weight | Block 8 Attention Output (W) | ( ~8M) 8388608 | 4096 x 2048 x 1 x 1 | F16 |
| 106 | blk.8.attn_q_norm.weight | Block 8 Attn_Q_Norm (W) | ( 128) 128 | 128 x 1 x 1 x 1 | F32 |
| 107 | blk.8.attn_q.weight | Block 8 Attention Query (W) | ( ~8M) 8388608 | 2048 x 4096 x 1 x 1 | F16 |
| 108 | blk.8.attn_v.weight | Block 8 Attention Value (W) | ( ~1M) 1048576 | 2048 x 512 x 1 x 1 | F16 |
- Total elements in blk.8: (~623M) 623120640
- Percentage of total elements: 2.04%
### Block 9 Tensor Group : ~623M Elements
| T_ID | Tensor Layer Name | Human Friendly Tensor Layer Name | Elements | Shape | Type |
|-----:|:---------------------------|:------------------------------------------------------------------------------------------|:------------------|:----------------------|:-----|
| 109 | blk.9.ffn_gate_inp.weight | Block 9 Expert-Routing Layer For The Feed-Forward Network In Mixture Of Expert Models (W) | (~262K) 262144 | 2048 x 128 x 1 x 1 | F32 |
| 110 | blk.9.attn_k_norm.weight | Block 9 Attn_K_Norm (W) | ( 128) 128 | 128 x 1 x 1 x 1 | F32 |
| 111 | blk.9.attn_k.weight | Block 9 Attention Key (W) | ( ~1M) 1048576 | 2048 x 512 x 1 x 1 | F16 |
| 112 | blk.9.attn_output.weight | Block 9 Attention Output (W) | ( ~8M) 8388608 | 4096 x 2048 x 1 x 1 | F16 |
| 113 | blk.9.attn_q_norm.weight | Block 9 Attn_Q_Norm (W) | ( 128) 128 | 128 x 1 x 1 x 1 | F32 |
| 114 | blk.9.attn_q.weight | Block 9 Attention Query (W) | ( ~8M) 8388608 | 2048 x 4096 x 1 x 1 | F16 |
| 115 | blk.9.attn_v.weight | Block 9 Attention Value (W) | ( ~1M) 1048576 | 2048 x 512 x 1 x 1 | F16 |
| 147 | blk.9.attn_norm.weight | Block 9 Attention Normalization (W) | ( ~2K) 2048 | 2048 x 1 x 1 x 1 | F32 |
| 148 | blk.9.ffn_down_exps.weight | Block 9 Ffn_Down_Exps (W) | (~201M) 201326592 | 768 x 2048 x 128 x 1 | F16 |
| 149 | blk.9.ffn_gate_exps.weight | Block 9 Ffn_Gate_Exps (W) | (~201M) 201326592 | 2048 x 768 x 128 x 1 | F16 |
| 150 | blk.9.ffn_up_exps.weight | Block 9 Ffn_Up_Exps (W) | (~201M) 201326592 | 2048 x 768 x 128 x 1 | F16 |
| 151 | blk.9.ffn_norm.weight | Block 9 Feed-Forward Network Normalization (W) | ( ~2K) 2048 | 2048 x 1 x 1 x 1 | F32 |
- Total elements in blk.9: (~623M) 623120640
- Percentage of total elements: 2.04%
### Block 10 Tensor Group : ~623M Elements
| T_ID | Tensor Layer Name | Human Friendly Tensor Layer Name | Elements | Shape | Type |
|-----:|:----------------------------|:-------------------------------------------------------------------------------------------|:------------------|:----------------------|:-----|
| 116 | blk.10.attn_norm.weight | Block 10 Attention Normalization (W) | ( ~2K) 2048 | 2048 x 1 x 1 x 1 | F32 |
| 117 | blk.10.ffn_down_exps.weight | Block 10 Ffn_Down_Exps (W) | (~201M) 201326592 | 768 x 2048 x 128 x 1 | F16 |
| 118 | blk.10.ffn_gate_exps.weight | Block 10 Ffn_Gate_Exps (W) | (~201M) 201326592 | 2048 x 768 x 128 x 1 | F16 |
| 119 | blk.10.ffn_up_exps.weight | Block 10 Ffn_Up_Exps (W) | (~201M) 201326592 | 2048 x 768 x 128 x 1 | F16 |
| 120 | blk.10.ffn_gate_inp.weight | Block 10 Expert-Routing Layer For The Feed-Forward Network In Mixture Of Expert Models (W) | (~262K) 262144 | 2048 x 128 x 1 x 1 | F32 |
| 121 | blk.10.ffn_norm.weight | Block 10 Feed-Forward Network Normalization (W) | ( ~2K) 2048 | 2048 x 1 x 1 x 1 | F32 |
| 122 | blk.10.attn_k_norm.weight | Block 10 Attn_K_Norm (W) | ( 128) 128 | 128 x 1 x 1 x 1 | F32 |
| 123 | blk.10.attn_k.weight | Block 10 Attention Key (W) | ( ~1M) 1048576 | 2048 x 512 x 1 x 1 | F16 |
| 124 | blk.10.attn_output.weight | Block 10 Attention Output (W) | ( ~8M) 8388608 | 4096 x 2048 x 1 x 1 | F16 |
| 125 | blk.10.attn_q_norm.weight | Block 10 Attn_Q_Norm (W) | ( 128) 128 | 128 x 1 x 1 x 1 | F32 |
| 126 | blk.10.attn_q.weight | Block 10 Attention Query (W) | ( ~8M) 8388608 | 2048 x 4096 x 1 x 1 | F16 |
| 127 | blk.10.attn_v.weight | Block 10 Attention Value (W) | ( ~1M) 1048576 | 2048 x 512 x 1 x 1 | F16 |
- Total elements in blk.10: (~623M) 623120640
- Percentage of total elements: 2.04%
### Block 11 Tensor Group : ~623M Elements
| T_ID | Tensor Layer Name | Human Friendly Tensor Layer Name | Elements | Shape | Type |
|-----:|:----------------------------|:-------------------------------------------------------------------------------------------|:------------------|:----------------------|:-----|
| 128 | blk.11.attn_norm.weight | Block 11 Attention Normalization (W) | ( ~2K) 2048 | 2048 x 1 x 1 x 1 | F32 |
| 129 | blk.11.ffn_down_exps.weight | Block 11 Ffn_Down_Exps (W) | (~201M) 201326592 | 768 x 2048 x 128 x 1 | F16 |
| 130 | blk.11.ffn_gate_exps.weight | Block 11 Ffn_Gate_Exps (W) | (~201M) 201326592 | 2048 x 768 x 128 x 1 | F16 |
| 131 | blk.11.ffn_up_exps.weight | Block 11 Ffn_Up_Exps (W) | (~201M) 201326592 | 2048 x 768 x 128 x 1 | F16 |
| 132 | blk.11.ffn_gate_inp.weight | Block 11 Expert-Routing Layer For The Feed-Forward Network In Mixture Of Expert Models (W) | (~262K) 262144 | 2048 x 128 x 1 x 1 | F32 |
| 133 | blk.11.ffn_norm.weight | Block 11 Feed-Forward Network Normalization (W) | ( ~2K) 2048 | 2048 x 1 x 1 x 1 | F32 |
| 134 | blk.11.attn_k_norm.weight | Block 11 Attn_K_Norm (W) | ( 128) 128 | 128 x 1 x 1 x 1 | F32 |
| 135 | blk.11.attn_k.weight | Block 11 Attention Key (W) | ( ~1M) 1048576 | 2048 x 512 x 1 x 1 | F16 |
| 136 | blk.11.attn_output.weight | Block 11 Attention Output (W) | ( ~8M) 8388608 | 4096 x 2048 x 1 x 1 | F16 |
| 137 | blk.11.attn_q_norm.weight | Block 11 Attn_Q_Norm (W) | ( 128) 128 | 128 x 1 x 1 x 1 | F32 |
| 138 | blk.11.attn_q.weight | Block 11 Attention Query (W) | ( ~8M) 8388608 | 2048 x 4096 x 1 x 1 | F16 |
| 139 | blk.11.attn_v.weight | Block 11 Attention Value (W) | ( ~1M) 1048576 | 2048 x 512 x 1 x 1 | F16 |
- Total elements in blk.11: (~623M) 623120640
- Percentage of total elements: 2.04%
### Block 12 Tensor Group : ~623M Elements
| T_ID | Tensor Layer Name | Human Friendly Tensor Layer Name | Elements | Shape | Type |
|-----:|:----------------------------|:-------------------------------------------------------------------------------------------|:------------------|:----------------------|:-----|
| 140 | blk.12.ffn_gate_inp.weight | Block 12 Expert-Routing Layer For The Feed-Forward Network In Mixture Of Expert Models (W) | (~262K) 262144 | 2048 x 128 x 1 x 1 | F32 |
| 141 | blk.12.attn_k_norm.weight | Block 12 Attn_K_Norm (W) | ( 128) 128 | 128 x 1 x 1 x 1 | F32 |
| 142 | blk.12.attn_k.weight | Block 12 Attention Key (W) | ( ~1M) 1048576 | 2048 x 512 x 1 x 1 | F16 |
| 143 | blk.12.attn_output.weight | Block 12 Attention Output (W) | ( ~8M) 8388608 | 4096 x 2048 x 1 x 1 | F16 |
| 144 | blk.12.attn_q_norm.weight | Block 12 Attn_Q_Norm (W) | ( 128) 128 | 128 x 1 x 1 x 1 | F32 |
| 145 | blk.12.attn_q.weight | Block 12 Attention Query (W) | ( ~8M) 8388608 | 2048 x 4096 x 1 x 1 | F16 |
| 146 | blk.12.attn_v.weight | Block 12 Attention Value (W) | ( ~1M) 1048576 | 2048 x 512 x 1 x 1 | F16 |
| 152 | blk.12.attn_norm.weight | Block 12 Attention Normalization (W) | ( ~2K) 2048 | 2048 x 1 x 1 x 1 | F32 |
| 153 | blk.12.ffn_down_exps.weight | Block 12 Ffn_Down_Exps (W) | (~201M) 201326592 | 768 x 2048 x 128 x 1 | F16 |
| 154 | blk.12.ffn_gate_exps.weight | Block 12 Ffn_Gate_Exps (W) | (~201M) 201326592 | 2048 x 768 x 128 x 1 | F16 |
| 155 | blk.12.ffn_up_exps.weight | Block 12 Ffn_Up_Exps (W) | (~201M) 201326592 | 2048 x 768 x 128 x 1 | F16 |
| 156 | blk.12.ffn_norm.weight | Block 12 Feed-Forward Network Normalization (W) | ( ~2K) 2048 | 2048 x 1 x 1 x 1 | F32 |
- Total elements in blk.12: (~623M) 623120640
- Percentage of total elements: 2.04%
### Block 13 Tensor Group : ~623M Elements
| T_ID | Tensor Layer Name | Human Friendly Tensor Layer Name | Elements | Shape | Type |
|-----:|:----------------------------|:-------------------------------------------------------------------------------------------|:------------------|:----------------------|:-----|
| 157 | blk.13.attn_norm.weight | Block 13 Attention Normalization (W) | ( ~2K) 2048 | 2048 x 1 x 1 x 1 | F32 |
| 158 | blk.13.ffn_down_exps.weight | Block 13 Ffn_Down_Exps (W) | (~201M) 201326592 | 768 x 2048 x 128 x 1 | F16 |
| 159 | blk.13.ffn_gate_exps.weight | Block 13 Ffn_Gate_Exps (W) | (~201M) 201326592 | 2048 x 768 x 128 x 1 | F16 |
| 160 | blk.13.ffn_up_exps.weight | Block 13 Ffn_Up_Exps (W) | (~201M) 201326592 | 2048 x 768 x 128 x 1 | F16 |
| 161 | blk.13.ffn_gate_inp.weight | Block 13 Expert-Routing Layer For The Feed-Forward Network In Mixture Of Expert Models (W) | (~262K) 262144 | 2048 x 128 x 1 x 1 | F32 |
| 162 | blk.13.ffn_norm.weight | Block 13 Feed-Forward Network Normalization (W) | ( ~2K) 2048 | 2048 x 1 x 1 x 1 | F32 |
| 163 | blk.13.attn_k_norm.weight | Block 13 Attn_K_Norm (W) | ( 128) 128 | 128 x 1 x 1 x 1 | F32 |
| 164 | blk.13.attn_k.weight | Block 13 Attention Key (W) | ( ~1M) 1048576 | 2048 x 512 x 1 x 1 | F16 |
| 165 | blk.13.attn_output.weight | Block 13 Attention Output (W) | ( ~8M) 8388608 | 4096 x 2048 x 1 x 1 | F16 |
| 166 | blk.13.attn_q_norm.weight | Block 13 Attn_Q_Norm (W) | ( 128) 128 | 128 x 1 x 1 x 1 | F32 |
| 167 | blk.13.attn_q.weight | Block 13 Attention Query (W) | ( ~8M) 8388608 | 2048 x 4096 x 1 x 1 | F16 |
| 168 | blk.13.attn_v.weight | Block 13 Attention Value (W) | ( ~1M) 1048576 | 2048 x 512 x 1 x 1 | F16 |
- Total elements in blk.13: (~623M) 623120640
- Percentage of total elements: 2.04%
### Block 14 Tensor Group : ~623M Elements
| T_ID | Tensor Layer Name | Human Friendly Tensor Layer Name | Elements | Shape | Type |
|-----:|:----------------------------|:-------------------------------------------------------------------------------------------|:------------------|:----------------------|:-----|
| 169 | blk.14.attn_norm.weight | Block 14 Attention Normalization (W) | ( ~2K) 2048 | 2048 x 1 x 1 x 1 | F32 |
| 170 | blk.14.ffn_down_exps.weight | Block 14 Ffn_Down_Exps (W) | (~201M) 201326592 | 768 x 2048 x 128 x 1 | F16 |
| 171 | blk.14.ffn_gate_exps.weight | Block 14 Ffn_Gate_Exps (W) | (~201M) 201326592 | 2048 x 768 x 128 x 1 | F16 |
| 172 | blk.14.ffn_up_exps.weight | Block 14 Ffn_Up_Exps (W) | (~201M) 201326592 | 2048 x 768 x 128 x 1 | F16 |
| 173 | blk.14.ffn_gate_inp.weight | Block 14 Expert-Routing Layer For The Feed-Forward Network In Mixture Of Expert Models (W) | (~262K) 262144 | 2048 x 128 x 1 x 1 | F32 |
| 174 | blk.14.ffn_norm.weight | Block 14 Feed-Forward Network Normalization (W) | ( ~2K) 2048 | 2048 x 1 x 1 x 1 | F32 |
| 175 | blk.14.attn_k_norm.weight | Block 14 Attn_K_Norm (W) | ( 128) 128 | 128 x 1 x 1 x 1 | F32 |
| 176 | blk.14.attn_k.weight | Block 14 Attention Key (W) | ( ~1M) 1048576 | 2048 x 512 x 1 x 1 | F16 |
| 177 | blk.14.attn_output.weight | Block 14 Attention Output (W) | ( ~8M) 8388608 | 4096 x 2048 x 1 x 1 | F16 |
| 178 | blk.14.attn_q_norm.weight | Block 14 Attn_Q_Norm (W) | ( 128) 128 | 128 x 1 x 1 x 1 | F32 |
| 179 | blk.14.attn_q.weight | Block 14 Attention Query (W) | ( ~8M) 8388608 | 2048 x 4096 x 1 x 1 | F16 |
| 180 | blk.14.attn_v.weight | Block 14 Attention Value (W) | ( ~1M) 1048576 | 2048 x 512 x 1 x 1 | F16 |
- Total elements in blk.14: (~623M) 623120640
- Percentage of total elements: 2.04%
### Block 15 Tensor Group : ~623M Elements
| T_ID | Tensor Layer Name | Human Friendly Tensor Layer Name | Elements | Shape | Type |
|-----:|:----------------------------|:-------------------------------------------------------------------------------------------|:------------------|:----------------------|:-----|
| 181 | blk.15.ffn_gate_inp.weight | Block 15 Expert-Routing Layer For The Feed-Forward Network In Mixture Of Expert Models (W) | (~262K) 262144 | 2048 x 128 x 1 x 1 | F32 |
| 182 | blk.15.attn_k_norm.weight | Block 15 Attn_K_Norm (W) | ( 128) 128 | 128 x 1 x 1 x 1 | F32 |
| 183 | blk.15.attn_k.weight | Block 15 Attention Key (W) | ( ~1M) 1048576 | 2048 x 512 x 1 x 1 | F16 |
| 184 | blk.15.attn_output.weight | Block 15 Attention Output (W) | ( ~8M) 8388608 | 4096 x 2048 x 1 x 1 | F16 |
| 185 | blk.15.attn_q_norm.weight | Block 15 Attn_Q_Norm (W) | ( 128) 128 | 128 x 1 x 1 x 1 | F32 |
| 186 | blk.15.attn_q.weight | Block 15 Attention Query (W) | ( ~8M) 8388608 | 2048 x 4096 x 1 x 1 | F16 |
| 187 | blk.15.attn_v.weight | Block 15 Attention Value (W) | ( ~1M) 1048576 | 2048 x 512 x 1 x 1 | F16 |
| 188 | blk.15.attn_norm.weight | Block 15 Attention Normalization (W) | ( ~2K) 2048 | 2048 x 1 x 1 x 1 | F32 |
| 189 | blk.15.ffn_down_exps.weight | Block 15 Ffn_Down_Exps (W) | (~201M) 201326592 | 768 x 2048 x 128 x 1 | F16 |
| 190 | blk.15.ffn_gate_exps.weight | Block 15 Ffn_Gate_Exps (W) | (~201M) 201326592 | 2048 x 768 x 128 x 1 | F16 |
| 191 | blk.15.ffn_up_exps.weight | Block 15 Ffn_Up_Exps (W) | (~201M) 201326592 | 2048 x 768 x 128 x 1 | F16 |
| 192 | blk.15.ffn_norm.weight | Block 15 Feed-Forward Network Normalization (W) | ( ~2K) 2048 | 2048 x 1 x 1 x 1 | F32 |
- Total elements in blk.15: (~623M) 623120640
- Percentage of total elements: 2.04%
### Block 16 Tensor Group : ~623M Elements
| T_ID | Tensor Layer Name | Human Friendly Tensor Layer Name | Elements | Shape | Type |
|-----:|:----------------------------|:-------------------------------------------------------------------------------------------|:------------------|:----------------------|:-----|
| 193 | blk.16.attn_norm.weight | Block 16 Attention Normalization (W) | ( ~2K) 2048 | 2048 x 1 x 1 x 1 | F32 |
| 194 | blk.16.ffn_down_exps.weight | Block 16 Ffn_Down_Exps (W) | (~201M) 201326592 | 768 x 2048 x 128 x 1 | F16 |
| 195 | blk.16.ffn_gate_exps.weight | Block 16 Ffn_Gate_Exps (W) | (~201M) 201326592 | 2048 x 768 x 128 x 1 | F16 |
| 196 | blk.16.ffn_up_exps.weight | Block 16 Ffn_Up_Exps (W) | (~201M) 201326592 | 2048 x 768 x 128 x 1 | F16 |
| 197 | blk.16.ffn_gate_inp.weight | Block 16 Expert-Routing Layer For The Feed-Forward Network In Mixture Of Expert Models (W) | (~262K) 262144 | 2048 x 128 x 1 x 1 | F32 |
| 198 | blk.16.ffn_norm.weight | Block 16 Feed-Forward Network Normalization (W) | ( ~2K) 2048 | 2048 x 1 x 1 x 1 | F32 |
| 199 | blk.16.attn_k_norm.weight | Block 16 Attn_K_Norm (W) | ( 128) 128 | 128 x 1 x 1 x 1 | F32 |
| 200 | blk.16.attn_k.weight | Block 16 Attention Key (W) | ( ~1M) 1048576 | 2048 x 512 x 1 x 1 | F16 |
| 201 | blk.16.attn_output.weight | Block 16 Attention Output (W) | ( ~8M) 8388608 | 4096 x 2048 x 1 x 1 | F16 |
| 202 | blk.16.attn_q_norm.weight | Block 16 Attn_Q_Norm (W) | ( 128) 128 | 128 x 1 x 1 x 1 | F32 |
| 203 | blk.16.attn_q.weight | Block 16 Attention Query (W) | ( ~8M) 8388608 | 2048 x 4096 x 1 x 1 | F16 |
| 204 | blk.16.attn_v.weight | Block 16 Attention Value (W) | ( ~1M) 1048576 | 2048 x 512 x 1 x 1 | F16 |
- Total elements in blk.16: (~623M) 623120640
- Percentage of total elements: 2.04%
### Block 17 Tensor Group : ~623M Elements
| T_ID | Tensor Layer Name | Human Friendly Tensor Layer Name | Elements | Shape | Type |
|-----:|:----------------------------|:-------------------------------------------------------------------------------------------|:------------------|:----------------------|:-----|
| 205 | blk.17.attn_norm.weight | Block 17 Attention Normalization (W) | ( ~2K) 2048 | 2048 x 1 x 1 x 1 | F32 |
| 206 | blk.17.ffn_down_exps.weight | Block 17 Ffn_Down_Exps (W) | (~201M) 201326592 | 768 x 2048 x 128 x 1 | F16 |
| 207 | blk.17.ffn_gate_exps.weight | Block 17 Ffn_Gate_Exps (W) | (~201M) 201326592 | 2048 x 768 x 128 x 1 | F16 |
| 208 | blk.17.ffn_up_exps.weight | Block 17 Ffn_Up_Exps (W) | (~201M) 201326592 | 2048 x 768 x 128 x 1 | F16 |
| 209 | blk.17.ffn_gate_inp.weight | Block 17 Expert-Routing Layer For The Feed-Forward Network In Mixture Of Expert Models (W) | (~262K) 262144 | 2048 x 128 x 1 x 1 | F32 |
| 210 | blk.17.ffn_norm.weight | Block 17 Feed-Forward Network Normalization (W) | ( ~2K) 2048 | 2048 x 1 x 1 x 1 | F32 |
| 211 | blk.17.attn_k_norm.weight | Block 17 Attn_K_Norm (W) | ( 128) 128 | 128 x 1 x 1 x 1 | F32 |
| 212 | blk.17.attn_k.weight | Block 17 Attention Key (W) | ( ~1M) 1048576 | 2048 x 512 x 1 x 1 | F16 |
| 213 | blk.17.attn_output.weight | Block 17 Attention Output (W) | ( ~8M) 8388608 | 4096 x 2048 x 1 x 1 | F16 |
| 214 | blk.17.attn_q_norm.weight | Block 17 Attn_Q_Norm (W) | ( 128) 128 | 128 x 1 x 1 x 1 | F32 |
| 215 | blk.17.attn_q.weight | Block 17 Attention Query (W) | ( ~8M) 8388608 | 2048 x 4096 x 1 x 1 | F16 |
| 216 | blk.17.attn_v.weight | Block 17 Attention Value (W) | ( ~1M) 1048576 | 2048 x 512 x 1 x 1 | F16 |
- Total elements in blk.17: (~623M) 623120640
- Percentage of total elements: 2.04%
### Block 18 Tensor Group : ~623M Elements
| T_ID | Tensor Layer Name | Human Friendly Tensor Layer Name | Elements | Shape | Type |
|-----:|:----------------------------|:-------------------------------------------------------------------------------------------|:------------------|:----------------------|:-----|
| 217 | blk.18.ffn_gate_inp.weight | Block 18 Expert-Routing Layer For The Feed-Forward Network In Mixture Of Expert Models (W) | (~262K) 262144 | 2048 x 128 x 1 x 1 | F32 |
| 218 | blk.18.attn_k_norm.weight | Block 18 Attn_K_Norm (W) | ( 128) 128 | 128 x 1 x 1 x 1 | F32 |
| 219 | blk.18.attn_k.weight | Block 18 Attention Key (W) | ( ~1M) 1048576 | 2048 x 512 x 1 x 1 | F16 |
| 220 | blk.18.attn_output.weight | Block 18 Attention Output (W) | ( ~8M) 8388608 | 4096 x 2048 x 1 x 1 | F16 |
| 221 | blk.18.attn_q_norm.weight | Block 18 Attn_Q_Norm (W) | ( 128) 128 | 128 x 1 x 1 x 1 | F32 |
| 222 | blk.18.attn_q.weight | Block 18 Attention Query (W) | ( ~8M) 8388608 | 2048 x 4096 x 1 x 1 | F16 |
| 223 | blk.18.attn_v.weight | Block 18 Attention Value (W) | ( ~1M) 1048576 | 2048 x 512 x 1 x 1 | F16 |
| 224 | blk.18.attn_norm.weight | Block 18 Attention Normalization (W) | ( ~2K) 2048 | 2048 x 1 x 1 x 1 | F32 |
| 225 | blk.18.ffn_down_exps.weight | Block 18 Ffn_Down_Exps (W) | (~201M) 201326592 | 768 x 2048 x 128 x 1 | F16 |
| 226 | blk.18.ffn_gate_exps.weight | Block 18 Ffn_Gate_Exps (W) | (~201M) 201326592 | 2048 x 768 x 128 x 1 | F16 |
| 227 | blk.18.ffn_up_exps.weight | Block 18 Ffn_Up_Exps (W) | (~201M) 201326592 | 2048 x 768 x 128 x 1 | F16 |
| 228 | blk.18.ffn_norm.weight | Block 18 Feed-Forward Network Normalization (W) | ( ~2K) 2048 | 2048 x 1 x 1 x 1 | F32 |
- Total elements in blk.18: (~623M) 623120640
- Percentage of total elements: 2.04%
### Block 19 Tensor Group : ~623M Elements
| T_ID | Tensor Layer Name | Human Friendly Tensor Layer Name | Elements | Shape | Type |
|-----:|:----------------------------|:-------------------------------------------------------------------------------------------|:------------------|:----------------------|:-----|
| 229 | blk.19.attn_norm.weight | Block 19 Attention Normalization (W) | ( ~2K) 2048 | 2048 x 1 x 1 x 1 | F32 |
| 230 | blk.19.ffn_down_exps.weight | Block 19 Ffn_Down_Exps (W) | (~201M) 201326592 | 768 x 2048 x 128 x 1 | F16 |
| 231 | blk.19.ffn_gate_exps.weight | Block 19 Ffn_Gate_Exps (W) | (~201M) 201326592 | 2048 x 768 x 128 x 1 | F16 |
| 232 | blk.19.ffn_up_exps.weight | Block 19 Ffn_Up_Exps (W) | (~201M) 201326592 | 2048 x 768 x 128 x 1 | F16 |
| 233 | blk.19.ffn_gate_inp.weight | Block 19 Expert-Routing Layer For The Feed-Forward Network In Mixture Of Expert Models (W) | (~262K) 262144 | 2048 x 128 x 1 x 1 | F32 |
| 234 | blk.19.ffn_norm.weight | Block 19 Feed-Forward Network Normalization (W) | ( ~2K) 2048 | 2048 x 1 x 1 x 1 | F32 |
| 235 | blk.19.attn_k_norm.weight | Block 19 Attn_K_Norm (W) | ( 128) 128 | 128 x 1 x 1 x 1 | F32 |
| 236 | blk.19.attn_k.weight | Block 19 Attention Key (W) | ( ~1M) 1048576 | 2048 x 512 x 1 x 1 | F16 |
| 237 | blk.19.attn_output.weight | Block 19 Attention Output (W) | ( ~8M) 8388608 | 4096 x 2048 x 1 x 1 | F16 |
| 238 | blk.19.attn_q_norm.weight | Block 19 Attn_Q_Norm (W) | ( 128) 128 | 128 x 1 x 1 x 1 | F32 |
| 239 | blk.19.attn_q.weight | Block 19 Attention Query (W) | ( ~8M) 8388608 | 2048 x 4096 x 1 x 1 | F16 |
| 240 | blk.19.attn_v.weight | Block 19 Attention Value (W) | ( ~1M) 1048576 | 2048 x 512 x 1 x 1 | F16 |
- Total elements in blk.19: (~623M) 623120640
- Percentage of total elements: 2.04%
### Block 20 Tensor Group : ~623M Elements
| T_ID | Tensor Layer Name | Human Friendly Tensor Layer Name | Elements | Shape | Type |
|-----:|:----------------------------|:-------------------------------------------------------------------------------------------|:------------------|:----------------------|:-----|
| 241 | blk.20.attn_norm.weight | Block 20 Attention Normalization (W) | ( ~2K) 2048 | 2048 x 1 x 1 x 1 | F32 |
| 242 | blk.20.ffn_down_exps.weight | Block 20 Ffn_Down_Exps (W) | (~201M) 201326592 | 768 x 2048 x 128 x 1 | F16 |
| 243 | blk.20.ffn_gate_exps.weight | Block 20 Ffn_Gate_Exps (W) | (~201M) 201326592 | 2048 x 768 x 128 x 1 | F16 |
| 244 | blk.20.ffn_up_exps.weight | Block 20 Ffn_Up_Exps (W) | (~201M) 201326592 | 2048 x 768 x 128 x 1 | F16 |
| 245 | blk.20.ffn_gate_inp.weight | Block 20 Expert-Routing Layer For The Feed-Forward Network In Mixture Of Expert Models (W) | (~262K) 262144 | 2048 x 128 x 1 x 1 | F32 |
| 246 | blk.20.ffn_norm.weight | Block 20 Feed-Forward Network Normalization (W) | ( ~2K) 2048 | 2048 x 1 x 1 x 1 | F32 |
| 247 | blk.20.attn_k_norm.weight | Block 20 Attn_K_Norm (W) | ( 128) 128 | 128 x 1 x 1 x 1 | F32 |
| 248 | blk.20.attn_k.weight | Block 20 Attention Key (W) | ( ~1M) 1048576 | 2048 x 512 x 1 x 1 | F16 |
| 249 | blk.20.attn_output.weight | Block 20 Attention Output (W) | ( ~8M) 8388608 | 4096 x 2048 x 1 x 1 | F16 |
| 250 | blk.20.attn_q_norm.weight | Block 20 Attn_Q_Norm (W) | ( 128) 128 | 128 x 1 x 1 x 1 | F32 |
| 251 | blk.20.attn_q.weight | Block 20 Attention Query (W) | ( ~8M) 8388608 | 2048 x 4096 x 1 x 1 | F16 |
| 252 | blk.20.attn_v.weight | Block 20 Attention Value (W) | ( ~1M) 1048576 | 2048 x 512 x 1 x 1 | F16 |
- Total elements in blk.20: (~623M) 623120640
- Percentage of total elements: 2.04%
### Block 21 Tensor Group : ~623M Elements
| T_ID | Tensor Layer Name | Human Friendly Tensor Layer Name | Elements | Shape | Type |
|-----:|:----------------------------|:-------------------------------------------------------------------------------------------|:------------------|:----------------------|:-----|
| 253 | blk.21.ffn_gate_inp.weight | Block 21 Expert-Routing Layer For The Feed-Forward Network In Mixture Of Expert Models (W) | (~262K) 262144 | 2048 x 128 x 1 x 1 | F32 |
| 254 | blk.21.attn_k_norm.weight | Block 21 Attn_K_Norm (W) | ( 128) 128 | 128 x 1 x 1 x 1 | F32 |
| 255 | blk.21.attn_k.weight | Block 21 Attention Key (W) | ( ~1M) 1048576 | 2048 x 512 x 1 x 1 | F16 |
| 256 | blk.21.attn_output.weight | Block 21 Attention Output (W) | ( ~8M) 8388608 | 4096 x 2048 x 1 x 1 | F16 |
| 257 | blk.21.attn_q_norm.weight | Block 21 Attn_Q_Norm (W) | ( 128) 128 | 128 x 1 x 1 x 1 | F32 |
| 258 | blk.21.attn_q.weight | Block 21 Attention Query (W) | ( ~8M) 8388608 | 2048 x 4096 x 1 x 1 | F16 |
| 259 | blk.21.attn_v.weight | Block 21 Attention Value (W) | ( ~1M) 1048576 | 2048 x 512 x 1 x 1 | F16 |
| 260 | blk.21.attn_norm.weight | Block 21 Attention Normalization (W) | ( ~2K) 2048 | 2048 x 1 x 1 x 1 | F32 |
| 261 | blk.21.ffn_down_exps.weight | Block 21 Ffn_Down_Exps (W) | (~201M) 201326592 | 768 x 2048 x 128 x 1 | F16 |
| 262 | blk.21.ffn_gate_exps.weight | Block 21 Ffn_Gate_Exps (W) | (~201M) 201326592 | 2048 x 768 x 128 x 1 | F16 |
| 263 | blk.21.ffn_up_exps.weight | Block 21 Ffn_Up_Exps (W) | (~201M) 201326592 | 2048 x 768 x 128 x 1 | F16 |
| 264 | blk.21.ffn_norm.weight | Block 21 Feed-Forward Network Normalization (W) | ( ~2K) 2048 | 2048 x 1 x 1 x 1 | F32 |
- Total elements in blk.21: (~623M) 623120640
- Percentage of total elements: 2.04%
### Block 22 Tensor Group : ~623M Elements
| T_ID | Tensor Layer Name | Human Friendly Tensor Layer Name | Elements | Shape | Type |
|-----:|:----------------------------|:-------------------------------------------------------------------------------------------|:------------------|:----------------------|:-----|
| 265 | blk.22.attn_norm.weight | Block 22 Attention Normalization (W) | ( ~2K) 2048 | 2048 x 1 x 1 x 1 | F32 |
| 266 | blk.22.ffn_down_exps.weight | Block 22 Ffn_Down_Exps (W) | (~201M) 201326592 | 768 x 2048 x 128 x 1 | F16 |
| 267 | blk.22.ffn_gate_exps.weight | Block 22 Ffn_Gate_Exps (W) | (~201M) 201326592 | 2048 x 768 x 128 x 1 | F16 |
| 268 | blk.22.ffn_up_exps.weight | Block 22 Ffn_Up_Exps (W) | (~201M) 201326592 | 2048 x 768 x 128 x 1 | F16 |
| 269 | blk.22.ffn_gate_inp.weight | Block 22 Expert-Routing Layer For The Feed-Forward Network In Mixture Of Expert Models (W) | (~262K) 262144 | 2048 x 128 x 1 x 1 | F32 |
| 270 | blk.22.ffn_norm.weight | Block 22 Feed-Forward Network Normalization (W) | ( ~2K) 2048 | 2048 x 1 x 1 x 1 | F32 |
| 271 | blk.22.attn_k_norm.weight | Block 22 Attn_K_Norm (W) | ( 128) 128 | 128 x 1 x 1 x 1 | F32 |
| 272 | blk.22.attn_k.weight | Block 22 Attention Key (W) | ( ~1M) 1048576 | 2048 x 512 x 1 x 1 | F16 |
| 273 | blk.22.attn_output.weight | Block 22 Attention Output (W) | ( ~8M) 8388608 | 4096 x 2048 x 1 x 1 | F16 |
| 274 | blk.22.attn_q_norm.weight | Block 22 Attn_Q_Norm (W) | ( 128) 128 | 128 x 1 x 1 x 1 | F32 |
| 275 | blk.22.attn_q.weight | Block 22 Attention Query (W) | ( ~8M) 8388608 | 2048 x 4096 x 1 x 1 | F16 |
| 276 | blk.22.attn_v.weight | Block 22 Attention Value (W) | ( ~1M) 1048576 | 2048 x 512 x 1 x 1 | F16 |
- Total elements in blk.22: (~623M) 623120640
- Percentage of total elements: 2.04%
### Block 23 Tensor Group : ~623M Elements
| T_ID | Tensor Layer Name | Human Friendly Tensor Layer Name | Elements | Shape | Type |
|-----:|:----------------------------|:-------------------------------------------------------------------------------------------|:------------------|:----------------------|:-----|
| 277 | blk.23.attn_norm.weight | Block 23 Attention Normalization (W) | ( ~2K) 2048 | 2048 x 1 x 1 x 1 | F32 |
| 278 | blk.23.ffn_down_exps.weight | Block 23 Ffn_Down_Exps (W) | (~201M) 201326592 | 768 x 2048 x 128 x 1 | F16 |
| 279 | blk.23.ffn_gate_exps.weight | Block 23 Ffn_Gate_Exps (W) | (~201M) 201326592 | 2048 x 768 x 128 x 1 | F16 |
| 280 | blk.23.ffn_up_exps.weight | Block 23 Ffn_Up_Exps (W) | (~201M) 201326592 | 2048 x 768 x 128 x 1 | F16 |
| 281 | blk.23.ffn_gate_inp.weight | Block 23 Expert-Routing Layer For The Feed-Forward Network In Mixture Of Expert Models (W) | (~262K) 262144 | 2048 x 128 x 1 x 1 | F32 |
| 282 | blk.23.ffn_norm.weight | Block 23 Feed-Forward Network Normalization (W) | ( ~2K) 2048 | 2048 x 1 x 1 x 1 | F32 |
| 283 | blk.23.attn_k_norm.weight | Block 23 Attn_K_Norm (W) | ( 128) 128 | 128 x 1 x 1 x 1 | F32 |
| 284 | blk.23.attn_k.weight | Block 23 Attention Key (W) | ( ~1M) 1048576 | 2048 x 512 x 1 x 1 | F16 |
| 285 | blk.23.attn_output.weight | Block 23 Attention Output (W) | ( ~8M) 8388608 | 4096 x 2048 x 1 x 1 | F16 |
| 286 | blk.23.attn_q_norm.weight | Block 23 Attn_Q_Norm (W) | ( 128) 128 | 128 x 1 x 1 x 1 | F32 |
| 287 | blk.23.attn_q.weight | Block 23 Attention Query (W) | ( ~8M) 8388608 | 2048 x 4096 x 1 x 1 | F16 |
| 288 | blk.23.attn_v.weight | Block 23 Attention Value (W) | ( ~1M) 1048576 | 2048 x 512 x 1 x 1 | F16 |
- Total elements in blk.23: (~623M) 623120640
- Percentage of total elements: 2.04%
### Block 24 Tensor Group : ~623M Elements
| T_ID | Tensor Layer Name | Human Friendly Tensor Layer Name | Elements | Shape | Type |
|-----:|:----------------------------|:-------------------------------------------------------------------------------------------|:------------------|:----------------------|:-----|
| 289 | blk.24.attn_norm.weight | Block 24 Attention Normalization (W) | ( ~2K) 2048 | 2048 x 1 x 1 x 1 | F32 |
| 290 | blk.24.ffn_down_exps.weight | Block 24 Ffn_Down_Exps (W) | (~201M) 201326592 | 768 x 2048 x 128 x 1 | F16 |
| 291 | blk.24.ffn_gate_exps.weight | Block 24 Ffn_Gate_Exps (W) | (~201M) 201326592 | 2048 x 768 x 128 x 1 | F16 |
| 292 | blk.24.ffn_up_exps.weight | Block 24 Ffn_Up_Exps (W) | (~201M) 201326592 | 2048 x 768 x 128 x 1 | F16 |
| 293 | blk.24.ffn_gate_inp.weight | Block 24 Expert-Routing Layer For The Feed-Forward Network In Mixture Of Expert Models (W) | (~262K) 262144 | 2048 x 128 x 1 x 1 | F32 |
| 294 | blk.24.ffn_norm.weight | Block 24 Feed-Forward Network Normalization (W) | ( ~2K) 2048 | 2048 x 1 x 1 x 1 | F32 |
| 295 | blk.24.attn_k_norm.weight | Block 24 Attn_K_Norm (W) | ( 128) 128 | 128 x 1 x 1 x 1 | F32 |
| 296 | blk.24.attn_k.weight | Block 24 Attention Key (W) | ( ~1M) 1048576 | 2048 x 512 x 1 x 1 | F16 |
| 297 | blk.24.attn_output.weight | Block 24 Attention Output (W) | ( ~8M) 8388608 | 4096 x 2048 x 1 x 1 | F16 |
| 298 | blk.24.attn_q_norm.weight | Block 24 Attn_Q_Norm (W) | ( 128) 128 | 128 x 1 x 1 x 1 | F32 |
| 299 | blk.24.attn_q.weight | Block 24 Attention Query (W) | ( ~8M) 8388608 | 2048 x 4096 x 1 x 1 | F16 |
| 300 | blk.24.attn_v.weight | Block 24 Attention Value (W) | ( ~1M) 1048576 | 2048 x 512 x 1 x 1 | F16 |
- Total elements in blk.24: (~623M) 623120640
- Percentage of total elements: 2.04%
### Block 25 Tensor Group : ~623M Elements
| T_ID | Tensor Layer Name | Human Friendly Tensor Layer Name | Elements | Shape | Type |
|-----:|:----------------------------|:-------------------------------------------------------------------------------------------|:------------------|:----------------------|:-----|
| 301 | blk.25.ffn_gate_inp.weight | Block 25 Expert-Routing Layer For The Feed-Forward Network In Mixture Of Expert Models (W) | (~262K) 262144 | 2048 x 128 x 1 x 1 | F32 |
| 302 | blk.25.attn_k_norm.weight | Block 25 Attn_K_Norm (W) | ( 128) 128 | 128 x 1 x 1 x 1 | F32 |
| 303 | blk.25.attn_k.weight | Block 25 Attention Key (W) | ( ~1M) 1048576 | 2048 x 512 x 1 x 1 | F16 |
| 304 | blk.25.attn_output.weight | Block 25 Attention Output (W) | ( ~8M) 8388608 | 4096 x 2048 x 1 x 1 | F16 |
| 305 | blk.25.attn_q_norm.weight | Block 25 Attn_Q_Norm (W) | ( 128) 128 | 128 x 1 x 1 x 1 | F32 |
| 306 | blk.25.attn_q.weight | Block 25 Attention Query (W) | ( ~8M) 8388608 | 2048 x 4096 x 1 x 1 | F16 |
| 307 | blk.25.attn_v.weight | Block 25 Attention Value (W) | ( ~1M) 1048576 | 2048 x 512 x 1 x 1 | F16 |
| 308 | blk.25.attn_norm.weight | Block 25 Attention Normalization (W) | ( ~2K) 2048 | 2048 x 1 x 1 x 1 | F32 |
| 309 | blk.25.ffn_down_exps.weight | Block 25 Ffn_Down_Exps (W) | (~201M) 201326592 | 768 x 2048 x 128 x 1 | F16 |
| 310 | blk.25.ffn_gate_exps.weight | Block 25 Ffn_Gate_Exps (W) | (~201M) 201326592 | 2048 x 768 x 128 x 1 | F16 |
| 311 | blk.25.ffn_up_exps.weight | Block 25 Ffn_Up_Exps (W) | (~201M) 201326592 | 2048 x 768 x 128 x 1 | F16 |
| 312 | blk.25.ffn_norm.weight | Block 25 Feed-Forward Network Normalization (W) | ( ~2K) 2048 | 2048 x 1 x 1 x 1 | F32 |
- Total elements in blk.25: (~623M) 623120640
- Percentage of total elements: 2.04%
### Block 26 Tensor Group : ~623M Elements
| T_ID | Tensor Layer Name | Human Friendly Tensor Layer Name | Elements | Shape | Type |
|-----:|:----------------------------|:-------------------------------------------------------------------------------------------|:------------------|:----------------------|:-----|
| 313 | blk.26.attn_norm.weight | Block 26 Attention Normalization (W) | ( ~2K) 2048 | 2048 x 1 x 1 x 1 | F32 |
| 314 | blk.26.ffn_down_exps.weight | Block 26 Ffn_Down_Exps (W) | (~201M) 201326592 | 768 x 2048 x 128 x 1 | F16 |
| 315 | blk.26.ffn_gate_exps.weight | Block 26 Ffn_Gate_Exps (W) | (~201M) 201326592 | 2048 x 768 x 128 x 1 | F16 |
| 316 | blk.26.ffn_up_exps.weight | Block 26 Ffn_Up_Exps (W) | (~201M) 201326592 | 2048 x 768 x 128 x 1 | F16 |
| 317 | blk.26.ffn_gate_inp.weight | Block 26 Expert-Routing Layer For The Feed-Forward Network In Mixture Of Expert Models (W) | (~262K) 262144 | 2048 x 128 x 1 x 1 | F32 |
| 318 | blk.26.ffn_norm.weight | Block 26 Feed-Forward Network Normalization (W) | ( ~2K) 2048 | 2048 x 1 x 1 x 1 | F32 |
| 319 | blk.26.attn_k_norm.weight | Block 26 Attn_K_Norm (W) | ( 128) 128 | 128 x 1 x 1 x 1 | F32 |
| 320 | blk.26.attn_k.weight | Block 26 Attention Key (W) | ( ~1M) 1048576 | 2048 x 512 x 1 x 1 | F16 |
| 321 | blk.26.attn_output.weight | Block 26 Attention Output (W) | ( ~8M) 8388608 | 4096 x 2048 x 1 x 1 | F16 |
| 322 | blk.26.attn_q_norm.weight | Block 26 Attn_Q_Norm (W) | ( 128) 128 | 128 x 1 x 1 x 1 | F32 |
| 323 | blk.26.attn_q.weight | Block 26 Attention Query (W) | ( ~8M) 8388608 | 2048 x 4096 x 1 x 1 | F16 |
| 324 | blk.26.attn_v.weight | Block 26 Attention Value (W) | ( ~1M) 1048576 | 2048 x 512 x 1 x 1 | F16 |
- Total elements in blk.26: (~623M) 623120640
- Percentage of total elements: 2.04%
### Block 27 Tensor Group : ~623M Elements
| T_ID | Tensor Layer Name | Human Friendly Tensor Layer Name | Elements | Shape | Type |
|-----:|:----------------------------|:-------------------------------------------------------------------------------------------|:------------------|:----------------------|:-----|
| 325 | blk.27.attn_norm.weight | Block 27 Attention Normalization (W) | ( ~2K) 2048 | 2048 x 1 x 1 x 1 | F32 |
| 326 | blk.27.ffn_down_exps.weight | Block 27 Ffn_Down_Exps (W) | (~201M) 201326592 | 768 x 2048 x 128 x 1 | F16 |
| 327 | blk.27.ffn_gate_exps.weight | Block 27 Ffn_Gate_Exps (W) | (~201M) 201326592 | 2048 x 768 x 128 x 1 | F16 |
| 328 | blk.27.ffn_up_exps.weight | Block 27 Ffn_Up_Exps (W) | (~201M) 201326592 | 2048 x 768 x 128 x 1 | F16 |
| 329 | blk.27.ffn_gate_inp.weight | Block 27 Expert-Routing Layer For The Feed-Forward Network In Mixture Of Expert Models (W) | (~262K) 262144 | 2048 x 128 x 1 x 1 | F32 |
| 330 | blk.27.ffn_norm.weight | Block 27 Feed-Forward Network Normalization (W) | ( ~2K) 2048 | 2048 x 1 x 1 x 1 | F32 |
| 331 | blk.27.attn_k_norm.weight | Block 27 Attn_K_Norm (W) | ( 128) 128 | 128 x 1 x 1 x 1 | F32 |
| 332 | blk.27.attn_k.weight | Block 27 Attention Key (W) | ( ~1M) 1048576 | 2048 x 512 x 1 x 1 | F16 |
| 333 | blk.27.attn_output.weight | Block 27 Attention Output (W) | ( ~8M) 8388608 | 4096 x 2048 x 1 x 1 | F16 |
| 334 | blk.27.attn_q_norm.weight | Block 27 Attn_Q_Norm (W) | ( 128) 128 | 128 x 1 x 1 x 1 | F32 |
| 335 | blk.27.attn_q.weight | Block 27 Attention Query (W) | ( ~8M) 8388608 | 2048 x 4096 x 1 x 1 | F16 |
| 336 | blk.27.attn_v.weight | Block 27 Attention Value (W) | ( ~1M) 1048576 | 2048 x 512 x 1 x 1 | F16 |
- Total elements in blk.27: (~623M) 623120640
- Percentage of total elements: 2.04%
### Block 28 Tensor Group : ~623M Elements
| T_ID | Tensor Layer Name | Human Friendly Tensor Layer Name | Elements | Shape | Type |
|-----:|:----------------------------|:-------------------------------------------------------------------------------------------|:------------------|:----------------------|:-----|
| 337 | blk.28.ffn_gate_inp.weight | Block 28 Expert-Routing Layer For The Feed-Forward Network In Mixture Of Expert Models (W) | (~262K) 262144 | 2048 x 128 x 1 x 1 | F32 |
| 338 | blk.28.attn_k_norm.weight | Block 28 Attn_K_Norm (W) | ( 128) 128 | 128 x 1 x 1 x 1 | F32 |
| 339 | blk.28.attn_k.weight | Block 28 Attention Key (W) | ( ~1M) 1048576 | 2048 x 512 x 1 x 1 | F16 |
| 340 | blk.28.attn_output.weight | Block 28 Attention Output (W) | ( ~8M) 8388608 | 4096 x 2048 x 1 x 1 | F16 |
| 341 | blk.28.attn_q_norm.weight | Block 28 Attn_Q_Norm (W) | ( 128) 128 | 128 x 1 x 1 x 1 | F32 |
| 342 | blk.28.attn_q.weight | Block 28 Attention Query (W) | ( ~8M) 8388608 | 2048 x 4096 x 1 x 1 | F16 |
| 343 | blk.28.attn_v.weight | Block 28 Attention Value (W) | ( ~1M) 1048576 | 2048 x 512 x 1 x 1 | F16 |
| 344 | blk.28.attn_norm.weight | Block 28 Attention Normalization (W) | ( ~2K) 2048 | 2048 x 1 x 1 x 1 | F32 |
| 345 | blk.28.ffn_down_exps.weight | Block 28 Ffn_Down_Exps (W) | (~201M) 201326592 | 768 x 2048 x 128 x 1 | F16 |
| 346 | blk.28.ffn_gate_exps.weight | Block 28 Ffn_Gate_Exps (W) | (~201M) 201326592 | 2048 x 768 x 128 x 1 | F16 |
| 347 | blk.28.ffn_up_exps.weight | Block 28 Ffn_Up_Exps (W) | (~201M) 201326592 | 2048 x 768 x 128 x 1 | F16 |
| 348 | blk.28.ffn_norm.weight | Block 28 Feed-Forward Network Normalization (W) | ( ~2K) 2048 | 2048 x 1 x 1 x 1 | F32 |
- Total elements in blk.28: (~623M) 623120640
- Percentage of total elements: 2.04%
### Block 29 Tensor Group : ~623M Elements
| T_ID | Tensor Layer Name | Human Friendly Tensor Layer Name | Elements | Shape | Type |
|-----:|:----------------------------|:-------------------------------------------------------------------------------------------|:------------------|:----------------------|:-----|
| 349 | blk.29.attn_norm.weight | Block 29 Attention Normalization (W) | ( ~2K) 2048 | 2048 x 1 x 1 x 1 | F32 |
| 350 | blk.29.ffn_down_exps.weight | Block 29 Ffn_Down_Exps (W) | (~201M) 201326592 | 768 x 2048 x 128 x 1 | F16 |
| 351 | blk.29.ffn_gate_exps.weight | Block 29 Ffn_Gate_Exps (W) | (~201M) 201326592 | 2048 x 768 x 128 x 1 | F16 |
| 352 | blk.29.ffn_up_exps.weight | Block 29 Ffn_Up_Exps (W) | (~201M) 201326592 | 2048 x 768 x 128 x 1 | F16 |
| 353 | blk.29.ffn_gate_inp.weight | Block 29 Expert-Routing Layer For The Feed-Forward Network In Mixture Of Expert Models (W) | (~262K) 262144 | 2048 x 128 x 1 x 1 | F32 |
| 354 | blk.29.ffn_norm.weight | Block 29 Feed-Forward Network Normalization (W) | ( ~2K) 2048 | 2048 x 1 x 1 x 1 | F32 |
| 355 | blk.29.attn_k_norm.weight | Block 29 Attn_K_Norm (W) | ( 128) 128 | 128 x 1 x 1 x 1 | F32 |
| 356 | blk.29.attn_k.weight | Block 29 Attention Key (W) | ( ~1M) 1048576 | 2048 x 512 x 1 x 1 | F16 |
| 357 | blk.29.attn_output.weight | Block 29 Attention Output (W) | ( ~8M) 8388608 | 4096 x 2048 x 1 x 1 | F16 |
| 358 | blk.29.attn_q_norm.weight | Block 29 Attn_Q_Norm (W) | ( 128) 128 | 128 x 1 x 1 x 1 | F32 |
| 359 | blk.29.attn_q.weight | Block 29 Attention Query (W) | ( ~8M) 8388608 | 2048 x 4096 x 1 x 1 | F16 |
| 360 | blk.29.attn_v.weight | Block 29 Attention Value (W) | ( ~1M) 1048576 | 2048 x 512 x 1 x 1 | F16 |
- Total elements in blk.29: (~623M) 623120640
- Percentage of total elements: 2.04%
### Block 30 Tensor Group : ~623M Elements
| T_ID | Tensor Layer Name | Human Friendly Tensor Layer Name | Elements | Shape | Type |
|-----:|:----------------------------|:-------------------------------------------------------------------------------------------|:------------------|:----------------------|:-----|
| 361 | blk.30.attn_norm.weight | Block 30 Attention Normalization (W) | ( ~2K) 2048 | 2048 x 1 x 1 x 1 | F32 |
| 362 | blk.30.ffn_down_exps.weight | Block 30 Ffn_Down_Exps (W) | (~201M) 201326592 | 768 x 2048 x 128 x 1 | F16 |
| 363 | blk.30.ffn_gate_exps.weight | Block 30 Ffn_Gate_Exps (W) | (~201M) 201326592 | 2048 x 768 x 128 x 1 | F16 |
| 364 | blk.30.ffn_up_exps.weight | Block 30 Ffn_Up_Exps (W) | (~201M) 201326592 | 2048 x 768 x 128 x 1 | F16 |
| 365 | blk.30.ffn_gate_inp.weight | Block 30 Expert-Routing Layer For The Feed-Forward Network In Mixture Of Expert Models (W) | (~262K) 262144 | 2048 x 128 x 1 x 1 | F32 |
| 366 | blk.30.ffn_norm.weight | Block 30 Feed-Forward Network Normalization (W) | ( ~2K) 2048 | 2048 x 1 x 1 x 1 | F32 |
| 367 | blk.30.attn_k_norm.weight | Block 30 Attn_K_Norm (W) | ( 128) 128 | 128 x 1 x 1 x 1 | F32 |
| 368 | blk.30.attn_k.weight | Block 30 Attention Key (W) | ( ~1M) 1048576 | 2048 x 512 x 1 x 1 | F16 |
| 369 | blk.30.attn_output.weight | Block 30 Attention Output (W) | ( ~8M) 8388608 | 4096 x 2048 x 1 x 1 | F16 |
| 370 | blk.30.attn_q_norm.weight | Block 30 Attn_Q_Norm (W) | ( 128) 128 | 128 x 1 x 1 x 1 | F32 |
| 371 | blk.30.attn_q.weight | Block 30 Attention Query (W) | ( ~8M) 8388608 | 2048 x 4096 x 1 x 1 | F16 |
| 372 | blk.30.attn_v.weight | Block 30 Attention Value (W) | ( ~1M) 1048576 | 2048 x 512 x 1 x 1 | F16 |
- Total elements in blk.30: (~623M) 623120640
- Percentage of total elements: 2.04%
### Block 31 Tensor Group : ~623M Elements
| T_ID | Tensor Layer Name | Human Friendly Tensor Layer Name | Elements | Shape | Type |
|-----:|:----------------------------|:-------------------------------------------------------------------------------------------|:------------------|:----------------------|:-----|
| 373 | blk.31.ffn_gate_inp.weight | Block 31 Expert-Routing Layer For The Feed-Forward Network In Mixture Of Expert Models (W) | (~262K) 262144 | 2048 x 128 x 1 x 1 | F32 |
| 374 | blk.31.attn_k_norm.weight | Block 31 Attn_K_Norm (W) | ( 128) 128 | 128 x 1 x 1 x 1 | F32 |
| 375 | blk.31.attn_k.weight | Block 31 Attention Key (W) | ( ~1M) 1048576 | 2048 x 512 x 1 x 1 | F16 |
| 376 | blk.31.attn_output.weight | Block 31 Attention Output (W) | ( ~8M) 8388608 | 4096 x 2048 x 1 x 1 | F16 |
| 377 | blk.31.attn_q_norm.weight | Block 31 Attn_Q_Norm (W) | ( 128) 128 | 128 x 1 x 1 x 1 | F32 |
| 378 | blk.31.attn_q.weight | Block 31 Attention Query (W) | ( ~8M) 8388608 | 2048 x 4096 x 1 x 1 | F16 |
| 379 | blk.31.attn_v.weight | Block 31 Attention Value (W) | ( ~1M) 1048576 | 2048 x 512 x 1 x 1 | F16 |
| 380 | blk.31.attn_norm.weight | Block 31 Attention Normalization (W) | ( ~2K) 2048 | 2048 x 1 x 1 x 1 | F32 |
| 381 | blk.31.ffn_down_exps.weight | Block 31 Ffn_Down_Exps (W) | (~201M) 201326592 | 768 x 2048 x 128 x 1 | F16 |
| 382 | blk.31.ffn_gate_exps.weight | Block 31 Ffn_Gate_Exps (W) | (~201M) 201326592 | 2048 x 768 x 128 x 1 | F16 |
| 383 | blk.31.ffn_up_exps.weight | Block 31 Ffn_Up_Exps (W) | (~201M) 201326592 | 2048 x 768 x 128 x 1 | F16 |
| 384 | blk.31.ffn_norm.weight | Block 31 Feed-Forward Network Normalization (W) | ( ~2K) 2048 | 2048 x 1 x 1 x 1 | F32 |
- Total elements in blk.31: (~623M) 623120640
- Percentage of total elements: 2.04%
### Block 32 Tensor Group : ~623M Elements
| T_ID | Tensor Layer Name | Human Friendly Tensor Layer Name | Elements | Shape | Type |
|-----:|:----------------------------|:-------------------------------------------------------------------------------------------|:------------------|:----------------------|:-----|
| 385 | blk.32.attn_norm.weight | Block 32 Attention Normalization (W) | ( ~2K) 2048 | 2048 x 1 x 1 x 1 | F32 |
| 386 | blk.32.ffn_down_exps.weight | Block 32 Ffn_Down_Exps (W) | (~201M) 201326592 | 768 x 2048 x 128 x 1 | F16 |
| 387 | blk.32.ffn_gate_exps.weight | Block 32 Ffn_Gate_Exps (W) | (~201M) 201326592 | 2048 x 768 x 128 x 1 | F16 |
| 388 | blk.32.ffn_up_exps.weight | Block 32 Ffn_Up_Exps (W) | (~201M) 201326592 | 2048 x 768 x 128 x 1 | F16 |
| 389 | blk.32.ffn_gate_inp.weight | Block 32 Expert-Routing Layer For The Feed-Forward Network In Mixture Of Expert Models (W) | (~262K) 262144 | 2048 x 128 x 1 x 1 | F32 |
| 390 | blk.32.ffn_norm.weight | Block 32 Feed-Forward Network Normalization (W) | ( ~2K) 2048 | 2048 x 1 x 1 x 1 | F32 |
| 391 | blk.32.attn_k_norm.weight | Block 32 Attn_K_Norm (W) | ( 128) 128 | 128 x 1 x 1 x 1 | F32 |
| 392 | blk.32.attn_k.weight | Block 32 Attention Key (W) | ( ~1M) 1048576 | 2048 x 512 x 1 x 1 | F16 |
| 393 | blk.32.attn_output.weight | Block 32 Attention Output (W) | ( ~8M) 8388608 | 4096 x 2048 x 1 x 1 | F16 |
| 394 | blk.32.attn_q_norm.weight | Block 32 Attn_Q_Norm (W) | ( 128) 128 | 128 x 1 x 1 x 1 | F32 |
| 395 | blk.32.attn_q.weight | Block 32 Attention Query (W) | ( ~8M) 8388608 | 2048 x 4096 x 1 x 1 | F16 |
| 396 | blk.32.attn_v.weight | Block 32 Attention Value (W) | ( ~1M) 1048576 | 2048 x 512 x 1 x 1 | F16 |
- Total elements in blk.32: (~623M) 623120640
- Percentage of total elements: 2.04%
### Block 33 Tensor Group : ~623M Elements
| T_ID | Tensor Layer Name | Human Friendly Tensor Layer Name | Elements | Shape | Type |
|-----:|:----------------------------|:-------------------------------------------------------------------------------------------|:------------------|:----------------------|:-----|
| 397 | blk.33.attn_norm.weight | Block 33 Attention Normalization (W) | ( ~2K) 2048 | 2048 x 1 x 1 x 1 | F32 |
| 398 | blk.33.ffn_down_exps.weight | Block 33 Ffn_Down_Exps (W) | (~201M) 201326592 | 768 x 2048 x 128 x 1 | F16 |
| 399 | blk.33.ffn_gate_exps.weight | Block 33 Ffn_Gate_Exps (W) | (~201M) 201326592 | 2048 x 768 x 128 x 1 | F16 |
| 400 | blk.33.ffn_up_exps.weight | Block 33 Ffn_Up_Exps (W) | (~201M) 201326592 | 2048 x 768 x 128 x 1 | F16 |
| 401 | blk.33.ffn_gate_inp.weight | Block 33 Expert-Routing Layer For The Feed-Forward Network In Mixture Of Expert Models (W) | (~262K) 262144 | 2048 x 128 x 1 x 1 | F32 |
| 402 | blk.33.ffn_norm.weight | Block 33 Feed-Forward Network Normalization (W) | ( ~2K) 2048 | 2048 x 1 x 1 x 1 | F32 |
| 403 | blk.33.attn_k_norm.weight | Block 33 Attn_K_Norm (W) | ( 128) 128 | 128 x 1 x 1 x 1 | F32 |
| 404 | blk.33.attn_k.weight | Block 33 Attention Key (W) | ( ~1M) 1048576 | 2048 x 512 x 1 x 1 | F16 |
| 405 | blk.33.attn_output.weight | Block 33 Attention Output (W) | ( ~8M) 8388608 | 4096 x 2048 x 1 x 1 | F16 |
| 406 | blk.33.attn_q_norm.weight | Block 33 Attn_Q_Norm (W) | ( 128) 128 | 128 x 1 x 1 x 1 | F32 |
| 407 | blk.33.attn_q.weight | Block 33 Attention Query (W) | ( ~8M) 8388608 | 2048 x 4096 x 1 x 1 | F16 |
| 408 | blk.33.attn_v.weight | Block 33 Attention Value (W) | ( ~1M) 1048576 | 2048 x 512 x 1 x 1 | F16 |
- Total elements in blk.33: (~623M) 623120640
- Percentage of total elements: 2.04%
### Block 34 Tensor Group : ~623M Elements
| T_ID | Tensor Layer Name | Human Friendly Tensor Layer Name | Elements | Shape | Type |
|-----:|:----------------------------|:-------------------------------------------------------------------------------------------|:------------------|:----------------------|:-----|
| 409 | blk.34.ffn_gate_inp.weight | Block 34 Expert-Routing Layer For The Feed-Forward Network In Mixture Of Expert Models (W) | (~262K) 262144 | 2048 x 128 x 1 x 1 | F32 |
| 410 | blk.34.attn_k_norm.weight | Block 34 Attn_K_Norm (W) | ( 128) 128 | 128 x 1 x 1 x 1 | F32 |
| 411 | blk.34.attn_k.weight | Block 34 Attention Key (W) | ( ~1M) 1048576 | 2048 x 512 x 1 x 1 | F16 |
| 412 | blk.34.attn_output.weight | Block 34 Attention Output (W) | ( ~8M) 8388608 | 4096 x 2048 x 1 x 1 | F16 |
| 413 | blk.34.attn_q_norm.weight | Block 34 Attn_Q_Norm (W) | ( 128) 128 | 128 x 1 x 1 x 1 | F32 |
| 414 | blk.34.attn_q.weight | Block 34 Attention Query (W) | ( ~8M) 8388608 | 2048 x 4096 x 1 x 1 | F16 |
| 415 | blk.34.attn_v.weight | Block 34 Attention Value (W) | ( ~1M) 1048576 | 2048 x 512 x 1 x 1 | F16 |
| 416 | blk.34.attn_norm.weight | Block 34 Attention Normalization (W) | ( ~2K) 2048 | 2048 x 1 x 1 x 1 | F32 |
| 417 | blk.34.ffn_down_exps.weight | Block 34 Ffn_Down_Exps (W) | (~201M) 201326592 | 768 x 2048 x 128 x 1 | F16 |
| 418 | blk.34.ffn_gate_exps.weight | Block 34 Ffn_Gate_Exps (W) | (~201M) 201326592 | 2048 x 768 x 128 x 1 | F16 |
| 419 | blk.34.ffn_up_exps.weight | Block 34 Ffn_Up_Exps (W) | (~201M) 201326592 | 2048 x 768 x 128 x 1 | F16 |
| 420 | blk.34.ffn_norm.weight | Block 34 Feed-Forward Network Normalization (W) | ( ~2K) 2048 | 2048 x 1 x 1 x 1 | F32 |
- Total elements in blk.34: (~623M) 623120640
- Percentage of total elements: 2.04%
### Block 35 Tensor Group : ~623M Elements
| T_ID | Tensor Layer Name | Human Friendly Tensor Layer Name | Elements | Shape | Type |
|-----:|:----------------------------|:-------------------------------------------------------------------------------------------|:------------------|:----------------------|:-----|
| 421 | blk.35.attn_norm.weight | Block 35 Attention Normalization (W) | ( ~2K) 2048 | 2048 x 1 x 1 x 1 | F32 |
| 422 | blk.35.ffn_down_exps.weight | Block 35 Ffn_Down_Exps (W) | (~201M) 201326592 | 768 x 2048 x 128 x 1 | F16 |
| 423 | blk.35.ffn_gate_exps.weight | Block 35 Ffn_Gate_Exps (W) | (~201M) 201326592 | 2048 x 768 x 128 x 1 | F16 |
| 424 | blk.35.ffn_up_exps.weight | Block 35 Ffn_Up_Exps (W) | (~201M) 201326592 | 2048 x 768 x 128 x 1 | F16 |
| 425 | blk.35.ffn_gate_inp.weight | Block 35 Expert-Routing Layer For The Feed-Forward Network In Mixture Of Expert Models (W) | (~262K) 262144 | 2048 x 128 x 1 x 1 | F32 |
| 426 | blk.35.ffn_norm.weight | Block 35 Feed-Forward Network Normalization (W) | ( ~2K) 2048 | 2048 x 1 x 1 x 1 | F32 |
| 427 | blk.35.attn_k_norm.weight | Block 35 Attn_K_Norm (W) | ( 128) 128 | 128 x 1 x 1 x 1 | F32 |
| 428 | blk.35.attn_k.weight | Block 35 Attention Key (W) | ( ~1M) 1048576 | 2048 x 512 x 1 x 1 | F16 |
| 429 | blk.35.attn_output.weight | Block 35 Attention Output (W) | ( ~8M) 8388608 | 4096 x 2048 x 1 x 1 | F16 |
| 430 | blk.35.attn_q_norm.weight | Block 35 Attn_Q_Norm (W) | ( 128) 128 | 128 x 1 x 1 x 1 | F32 |
| 431 | blk.35.attn_q.weight | Block 35 Attention Query (W) | ( ~8M) 8388608 | 2048 x 4096 x 1 x 1 | F16 |
| 432 | blk.35.attn_v.weight | Block 35 Attention Value (W) | ( ~1M) 1048576 | 2048 x 512 x 1 x 1 | F16 |
- Total elements in blk.35: (~623M) 623120640
- Percentage of total elements: 2.04%
### Block 36 Tensor Group : ~623M Elements
| T_ID | Tensor Layer Name | Human Friendly Tensor Layer Name | Elements | Shape | Type |
|-----:|:----------------------------|:-------------------------------------------------------------------------------------------|:------------------|:----------------------|:-----|
| 433 | blk.36.attn_norm.weight | Block 36 Attention Normalization (W) | ( ~2K) 2048 | 2048 x 1 x 1 x 1 | F32 |
| 434 | blk.36.ffn_down_exps.weight | Block 36 Ffn_Down_Exps (W) | (~201M) 201326592 | 768 x 2048 x 128 x 1 | F16 |
| 435 | blk.36.ffn_gate_exps.weight | Block 36 Ffn_Gate_Exps (W) | (~201M) 201326592 | 2048 x 768 x 128 x 1 | F16 |
| 436 | blk.36.ffn_up_exps.weight | Block 36 Ffn_Up_Exps (W) | (~201M) 201326592 | 2048 x 768 x 128 x 1 | F16 |
| 437 | blk.36.ffn_gate_inp.weight | Block 36 Expert-Routing Layer For The Feed-Forward Network In Mixture Of Expert Models (W) | (~262K) 262144 | 2048 x 128 x 1 x 1 | F32 |
| 438 | blk.36.ffn_norm.weight | Block 36 Feed-Forward Network Normalization (W) | ( ~2K) 2048 | 2048 x 1 x 1 x 1 | F32 |
| 439 | blk.36.attn_k_norm.weight | Block 36 Attn_K_Norm (W) | ( 128) 128 | 128 x 1 x 1 x 1 | F32 |
| 440 | blk.36.attn_k.weight | Block 36 Attention Key (W) | ( ~1M) 1048576 | 2048 x 512 x 1 x 1 | F16 |
| 441 | blk.36.attn_output.weight | Block 36 Attention Output (W) | ( ~8M) 8388608 | 4096 x 2048 x 1 x 1 | F16 |
| 442 | blk.36.attn_q_norm.weight | Block 36 Attn_Q_Norm (W) | ( 128) 128 | 128 x 1 x 1 x 1 | F32 |
| 443 | blk.36.attn_q.weight | Block 36 Attention Query (W) | ( ~8M) 8388608 | 2048 x 4096 x 1 x 1 | F16 |
| 444 | blk.36.attn_v.weight | Block 36 Attention Value (W) | ( ~1M) 1048576 | 2048 x 512 x 1 x 1 | F16 |
- Total elements in blk.36: (~623M) 623120640
- Percentage of total elements: 2.04%
### Block 37 Tensor Group : ~623M Elements
| T_ID | Tensor Layer Name | Human Friendly Tensor Layer Name | Elements | Shape | Type |
|-----:|:----------------------------|:-------------------------------------------------------------------------------------------|:------------------|:----------------------|:-----|
| 445 | blk.37.attn_norm.weight | Block 37 Attention Normalization (W) | ( ~2K) 2048 | 2048 x 1 x 1 x 1 | F32 |
| 446 | blk.37.ffn_down_exps.weight | Block 37 Ffn_Down_Exps (W) | (~201M) 201326592 | 768 x 2048 x 128 x 1 | F16 |
| 447 | blk.37.ffn_gate_exps.weight | Block 37 Ffn_Gate_Exps (W) | (~201M) 201326592 | 2048 x 768 x 128 x 1 | F16 |
| 448 | blk.37.ffn_up_exps.weight | Block 37 Ffn_Up_Exps (W) | (~201M) 201326592 | 2048 x 768 x 128 x 1 | F16 |
| 449 | blk.37.ffn_gate_inp.weight | Block 37 Expert-Routing Layer For The Feed-Forward Network In Mixture Of Expert Models (W) | (~262K) 262144 | 2048 x 128 x 1 x 1 | F32 |
| 450 | blk.37.ffn_norm.weight | Block 37 Feed-Forward Network Normalization (W) | ( ~2K) 2048 | 2048 x 1 x 1 x 1 | F32 |
| 451 | blk.37.attn_k_norm.weight | Block 37 Attn_K_Norm (W) | ( 128) 128 | 128 x 1 x 1 x 1 | F32 |
| 452 | blk.37.attn_k.weight | Block 37 Attention Key (W) | ( ~1M) 1048576 | 2048 x 512 x 1 x 1 | F16 |
| 453 | blk.37.attn_output.weight | Block 37 Attention Output (W) | ( ~8M) 8388608 | 4096 x 2048 x 1 x 1 | F16 |
| 454 | blk.37.attn_q_norm.weight | Block 37 Attn_Q_Norm (W) | ( 128) 128 | 128 x 1 x 1 x 1 | F32 |
| 455 | blk.37.attn_q.weight | Block 37 Attention Query (W) | ( ~8M) 8388608 | 2048 x 4096 x 1 x 1 | F16 |
| 456 | blk.37.attn_v.weight | Block 37 Attention Value (W) | ( ~1M) 1048576 | 2048 x 512 x 1 x 1 | F16 |
- Total elements in blk.37: (~623M) 623120640
- Percentage of total elements: 2.04%
### Block 38 Tensor Group : ~623M Elements
| T_ID | Tensor Layer Name | Human Friendly Tensor Layer Name | Elements | Shape | Type |
|-----:|:----------------------------|:-------------------------------------------------------------------------------------------|:------------------|:----------------------|:-----|
| 457 | blk.38.attn_norm.weight | Block 38 Attention Normalization (W) | ( ~2K) 2048 | 2048 x 1 x 1 x 1 | F32 |
| 458 | blk.38.ffn_down_exps.weight | Block 38 Ffn_Down_Exps (W) | (~201M) 201326592 | 768 x 2048 x 128 x 1 | F16 |
| 459 | blk.38.ffn_gate_exps.weight | Block 38 Ffn_Gate_Exps (W) | (~201M) 201326592 | 2048 x 768 x 128 x 1 | F16 |
| 460 | blk.38.ffn_up_exps.weight | Block 38 Ffn_Up_Exps (W) | (~201M) 201326592 | 2048 x 768 x 128 x 1 | F16 |
| 461 | blk.38.ffn_gate_inp.weight | Block 38 Expert-Routing Layer For The Feed-Forward Network In Mixture Of Expert Models (W) | (~262K) 262144 | 2048 x 128 x 1 x 1 | F32 |
| 462 | blk.38.ffn_norm.weight | Block 38 Feed-Forward Network Normalization (W) | ( ~2K) 2048 | 2048 x 1 x 1 x 1 | F32 |
| 463 | blk.38.attn_k_norm.weight | Block 38 Attn_K_Norm (W) | ( 128) 128 | 128 x 1 x 1 x 1 | F32 |
| 464 | blk.38.attn_k.weight | Block 38 Attention Key (W) | ( ~1M) 1048576 | 2048 x 512 x 1 x 1 | F16 |
| 465 | blk.38.attn_output.weight | Block 38 Attention Output (W) | ( ~8M) 8388608 | 4096 x 2048 x 1 x 1 | F16 |
| 466 | blk.38.attn_q_norm.weight | Block 38 Attn_Q_Norm (W) | ( 128) 128 | 128 x 1 x 1 x 1 | F32 |
| 467 | blk.38.attn_q.weight | Block 38 Attention Query (W) | ( ~8M) 8388608 | 2048 x 4096 x 1 x 1 | F16 |
| 468 | blk.38.attn_v.weight | Block 38 Attention Value (W) | ( ~1M) 1048576 | 2048 x 512 x 1 x 1 | F16 |
- Total elements in blk.38: (~623M) 623120640
- Percentage of total elements: 2.04%
### Block 39 Tensor Group : ~623M Elements
| T_ID | Tensor Layer Name | Human Friendly Tensor Layer Name | Elements | Shape | Type |
|-----:|:----------------------------|:-------------------------------------------------------------------------------------------|:------------------|:----------------------|:-----|
| 469 | blk.39.attn_norm.weight | Block 39 Attention Normalization (W) | ( ~2K) 2048 | 2048 x 1 x 1 x 1 | F32 |
| 470 | blk.39.ffn_down_exps.weight | Block 39 Ffn_Down_Exps (W) | (~201M) 201326592 | 768 x 2048 x 128 x 1 | F16 |
| 471 | blk.39.ffn_gate_exps.weight | Block 39 Ffn_Gate_Exps (W) | (~201M) 201326592 | 2048 x 768 x 128 x 1 | F16 |
| 472 | blk.39.ffn_up_exps.weight | Block 39 Ffn_Up_Exps (W) | (~201M) 201326592 | 2048 x 768 x 128 x 1 | F16 |
| 473 | blk.39.ffn_gate_inp.weight | Block 39 Expert-Routing Layer For The Feed-Forward Network In Mixture Of Expert Models (W) | (~262K) 262144 | 2048 x 128 x 1 x 1 | F32 |
| 474 | blk.39.ffn_norm.weight | Block 39 Feed-Forward Network Normalization (W) | ( ~2K) 2048 | 2048 x 1 x 1 x 1 | F32 |
| 475 | blk.39.attn_k_norm.weight | Block 39 Attn_K_Norm (W) | ( 128) 128 | 128 x 1 x 1 x 1 | F32 |
| 476 | blk.39.attn_k.weight | Block 39 Attention Key (W) | ( ~1M) 1048576 | 2048 x 512 x 1 x 1 | F16 |
| 477 | blk.39.attn_output.weight | Block 39 Attention Output (W) | ( ~8M) 8388608 | 4096 x 2048 x 1 x 1 | F16 |
| 478 | blk.39.attn_q_norm.weight | Block 39 Attn_Q_Norm (W) | ( 128) 128 | 128 x 1 x 1 x 1 | F32 |
| 479 | blk.39.attn_q.weight | Block 39 Attention Query (W) | ( ~8M) 8388608 | 2048 x 4096 x 1 x 1 | F16 |
| 480 | blk.39.attn_v.weight | Block 39 Attention Value (W) | ( ~1M) 1048576 | 2048 x 512 x 1 x 1 | F16 |
- Total elements in blk.39: (~623M) 623120640
- Percentage of total elements: 2.04%
### Block 40 Tensor Group : ~623M Elements
| T_ID | Tensor Layer Name | Human Friendly Tensor Layer Name | Elements | Shape | Type |
|-----:|:----------------------------|:-------------------------------------------------------------------------------------------|:------------------|:----------------------|:-----|
| 481 | blk.40.attn_norm.weight | Block 40 Attention Normalization (W) | ( ~2K) 2048 | 2048 x 1 x 1 x 1 | F32 |
| 482 | blk.40.ffn_down_exps.weight | Block 40 Ffn_Down_Exps (W) | (~201M) 201326592 | 768 x 2048 x 128 x 1 | F16 |
| 483 | blk.40.ffn_gate_exps.weight | Block 40 Ffn_Gate_Exps (W) | (~201M) 201326592 | 2048 x 768 x 128 x 1 | F16 |
| 484 | blk.40.ffn_up_exps.weight | Block 40 Ffn_Up_Exps (W) | (~201M) 201326592 | 2048 x 768 x 128 x 1 | F16 |
| 485 | blk.40.ffn_gate_inp.weight | Block 40 Expert-Routing Layer For The Feed-Forward Network In Mixture Of Expert Models (W) | (~262K) 262144 | 2048 x 128 x 1 x 1 | F32 |
| 486 | blk.40.ffn_norm.weight | Block 40 Feed-Forward Network Normalization (W) | ( ~2K) 2048 | 2048 x 1 x 1 x 1 | F32 |
| 487 | blk.40.attn_k_norm.weight | Block 40 Attn_K_Norm (W) | ( 128) 128 | 128 x 1 x 1 x 1 | F32 |
| 488 | blk.40.attn_k.weight | Block 40 Attention Key (W) | ( ~1M) 1048576 | 2048 x 512 x 1 x 1 | F16 |
| 489 | blk.40.attn_output.weight | Block 40 Attention Output (W) | ( ~8M) 8388608 | 4096 x 2048 x 1 x 1 | F16 |
| 490 | blk.40.attn_q_norm.weight | Block 40 Attn_Q_Norm (W) | ( 128) 128 | 128 x 1 x 1 x 1 | F32 |
| 491 | blk.40.attn_q.weight | Block 40 Attention Query (W) | ( ~8M) 8388608 | 2048 x 4096 x 1 x 1 | F16 |
| 492 | blk.40.attn_v.weight | Block 40 Attention Value (W) | ( ~1M) 1048576 | 2048 x 512 x 1 x 1 | F16 |
- Total elements in blk.40: (~623M) 623120640
- Percentage of total elements: 2.04%
### Block 41 Tensor Group : ~623M Elements
| T_ID | Tensor Layer Name | Human Friendly Tensor Layer Name | Elements | Shape | Type |
|-----:|:----------------------------|:-------------------------------------------------------------------------------------------|:------------------|:----------------------|:-----|
| 493 | blk.41.ffn_gate_inp.weight | Block 41 Expert-Routing Layer For The Feed-Forward Network In Mixture Of Expert Models (W) | (~262K) 262144 | 2048 x 128 x 1 x 1 | F32 |
| 494 | blk.41.attn_k_norm.weight | Block 41 Attn_K_Norm (W) | ( 128) 128 | 128 x 1 x 1 x 1 | F32 |
| 495 | blk.41.attn_k.weight | Block 41 Attention Key (W) | ( ~1M) 1048576 | 2048 x 512 x 1 x 1 | F16 |
| 496 | blk.41.attn_output.weight | Block 41 Attention Output (W) | ( ~8M) 8388608 | 4096 x 2048 x 1 x 1 | F16 |
| 497 | blk.41.attn_q_norm.weight | Block 41 Attn_Q_Norm (W) | ( 128) 128 | 128 x 1 x 1 x 1 | F32 |
| 498 | blk.41.attn_q.weight | Block 41 Attention Query (W) | ( ~8M) 8388608 | 2048 x 4096 x 1 x 1 | F16 |
| 499 | blk.41.attn_v.weight | Block 41 Attention Value (W) | ( ~1M) 1048576 | 2048 x 512 x 1 x 1 | F16 |
| 500 | blk.41.attn_norm.weight | Block 41 Attention Normalization (W) | ( ~2K) 2048 | 2048 x 1 x 1 x 1 | F32 |
| 501 | blk.41.ffn_down_exps.weight | Block 41 Ffn_Down_Exps (W) | (~201M) 201326592 | 768 x 2048 x 128 x 1 | F16 |
| 502 | blk.41.ffn_gate_exps.weight | Block 41 Ffn_Gate_Exps (W) | (~201M) 201326592 | 2048 x 768 x 128 x 1 | F16 |
| 503 | blk.41.ffn_up_exps.weight | Block 41 Ffn_Up_Exps (W) | (~201M) 201326592 | 2048 x 768 x 128 x 1 | F16 |
| 504 | blk.41.ffn_norm.weight | Block 41 Feed-Forward Network Normalization (W) | ( ~2K) 2048 | 2048 x 1 x 1 x 1 | F32 |
- Total elements in blk.41: (~623M) 623120640
- Percentage of total elements: 2.04%
### Block 42 Tensor Group : ~623M Elements
| T_ID | Tensor Layer Name | Human Friendly Tensor Layer Name | Elements | Shape | Type |
|-----:|:----------------------------|:-------------------------------------------------------------------------------------------|:------------------|:----------------------|:-----|
| 505 | blk.42.attn_norm.weight | Block 42 Attention Normalization (W) | ( ~2K) 2048 | 2048 x 1 x 1 x 1 | F32 |
| 506 | blk.42.ffn_down_exps.weight | Block 42 Ffn_Down_Exps (W) | (~201M) 201326592 | 768 x 2048 x 128 x 1 | F16 |
| 507 | blk.42.ffn_gate_exps.weight | Block 42 Ffn_Gate_Exps (W) | (~201M) 201326592 | 2048 x 768 x 128 x 1 | F16 |
| 508 | blk.42.ffn_up_exps.weight | Block 42 Ffn_Up_Exps (W) | (~201M) 201326592 | 2048 x 768 x 128 x 1 | F16 |
| 509 | blk.42.ffn_gate_inp.weight | Block 42 Expert-Routing Layer For The Feed-Forward Network In Mixture Of Expert Models (W) | (~262K) 262144 | 2048 x 128 x 1 x 1 | F32 |
| 510 | blk.42.ffn_norm.weight | Block 42 Feed-Forward Network Normalization (W) | ( ~2K) 2048 | 2048 x 1 x 1 x 1 | F32 |
| 511 | blk.42.attn_k_norm.weight | Block 42 Attn_K_Norm (W) | ( 128) 128 | 128 x 1 x 1 x 1 | F32 |
| 512 | blk.42.attn_k.weight | Block 42 Attention Key (W) | ( ~1M) 1048576 | 2048 x 512 x 1 x 1 | F16 |
| 513 | blk.42.attn_output.weight | Block 42 Attention Output (W) | ( ~8M) 8388608 | 4096 x 2048 x 1 x 1 | F16 |
| 514 | blk.42.attn_q_norm.weight | Block 42 Attn_Q_Norm (W) | ( 128) 128 | 128 x 1 x 1 x 1 | F32 |
| 515 | blk.42.attn_q.weight | Block 42 Attention Query (W) | ( ~8M) 8388608 | 2048 x 4096 x 1 x 1 | F16 |
| 516 | blk.42.attn_v.weight | Block 42 Attention Value (W) | ( ~1M) 1048576 | 2048 x 512 x 1 x 1 | F16 |
- Total elements in blk.42: (~623M) 623120640
- Percentage of total elements: 2.04%
### Block 43 Tensor Group : ~623M Elements
| T_ID | Tensor Layer Name | Human Friendly Tensor Layer Name | Elements | Shape | Type |
|-----:|:----------------------------|:-------------------------------------------------------------------------------------------|:------------------|:----------------------|:-----|
| 517 | blk.43.attn_norm.weight | Block 43 Attention Normalization (W) | ( ~2K) 2048 | 2048 x 1 x 1 x 1 | F32 |
| 518 | blk.43.ffn_down_exps.weight | Block 43 Ffn_Down_Exps (W) | (~201M) 201326592 | 768 x 2048 x 128 x 1 | F16 |
| 519 | blk.43.ffn_gate_exps.weight | Block 43 Ffn_Gate_Exps (W) | (~201M) 201326592 | 2048 x 768 x 128 x 1 | F16 |
| 520 | blk.43.ffn_up_exps.weight | Block 43 Ffn_Up_Exps (W) | (~201M) 201326592 | 2048 x 768 x 128 x 1 | F16 |
| 521 | blk.43.ffn_gate_inp.weight | Block 43 Expert-Routing Layer For The Feed-Forward Network In Mixture Of Expert Models (W) | (~262K) 262144 | 2048 x 128 x 1 x 1 | F32 |
| 522 | blk.43.ffn_norm.weight | Block 43 Feed-Forward Network Normalization (W) | ( ~2K) 2048 | 2048 x 1 x 1 x 1 | F32 |
| 523 | blk.43.attn_k_norm.weight | Block 43 Attn_K_Norm (W) | ( 128) 128 | 128 x 1 x 1 x 1 | F32 |
| 524 | blk.43.attn_k.weight | Block 43 Attention Key (W) | ( ~1M) 1048576 | 2048 x 512 x 1 x 1 | F16 |
| 525 | blk.43.attn_output.weight | Block 43 Attention Output (W) | ( ~8M) 8388608 | 4096 x 2048 x 1 x 1 | F16 |
| 526 | blk.43.attn_q_norm.weight | Block 43 Attn_Q_Norm (W) | ( 128) 128 | 128 x 1 x 1 x 1 | F32 |
| 527 | blk.43.attn_q.weight | Block 43 Attention Query (W) | ( ~8M) 8388608 | 2048 x 4096 x 1 x 1 | F16 |
| 528 | blk.43.attn_v.weight | Block 43 Attention Value (W) | ( ~1M) 1048576 | 2048 x 512 x 1 x 1 | F16 |
- Total elements in blk.43: (~623M) 623120640
- Percentage of total elements: 2.04%
### Block 44 Tensor Group : ~623M Elements
| T_ID | Tensor Layer Name | Human Friendly Tensor Layer Name | Elements | Shape | Type |
|-----:|:----------------------------|:-------------------------------------------------------------------------------------------|:------------------|:----------------------|:-----|
| 529 | blk.44.ffn_gate_inp.weight | Block 44 Expert-Routing Layer For The Feed-Forward Network In Mixture Of Expert Models (W) | (~262K) 262144 | 2048 x 128 x 1 x 1 | F32 |
| 530 | blk.44.attn_k_norm.weight | Block 44 Attn_K_Norm (W) | ( 128) 128 | 128 x 1 x 1 x 1 | F32 |
| 531 | blk.44.attn_k.weight | Block 44 Attention Key (W) | ( ~1M) 1048576 | 2048 x 512 x 1 x 1 | F16 |
| 532 | blk.44.attn_output.weight | Block 44 Attention Output (W) | ( ~8M) 8388608 | 4096 x 2048 x 1 x 1 | F16 |
| 533 | blk.44.attn_q_norm.weight | Block 44 Attn_Q_Norm (W) | ( 128) 128 | 128 x 1 x 1 x 1 | F32 |
| 534 | blk.44.attn_q.weight | Block 44 Attention Query (W) | ( ~8M) 8388608 | 2048 x 4096 x 1 x 1 | F16 |
| 535 | blk.44.attn_v.weight | Block 44 Attention Value (W) | ( ~1M) 1048576 | 2048 x 512 x 1 x 1 | F16 |
| 536 | blk.44.attn_norm.weight | Block 44 Attention Normalization (W) | ( ~2K) 2048 | 2048 x 1 x 1 x 1 | F32 |
| 537 | blk.44.ffn_down_exps.weight | Block 44 Ffn_Down_Exps (W) | (~201M) 201326592 | 768 x 2048 x 128 x 1 | F16 |
| 538 | blk.44.ffn_gate_exps.weight | Block 44 Ffn_Gate_Exps (W) | (~201M) 201326592 | 2048 x 768 x 128 x 1 | F16 |
| 539 | blk.44.ffn_up_exps.weight | Block 44 Ffn_Up_Exps (W) | (~201M) 201326592 | 2048 x 768 x 128 x 1 | F16 |
| 540 | blk.44.ffn_norm.weight | Block 44 Feed-Forward Network Normalization (W) | ( ~2K) 2048 | 2048 x 1 x 1 x 1 | F32 |
- Total elements in blk.44: (~623M) 623120640
- Percentage of total elements: 2.04%
### Block 45 Tensor Group : ~623M Elements
| T_ID | Tensor Layer Name | Human Friendly Tensor Layer Name | Elements | Shape | Type |
|-----:|:----------------------------|:-------------------------------------------------------------------------------------------|:------------------|:----------------------|:-----|
| 541 | blk.45.attn_norm.weight | Block 45 Attention Normalization (W) | ( ~2K) 2048 | 2048 x 1 x 1 x 1 | F32 |
| 542 | blk.45.ffn_down_exps.weight | Block 45 Ffn_Down_Exps (W) | (~201M) 201326592 | 768 x 2048 x 128 x 1 | F16 |
| 543 | blk.45.ffn_gate_exps.weight | Block 45 Ffn_Gate_Exps (W) | (~201M) 201326592 | 2048 x 768 x 128 x 1 | F16 |
| 544 | blk.45.ffn_up_exps.weight | Block 45 Ffn_Up_Exps (W) | (~201M) 201326592 | 2048 x 768 x 128 x 1 | F16 |
| 545 | blk.45.ffn_gate_inp.weight | Block 45 Expert-Routing Layer For The Feed-Forward Network In Mixture Of Expert Models (W) | (~262K) 262144 | 2048 x 128 x 1 x 1 | F32 |
| 546 | blk.45.ffn_norm.weight | Block 45 Feed-Forward Network Normalization (W) | ( ~2K) 2048 | 2048 x 1 x 1 x 1 | F32 |
| 547 | blk.45.attn_k_norm.weight | Block 45 Attn_K_Norm (W) | ( 128) 128 | 128 x 1 x 1 x 1 | F32 |
| 548 | blk.45.attn_k.weight | Block 45 Attention Key (W) | ( ~1M) 1048576 | 2048 x 512 x 1 x 1 | F16 |
| 549 | blk.45.attn_output.weight | Block 45 Attention Output (W) | ( ~8M) 8388608 | 4096 x 2048 x 1 x 1 | F16 |
| 550 | blk.45.attn_q_norm.weight | Block 45 Attn_Q_Norm (W) | ( 128) 128 | 128 x 1 x 1 x 1 | F32 |
| 551 | blk.45.attn_q.weight | Block 45 Attention Query (W) | ( ~8M) 8388608 | 2048 x 4096 x 1 x 1 | F16 |
| 552 | blk.45.attn_v.weight | Block 45 Attention Value (W) | ( ~1M) 1048576 | 2048 x 512 x 1 x 1 | F16 |
- Total elements in blk.45: (~623M) 623120640
- Percentage of total elements: 2.04%
### Block 46 Tensor Group : ~623M Elements
| T_ID | Tensor Layer Name | Human Friendly Tensor Layer Name | Elements | Shape | Type |
|-----:|:----------------------------|:-------------------------------------------------------------------------------------------|:------------------|:----------------------|:-----|
| 553 | blk.46.attn_norm.weight | Block 46 Attention Normalization (W) | ( ~2K) 2048 | 2048 x 1 x 1 x 1 | F32 |
| 554 | blk.46.ffn_down_exps.weight | Block 46 Ffn_Down_Exps (W) | (~201M) 201326592 | 768 x 2048 x 128 x 1 | F16 |
| 555 | blk.46.ffn_gate_exps.weight | Block 46 Ffn_Gate_Exps (W) | (~201M) 201326592 | 2048 x 768 x 128 x 1 | F16 |
| 556 | blk.46.ffn_up_exps.weight | Block 46 Ffn_Up_Exps (W) | (~201M) 201326592 | 2048 x 768 x 128 x 1 | F16 |
| 557 | blk.46.ffn_gate_inp.weight | Block 46 Expert-Routing Layer For The Feed-Forward Network In Mixture Of Expert Models (W) | (~262K) 262144 | 2048 x 128 x 1 x 1 | F32 |
| 558 | blk.46.ffn_norm.weight | Block 46 Feed-Forward Network Normalization (W) | ( ~2K) 2048 | 2048 x 1 x 1 x 1 | F32 |
| 559 | blk.46.attn_k_norm.weight | Block 46 Attn_K_Norm (W) | ( 128) 128 | 128 x 1 x 1 x 1 | F32 |
| 560 | blk.46.attn_k.weight | Block 46 Attention Key (W) | ( ~1M) 1048576 | 2048 x 512 x 1 x 1 | F16 |
| 561 | blk.46.attn_output.weight | Block 46 Attention Output (W) | ( ~8M) 8388608 | 4096 x 2048 x 1 x 1 | F16 |
| 562 | blk.46.attn_q_norm.weight | Block 46 Attn_Q_Norm (W) | ( 128) 128 | 128 x 1 x 1 x 1 | F32 |
| 563 | blk.46.attn_q.weight | Block 46 Attention Query (W) | ( ~8M) 8388608 | 2048 x 4096 x 1 x 1 | F16 |
| 564 | blk.46.attn_v.weight | Block 46 Attention Value (W) | ( ~1M) 1048576 | 2048 x 512 x 1 x 1 | F16 |
- Total elements in blk.46: (~623M) 623120640
- Percentage of total elements: 2.04%
### Block 47 Tensor Group : ~623M Elements
| T_ID | Tensor Layer Name | Human Friendly Tensor Layer Name | Elements | Shape | Type |
|-----:|:----------------------------|:-------------------------------------------------------------------------------------------|:------------------|:----------------------|:-----|
| 565 | blk.47.ffn_gate_inp.weight | Block 47 Expert-Routing Layer For The Feed-Forward Network In Mixture Of Expert Models (W) | (~262K) 262144 | 2048 x 128 x 1 x 1 | F32 |
| 566 | blk.47.attn_k_norm.weight | Block 47 Attn_K_Norm (W) | ( 128) 128 | 128 x 1 x 1 x 1 | F32 |
| 567 | blk.47.attn_k.weight | Block 47 Attention Key (W) | ( ~1M) 1048576 | 2048 x 512 x 1 x 1 | F16 |
| 568 | blk.47.attn_output.weight | Block 47 Attention Output (W) | ( ~8M) 8388608 | 4096 x 2048 x 1 x 1 | F16 |
| 569 | blk.47.attn_q_norm.weight | Block 47 Attn_Q_Norm (W) | ( 128) 128 | 128 x 1 x 1 x 1 | F32 |
| 570 | blk.47.attn_q.weight | Block 47 Attention Query (W) | ( ~8M) 8388608 | 2048 x 4096 x 1 x 1 | F16 |
| 571 | blk.47.attn_v.weight | Block 47 Attention Value (W) | ( ~1M) 1048576 | 2048 x 512 x 1 x 1 | F16 |
| 573 | blk.47.attn_norm.weight | Block 47 Attention Normalization (W) | ( ~2K) 2048 | 2048 x 1 x 1 x 1 | F32 |
| 574 | blk.47.ffn_down_exps.weight | Block 47 Ffn_Down_Exps (W) | (~201M) 201326592 | 768 x 2048 x 128 x 1 | F16 |
| 575 | blk.47.ffn_gate_exps.weight | Block 47 Ffn_Gate_Exps (W) | (~201M) 201326592 | 2048 x 768 x 128 x 1 | F16 |
| 576 | blk.47.ffn_up_exps.weight | Block 47 Ffn_Up_Exps (W) | (~201M) 201326592 | 2048 x 768 x 128 x 1 | F16 |
| 577 | blk.47.ffn_norm.weight | Block 47 Feed-Forward Network Normalization (W) | ( ~2K) 2048 | 2048 x 1 x 1 x 1 | F32 |
- Total elements in blk.47: (~623M) 623120640
- Percentage of total elements: 2.04%