1248 lines
109 KiB
Markdown
1248 lines
109 KiB
Markdown
# granite-4.1-8b-WIP/granite-4.1-8b-Q3_K.gguf - GGUF Internal File Dump
|
|
|
|
- Endian: LITTLE endian
|
|
|
|
## Key Value Metadata Store
|
|
|
|
There are 42 key-value pairs in this file
|
|
|
|
| POS | TYPE | Count | Key | Value |
|
|
|----:|:---------|-------:|:-----------------------------------------|:--------------------------------------------------------------------|
|
|
| 1 | UINT32 | 1 | GGUF.version | 3 |
|
|
| 2 | UINT64 | 1 | GGUF.tensor_count | 363 |
|
|
| 3 | UINT64 | 1 | GGUF.kv_count | 39 |
|
|
| 4 | STRING | 1 | general.architecture | `granite` |
|
|
| 5 | STRING | 1 | general.type | `model` |
|
|
| 6 | STRING | 1 | general.name | `Granite 4.1 8b` |
|
|
| 7 | STRING | 1 | general.basename | `granite-4.1` |
|
|
| 8 | STRING | 1 | general.size_label | `8B` |
|
|
| 9 | STRING | 1 | general.license | `apache-2.0` |
|
|
| 10 | [STRING] | 2 | general.tags | [ `language`, `granite-4.1` ] |
|
|
| 11 | UINT32 | 1 | granite.block_count | 40 |
|
|
| 12 | UINT32 | 1 | granite.context_length | 131072 |
|
|
| 13 | UINT32 | 1 | granite.embedding_length | 4096 |
|
|
| 14 | UINT32 | 1 | granite.feed_forward_length | 12800 |
|
|
| 15 | UINT32 | 1 | granite.attention.head_count | 32 |
|
|
| 16 | UINT32 | 1 | granite.attention.head_count_kv | 8 |
|
|
| 17 | FLOAT32 | 1 | granite.rope.freq_base | 10000000.0 |
|
|
| 18 | FLOAT32 | 1 | granite.attention.layer_norm_rms_epsilon | 1e-05 |
|
|
| 19 | UINT32 | 1 | granite.vocab_size | 100352 |
|
|
| 20 | UINT32 | 1 | granite.rope.dimension_count | 128 |
|
|
| 21 | FLOAT32 | 1 | granite.attention.scale | 0.0078125 |
|
|
| 22 | FLOAT32 | 1 | granite.embedding_scale | 12.0 |
|
|
| 23 | FLOAT32 | 1 | granite.residual_scale | 0.22 |
|
|
| 24 | FLOAT32 | 1 | granite.logit_scale | 16.0 |
|
|
| 25 | STRING | 1 | tokenizer.ggml.model | `gpt2` |
|
|
| 26 | STRING | 1 | tokenizer.ggml.pre | `granite-docling` |
|
|
| 27 | [STRING] | 100352 | tokenizer.ggml.tokens | [ `!`, `"`, `#`, `$`, `%`, ... ] |
|
|
| 28 | [INT32] | 100352 | tokenizer.ggml.token_type | [ 1, 1, 1, 1, 1, 1, 1, ... ] |
|
|
| 29 | [STRING] | 100000 | tokenizer.ggml.merges | [ `Ġ Ġ`, `ĠĠ ĠĠ`, `i n`, `Ġ t`, `ĠĠĠĠ ĠĠĠĠ`, ... ] |
|
|
| 30 | UINT32 | 1 | tokenizer.ggml.bos_token_id | 100257 |
|
|
| 31 | UINT32 | 1 | tokenizer.ggml.eos_token_id | 100257 |
|
|
| 32 | UINT32 | 1 | tokenizer.ggml.unknown_token_id | 100269 |
|
|
| 33 | UINT32 | 1 | tokenizer.ggml.padding_token_id | 100256 |
|
|
| 34 | BOOL | 1 | tokenizer.ggml.add_bos_token | False |
|
|
| 35 | STRING | 1 | tokenizer.chat_template | `{%- set tools_system_message_p`...`end_of_role|>' }}{%- endif %}` |
|
|
| 36 | BOOL | 1 | tokenizer.ggml.add_space_prefix | False |
|
|
| 37 | UINT32 | 1 | general.quantization_version | 2 |
|
|
| 38 | UINT32 | 1 | general.file_type | 30 |
|
|
| 39 | STRING | 1 | quantize.imatrix.file | `imatrix/imatrix-granite-4.1-8b-medium.gguf` |
|
|
| 40 | STRING | 1 | quantize.imatrix.dataset | `../../datasets/imatrix/combined_all_medium.txt` |
|
|
| 41 | UINT32 | 1 | quantize.imatrix.entries_count | 280 |
|
|
| 42 | UINT32 | 1 | quantize.imatrix.chunks_count | 3601 |
|
|
|
|
## Tensors Overview ~9B Elements
|
|
|
|
Total number of elements in all tensors: 8791592960 Elements
|
|
|
|
- [granite-4.1-8b-WIP/granite-4.1-8b-Q3\_K.gguf - GGUF Internal File Dump](#granite-41-8b-wipgranite-41-8b-q3_kgguf---gguf-internal-file-dump)
|
|
- [Key Value Metadata Store](#key-value-metadata-store)
|
|
- [Tensors Overview ~9B Elements](#tensors-overview-9b-elements)
|
|
- [Tensor Data Offset](#tensor-data-offset)
|
|
- [Base Tensor Group : ~822M Elements](#base-tensor-group--822m-elements)
|
|
- [Block 0 Tensor Group : ~199M Elements](#block-0-tensor-group--199m-elements)
|
|
- [Block 1 Tensor Group : ~199M Elements](#block-1-tensor-group--199m-elements)
|
|
- [Block 2 Tensor Group : ~199M Elements](#block-2-tensor-group--199m-elements)
|
|
- [Block 3 Tensor Group : ~199M Elements](#block-3-tensor-group--199m-elements)
|
|
- [Block 4 Tensor Group : ~199M Elements](#block-4-tensor-group--199m-elements)
|
|
- [Block 5 Tensor Group : ~199M Elements](#block-5-tensor-group--199m-elements)
|
|
- [Block 6 Tensor Group : ~199M Elements](#block-6-tensor-group--199m-elements)
|
|
- [Block 7 Tensor Group : ~199M Elements](#block-7-tensor-group--199m-elements)
|
|
- [Block 8 Tensor Group : ~199M Elements](#block-8-tensor-group--199m-elements)
|
|
- [Block 9 Tensor Group : ~199M Elements](#block-9-tensor-group--199m-elements)
|
|
- [Block 10 Tensor Group : ~199M Elements](#block-10-tensor-group--199m-elements)
|
|
- [Block 11 Tensor Group : ~199M Elements](#block-11-tensor-group--199m-elements)
|
|
- [Block 12 Tensor Group : ~199M Elements](#block-12-tensor-group--199m-elements)
|
|
- [Block 13 Tensor Group : ~199M Elements](#block-13-tensor-group--199m-elements)
|
|
- [Block 14 Tensor Group : ~199M Elements](#block-14-tensor-group--199m-elements)
|
|
- [Block 15 Tensor Group : ~199M Elements](#block-15-tensor-group--199m-elements)
|
|
- [Block 16 Tensor Group : ~199M Elements](#block-16-tensor-group--199m-elements)
|
|
- [Block 17 Tensor Group : ~199M Elements](#block-17-tensor-group--199m-elements)
|
|
- [Block 18 Tensor Group : ~199M Elements](#block-18-tensor-group--199m-elements)
|
|
- [Block 19 Tensor Group : ~199M Elements](#block-19-tensor-group--199m-elements)
|
|
- [Block 20 Tensor Group : ~199M Elements](#block-20-tensor-group--199m-elements)
|
|
- [Block 21 Tensor Group : ~199M Elements](#block-21-tensor-group--199m-elements)
|
|
- [Block 22 Tensor Group : ~199M Elements](#block-22-tensor-group--199m-elements)
|
|
- [Block 23 Tensor Group : ~199M Elements](#block-23-tensor-group--199m-elements)
|
|
- [Block 24 Tensor Group : ~199M Elements](#block-24-tensor-group--199m-elements)
|
|
- [Block 25 Tensor Group : ~199M Elements](#block-25-tensor-group--199m-elements)
|
|
- [Block 26 Tensor Group : ~199M Elements](#block-26-tensor-group--199m-elements)
|
|
- [Block 27 Tensor Group : ~199M Elements](#block-27-tensor-group--199m-elements)
|
|
- [Block 28 Tensor Group : ~199M Elements](#block-28-tensor-group--199m-elements)
|
|
- [Block 29 Tensor Group : ~199M Elements](#block-29-tensor-group--199m-elements)
|
|
- [Block 30 Tensor Group : ~199M Elements](#block-30-tensor-group--199m-elements)
|
|
- [Block 31 Tensor Group : ~199M Elements](#block-31-tensor-group--199m-elements)
|
|
- [Block 32 Tensor Group : ~199M Elements](#block-32-tensor-group--199m-elements)
|
|
- [Block 33 Tensor Group : ~199M Elements](#block-33-tensor-group--199m-elements)
|
|
- [Block 34 Tensor Group : ~199M Elements](#block-34-tensor-group--199m-elements)
|
|
- [Block 35 Tensor Group : ~199M Elements](#block-35-tensor-group--199m-elements)
|
|
- [Block 36 Tensor Group : ~199M Elements](#block-36-tensor-group--199m-elements)
|
|
- [Block 37 Tensor Group : ~199M Elements](#block-37-tensor-group--199m-elements)
|
|
- [Block 38 Tensor Group : ~199M Elements](#block-38-tensor-group--199m-elements)
|
|
- [Block 39 Tensor Group : ~199M Elements](#block-39-tensor-group--199m-elements)
|
|
|
|
### Tensor Data Offset
|
|
|
|
This table contains the offset and data segment relative to start of file
|
|
|
|
| T_ID | Tensor Layer Name | Data Offset (B) | Data Size (B) |
|
|
|-----:|:--------------------------|-----------------:|-----------------:|
|
|
| 0 | output.weight | 0x367400 | 0xdc80000 |
|
|
| 1 | output_norm.weight | 0xdfe7400 | 0x4000 |
|
|
| 2 | token_embd.weight | 0xdfeb400 | 0xa870000 |
|
|
| 3 | blk.0.attn_k.weight | 0x1885b400 | 0x128000 |
|
|
| 4 | blk.0.attn_norm.weight | 0x18983400 | 0x4000 |
|
|
| 5 | blk.0.attn_output.weight | 0x18987400 | 0x620000 |
|
|
| 6 | blk.0.attn_q.weight | 0x18fa7400 | 0x4a0000 |
|
|
| 7 | blk.0.attn_v.weight | 0x19447400 | 0x188000 |
|
|
| 8 | blk.0.ffn_down.weight | 0x195cf400 | 0x1068000 |
|
|
| 9 | blk.0.ffn_gate.weight | 0x1a637400 | 0xce4000 |
|
|
| 10 | blk.0.ffn_norm.weight | 0x1b31b400 | 0x4000 |
|
|
| 11 | blk.0.ffn_up.weight | 0x1b31f400 | 0x1324000 |
|
|
| 12 | blk.1.attn_k.weight | 0x1c643400 | 0x188000 |
|
|
| 13 | blk.1.attn_norm.weight | 0x1c7cb400 | 0x4000 |
|
|
| 14 | blk.1.attn_output.weight | 0x1c7cf400 | 0x880000 |
|
|
| 15 | blk.1.attn_q.weight | 0x1d04f400 | 0x6e0000 |
|
|
| 16 | blk.1.attn_v.weight | 0x1d72f400 | 0x240000 |
|
|
| 17 | blk.1.ffn_down.weight | 0x1d96f400 | 0x157c000 |
|
|
| 18 | blk.1.ffn_gate.weight | 0x1eeeb400 | 0x1324000 |
|
|
| 19 | blk.1.ffn_norm.weight | 0x2020f400 | 0x4000 |
|
|
| 20 | blk.1.ffn_up.weight | 0x20213400 | 0x1a90000 |
|
|
| 21 | blk.2.attn_k.weight | 0x21ca3400 | 0x1b8000 |
|
|
| 22 | blk.2.attn_norm.weight | 0x21e5b400 | 0x4000 |
|
|
| 23 | blk.2.attn_output.weight | 0x21e5f400 | 0x880000 |
|
|
| 24 | blk.2.attn_q.weight | 0x226df400 | 0x6e0000 |
|
|
| 25 | blk.2.attn_v.weight | 0x22dbf400 | 0x220000 |
|
|
| 26 | blk.2.ffn_down.weight | 0x22fdf400 | 0x157c000 |
|
|
| 27 | blk.2.ffn_gate.weight | 0x2455b400 | 0x1324000 |
|
|
| 28 | blk.2.ffn_norm.weight | 0x2587f400 | 0x4000 |
|
|
| 29 | blk.2.ffn_up.weight | 0x25883400 | 0x1a90000 |
|
|
| 30 | blk.3.attn_k.weight | 0x27313400 | 0x188000 |
|
|
| 31 | blk.3.attn_norm.weight | 0x2749b400 | 0x4000 |
|
|
| 32 | blk.3.attn_output.weight | 0x2749f400 | 0x880000 |
|
|
| 33 | blk.3.attn_q.weight | 0x27d1f400 | 0x6e0000 |
|
|
| 34 | blk.3.attn_v.weight | 0x283ff400 | 0x240000 |
|
|
| 35 | blk.3.ffn_down.weight | 0x2863f400 | 0x1324000 |
|
|
| 36 | blk.3.ffn_gate.weight | 0x29963400 | 0x157c000 |
|
|
| 37 | blk.3.ffn_norm.weight | 0x2aedf400 | 0x4000 |
|
|
| 38 | blk.3.ffn_up.weight | 0x2aee3400 | 0x157c000 |
|
|
| 39 | blk.4.attn_k.weight | 0x2c45f400 | 0x1b8000 |
|
|
| 40 | blk.4.attn_norm.weight | 0x2c617400 | 0x4000 |
|
|
| 41 | blk.4.attn_output.weight | 0x2c61b400 | 0x880000 |
|
|
| 42 | blk.4.attn_q.weight | 0x2ce9b400 | 0x6e0000 |
|
|
| 43 | blk.4.attn_v.weight | 0x2d57b400 | 0x240000 |
|
|
| 44 | blk.4.ffn_down.weight | 0x2d7bb400 | 0x157c000 |
|
|
| 45 | blk.4.ffn_gate.weight | 0x2ed37400 | 0x157c000 |
|
|
| 46 | blk.4.ffn_norm.weight | 0x302b3400 | 0x4000 |
|
|
| 47 | blk.4.ffn_up.weight | 0x302b7400 | 0x157c000 |
|
|
| 48 | blk.5.attn_k.weight | 0x31833400 | 0x1b8000 |
|
|
| 49 | blk.5.attn_norm.weight | 0x319eb400 | 0x4000 |
|
|
| 50 | blk.5.attn_output.weight | 0x319ef400 | 0x880000 |
|
|
| 51 | blk.5.attn_q.weight | 0x3226f400 | 0x6e0000 |
|
|
| 52 | blk.5.attn_v.weight | 0x3294f400 | 0x240000 |
|
|
| 53 | blk.5.ffn_down.weight | 0x32b8f400 | 0x1324000 |
|
|
| 54 | blk.5.ffn_gate.weight | 0x33eb3400 | 0x157c000 |
|
|
| 55 | blk.5.ffn_norm.weight | 0x3542f400 | 0x4000 |
|
|
| 56 | blk.5.ffn_up.weight | 0x35433400 | 0x157c000 |
|
|
| 57 | blk.6.attn_k.weight | 0x369af400 | 0x1b8000 |
|
|
| 58 | blk.6.attn_norm.weight | 0x36b67400 | 0x4000 |
|
|
| 59 | blk.6.attn_output.weight | 0x36b6b400 | 0x880000 |
|
|
| 60 | blk.6.attn_q.weight | 0x373eb400 | 0x6e0000 |
|
|
| 61 | blk.6.attn_v.weight | 0x37acb400 | 0x240000 |
|
|
| 62 | blk.6.ffn_down.weight | 0x37d0b400 | 0x157c000 |
|
|
| 63 | blk.6.ffn_gate.weight | 0x39287400 | 0x1324000 |
|
|
| 64 | blk.6.ffn_norm.weight | 0x3a5ab400 | 0x4000 |
|
|
| 65 | blk.6.ffn_up.weight | 0x3a5af400 | 0x157c000 |
|
|
| 66 | blk.7.attn_k.weight | 0x3bb2b400 | 0x1b8000 |
|
|
| 67 | blk.7.attn_norm.weight | 0x3bce3400 | 0x4000 |
|
|
| 68 | blk.7.attn_output.weight | 0x3bce7400 | 0x880000 |
|
|
| 69 | blk.7.attn_q.weight | 0x3c567400 | 0x6e0000 |
|
|
| 70 | blk.7.attn_v.weight | 0x3cc47400 | 0x240000 |
|
|
| 71 | blk.7.ffn_down.weight | 0x3ce87400 | 0x157c000 |
|
|
| 72 | blk.7.ffn_gate.weight | 0x3e403400 | 0x1324000 |
|
|
| 73 | blk.7.ffn_norm.weight | 0x3f727400 | 0x4000 |
|
|
| 74 | blk.7.ffn_up.weight | 0x3f72b400 | 0x157c000 |
|
|
| 75 | blk.8.attn_k.weight | 0x40ca7400 | 0x1b8000 |
|
|
| 76 | blk.8.attn_norm.weight | 0x40e5f400 | 0x4000 |
|
|
| 77 | blk.8.attn_output.weight | 0x40e63400 | 0x880000 |
|
|
| 78 | blk.8.attn_q.weight | 0x416e3400 | 0x6e0000 |
|
|
| 79 | blk.8.attn_v.weight | 0x41dc3400 | 0x240000 |
|
|
| 80 | blk.8.ffn_down.weight | 0x42003400 | 0x157c000 |
|
|
| 81 | blk.8.ffn_gate.weight | 0x4357f400 | 0x1324000 |
|
|
| 82 | blk.8.ffn_norm.weight | 0x448a3400 | 0x4000 |
|
|
| 83 | blk.8.ffn_up.weight | 0x448a7400 | 0x157c000 |
|
|
| 84 | blk.9.attn_k.weight | 0x45e23400 | 0x1b8000 |
|
|
| 85 | blk.9.attn_norm.weight | 0x45fdb400 | 0x4000 |
|
|
| 86 | blk.9.attn_output.weight | 0x45fdf400 | 0x880000 |
|
|
| 87 | blk.9.attn_q.weight | 0x4685f400 | 0x6e0000 |
|
|
| 88 | blk.9.attn_v.weight | 0x46f3f400 | 0x240000 |
|
|
| 89 | blk.9.ffn_down.weight | 0x4717f400 | 0x157c000 |
|
|
| 90 | blk.9.ffn_gate.weight | 0x486fb400 | 0x1324000 |
|
|
| 91 | blk.9.ffn_norm.weight | 0x49a1f400 | 0x4000 |
|
|
| 92 | blk.9.ffn_up.weight | 0x49a23400 | 0x157c000 |
|
|
| 93 | blk.10.attn_k.weight | 0x4af9f400 | 0x1b8000 |
|
|
| 94 | blk.10.attn_norm.weight | 0x4b157400 | 0x4000 |
|
|
| 95 | blk.10.attn_output.weight | 0x4b15b400 | 0x880000 |
|
|
| 96 | blk.10.attn_q.weight | 0x4b9db400 | 0x6e0000 |
|
|
| 97 | blk.10.attn_v.weight | 0x4c0bb400 | 0x240000 |
|
|
| 98 | blk.10.ffn_down.weight | 0x4c2fb400 | 0x157c000 |
|
|
| 99 | blk.10.ffn_gate.weight | 0x4d877400 | 0x1324000 |
|
|
| 100 | blk.10.ffn_norm.weight | 0x4eb9b400 | 0x4000 |
|
|
| 101 | blk.10.ffn_up.weight | 0x4eb9f400 | 0x157c000 |
|
|
| 102 | blk.11.attn_k.weight | 0x5011b400 | 0x1b8000 |
|
|
| 103 | blk.11.attn_norm.weight | 0x502d3400 | 0x4000 |
|
|
| 104 | blk.11.attn_output.weight | 0x502d7400 | 0x880000 |
|
|
| 105 | blk.11.attn_q.weight | 0x50b57400 | 0x6e0000 |
|
|
| 106 | blk.11.attn_v.weight | 0x51237400 | 0x220000 |
|
|
| 107 | blk.11.ffn_down.weight | 0x51457400 | 0x157c000 |
|
|
| 108 | blk.11.ffn_gate.weight | 0x529d3400 | 0x1324000 |
|
|
| 109 | blk.11.ffn_norm.weight | 0x53cf7400 | 0x4000 |
|
|
| 110 | blk.11.ffn_up.weight | 0x53cfb400 | 0x157c000 |
|
|
| 111 | blk.12.attn_k.weight | 0x55277400 | 0x1b8000 |
|
|
| 112 | blk.12.attn_norm.weight | 0x5542f400 | 0x4000 |
|
|
| 113 | blk.12.attn_output.weight | 0x55433400 | 0x880000 |
|
|
| 114 | blk.12.attn_q.weight | 0x55cb3400 | 0x6e0000 |
|
|
| 115 | blk.12.attn_v.weight | 0x56393400 | 0x240000 |
|
|
| 116 | blk.12.ffn_down.weight | 0x565d3400 | 0x157c000 |
|
|
| 117 | blk.12.ffn_gate.weight | 0x57b4f400 | 0x1324000 |
|
|
| 118 | blk.12.ffn_norm.weight | 0x58e73400 | 0x4000 |
|
|
| 119 | blk.12.ffn_up.weight | 0x58e77400 | 0x157c000 |
|
|
| 120 | blk.13.attn_k.weight | 0x5a3f3400 | 0x1b8000 |
|
|
| 121 | blk.13.attn_norm.weight | 0x5a5ab400 | 0x4000 |
|
|
| 122 | blk.13.attn_output.weight | 0x5a5af400 | 0x880000 |
|
|
| 123 | blk.13.attn_q.weight | 0x5ae2f400 | 0x6e0000 |
|
|
| 124 | blk.13.attn_v.weight | 0x5b50f400 | 0x240000 |
|
|
| 125 | blk.13.ffn_down.weight | 0x5b74f400 | 0x157c000 |
|
|
| 126 | blk.13.ffn_gate.weight | 0x5cccb400 | 0x1324000 |
|
|
| 127 | blk.13.ffn_norm.weight | 0x5dfef400 | 0x4000 |
|
|
| 128 | blk.13.ffn_up.weight | 0x5dff3400 | 0x157c000 |
|
|
| 129 | blk.14.attn_k.weight | 0x5f56f400 | 0x1b8000 |
|
|
| 130 | blk.14.attn_norm.weight | 0x5f727400 | 0x4000 |
|
|
| 131 | blk.14.attn_output.weight | 0x5f72b400 | 0x880000 |
|
|
| 132 | blk.14.attn_q.weight | 0x5ffab400 | 0x6e0000 |
|
|
| 133 | blk.14.attn_v.weight | 0x6068b400 | 0x240000 |
|
|
| 134 | blk.14.ffn_down.weight | 0x608cb400 | 0x157c000 |
|
|
| 135 | blk.14.ffn_gate.weight | 0x61e47400 | 0x1324000 |
|
|
| 136 | blk.14.ffn_norm.weight | 0x6316b400 | 0x4000 |
|
|
| 137 | blk.14.ffn_up.weight | 0x6316f400 | 0x157c000 |
|
|
| 138 | blk.15.attn_k.weight | 0x646eb400 | 0x1b8000 |
|
|
| 139 | blk.15.attn_norm.weight | 0x648a3400 | 0x4000 |
|
|
| 140 | blk.15.attn_output.weight | 0x648a7400 | 0x880000 |
|
|
| 141 | blk.15.attn_q.weight | 0x65127400 | 0x6e0000 |
|
|
| 142 | blk.15.attn_v.weight | 0x65807400 | 0x240000 |
|
|
| 143 | blk.15.ffn_down.weight | 0x65a47400 | 0x157c000 |
|
|
| 144 | blk.15.ffn_gate.weight | 0x66fc3400 | 0x157c000 |
|
|
| 145 | blk.15.ffn_norm.weight | 0x6853f400 | 0x4000 |
|
|
| 146 | blk.15.ffn_up.weight | 0x68543400 | 0x157c000 |
|
|
| 147 | blk.16.attn_k.weight | 0x69abf400 | 0x1b8000 |
|
|
| 148 | blk.16.attn_norm.weight | 0x69c77400 | 0x4000 |
|
|
| 149 | blk.16.attn_output.weight | 0x69c7b400 | 0x880000 |
|
|
| 150 | blk.16.attn_q.weight | 0x6a4fb400 | 0x6e0000 |
|
|
| 151 | blk.16.attn_v.weight | 0x6abdb400 | 0x240000 |
|
|
| 152 | blk.16.ffn_down.weight | 0x6ae1b400 | 0x157c000 |
|
|
| 153 | blk.16.ffn_gate.weight | 0x6c397400 | 0x1324000 |
|
|
| 154 | blk.16.ffn_norm.weight | 0x6d6bb400 | 0x4000 |
|
|
| 155 | blk.16.ffn_up.weight | 0x6d6bf400 | 0x157c000 |
|
|
| 156 | blk.17.attn_k.weight | 0x6ec3b400 | 0x1b8000 |
|
|
| 157 | blk.17.attn_norm.weight | 0x6edf3400 | 0x4000 |
|
|
| 158 | blk.17.attn_output.weight | 0x6edf7400 | 0x880000 |
|
|
| 159 | blk.17.attn_q.weight | 0x6f677400 | 0x6e0000 |
|
|
| 160 | blk.17.attn_v.weight | 0x6fd57400 | 0x240000 |
|
|
| 161 | blk.17.ffn_down.weight | 0x6ff97400 | 0x157c000 |
|
|
| 162 | blk.17.ffn_gate.weight | 0x71513400 | 0x1324000 |
|
|
| 163 | blk.17.ffn_norm.weight | 0x72837400 | 0x4000 |
|
|
| 164 | blk.17.ffn_up.weight | 0x7283b400 | 0x157c000 |
|
|
| 165 | blk.18.attn_k.weight | 0x73db7400 | 0x1b8000 |
|
|
| 166 | blk.18.attn_norm.weight | 0x73f6f400 | 0x4000 |
|
|
| 167 | blk.18.attn_output.weight | 0x73f73400 | 0x880000 |
|
|
| 168 | blk.18.attn_q.weight | 0x747f3400 | 0x6e0000 |
|
|
| 169 | blk.18.attn_v.weight | 0x74ed3400 | 0x240000 |
|
|
| 170 | blk.18.ffn_down.weight | 0x75113400 | 0x157c000 |
|
|
| 171 | blk.18.ffn_gate.weight | 0x7668f400 | 0x1324000 |
|
|
| 172 | blk.18.ffn_norm.weight | 0x779b3400 | 0x4000 |
|
|
| 173 | blk.18.ffn_up.weight | 0x779b7400 | 0x157c000 |
|
|
| 174 | blk.19.attn_k.weight | 0x78f33400 | 0x1b8000 |
|
|
| 175 | blk.19.attn_norm.weight | 0x790eb400 | 0x4000 |
|
|
| 176 | blk.19.attn_output.weight | 0x790ef400 | 0x880000 |
|
|
| 177 | blk.19.attn_q.weight | 0x7996f400 | 0x6e0000 |
|
|
| 178 | blk.19.attn_v.weight | 0x7a04f400 | 0x240000 |
|
|
| 179 | blk.19.ffn_down.weight | 0x7a28f400 | 0x157c000 |
|
|
| 180 | blk.19.ffn_gate.weight | 0x7b80b400 | 0x1324000 |
|
|
| 181 | blk.19.ffn_norm.weight | 0x7cb2f400 | 0x4000 |
|
|
| 182 | blk.19.ffn_up.weight | 0x7cb33400 | 0x157c000 |
|
|
| 183 | blk.20.attn_k.weight | 0x7e0af400 | 0x1b8000 |
|
|
| 184 | blk.20.attn_norm.weight | 0x7e267400 | 0x4000 |
|
|
| 185 | blk.20.attn_output.weight | 0x7e26b400 | 0x880000 |
|
|
| 186 | blk.20.attn_q.weight | 0x7eaeb400 | 0x6e0000 |
|
|
| 187 | blk.20.attn_v.weight | 0x7f1cb400 | 0x240000 |
|
|
| 188 | blk.20.ffn_down.weight | 0x7f40b400 | 0x157c000 |
|
|
| 189 | blk.20.ffn_gate.weight | 0x80987400 | 0x1324000 |
|
|
| 190 | blk.20.ffn_norm.weight | 0x81cab400 | 0x4000 |
|
|
| 191 | blk.20.ffn_up.weight | 0x81caf400 | 0x157c000 |
|
|
| 192 | blk.21.attn_k.weight | 0x8322b400 | 0x1b8000 |
|
|
| 193 | blk.21.attn_norm.weight | 0x833e3400 | 0x4000 |
|
|
| 194 | blk.21.attn_output.weight | 0x833e7400 | 0x880000 |
|
|
| 195 | blk.21.attn_q.weight | 0x83c67400 | 0x6e0000 |
|
|
| 196 | blk.21.attn_v.weight | 0x84347400 | 0x240000 |
|
|
| 197 | blk.21.ffn_down.weight | 0x84587400 | 0x157c000 |
|
|
| 198 | blk.21.ffn_gate.weight | 0x85b03400 | 0x1324000 |
|
|
| 199 | blk.21.ffn_norm.weight | 0x86e27400 | 0x4000 |
|
|
| 200 | blk.21.ffn_up.weight | 0x86e2b400 | 0x157c000 |
|
|
| 201 | blk.22.attn_k.weight | 0x883a7400 | 0x1b8000 |
|
|
| 202 | blk.22.attn_norm.weight | 0x8855f400 | 0x4000 |
|
|
| 203 | blk.22.attn_output.weight | 0x88563400 | 0x880000 |
|
|
| 204 | blk.22.attn_q.weight | 0x88de3400 | 0x6e0000 |
|
|
| 205 | blk.22.attn_v.weight | 0x894c3400 | 0x240000 |
|
|
| 206 | blk.22.ffn_down.weight | 0x89703400 | 0x157c000 |
|
|
| 207 | blk.22.ffn_gate.weight | 0x8ac7f400 | 0x1324000 |
|
|
| 208 | blk.22.ffn_norm.weight | 0x8bfa3400 | 0x4000 |
|
|
| 209 | blk.22.ffn_up.weight | 0x8bfa7400 | 0x157c000 |
|
|
| 210 | blk.23.attn_k.weight | 0x8d523400 | 0x1b8000 |
|
|
| 211 | blk.23.attn_norm.weight | 0x8d6db400 | 0x4000 |
|
|
| 212 | blk.23.attn_output.weight | 0x8d6df400 | 0x880000 |
|
|
| 213 | blk.23.attn_q.weight | 0x8df5f400 | 0x6e0000 |
|
|
| 214 | blk.23.attn_v.weight | 0x8e63f400 | 0x240000 |
|
|
| 215 | blk.23.ffn_down.weight | 0x8e87f400 | 0x157c000 |
|
|
| 216 | blk.23.ffn_gate.weight | 0x8fdfb400 | 0x1324000 |
|
|
| 217 | blk.23.ffn_norm.weight | 0x9111f400 | 0x4000 |
|
|
| 218 | blk.23.ffn_up.weight | 0x91123400 | 0x157c000 |
|
|
| 219 | blk.24.attn_k.weight | 0x9269f400 | 0x1b8000 |
|
|
| 220 | blk.24.attn_norm.weight | 0x92857400 | 0x4000 |
|
|
| 221 | blk.24.attn_output.weight | 0x9285b400 | 0x880000 |
|
|
| 222 | blk.24.attn_q.weight | 0x930db400 | 0x6e0000 |
|
|
| 223 | blk.24.attn_v.weight | 0x937bb400 | 0x240000 |
|
|
| 224 | blk.24.ffn_down.weight | 0x939fb400 | 0x157c000 |
|
|
| 225 | blk.24.ffn_gate.weight | 0x94f77400 | 0x1324000 |
|
|
| 226 | blk.24.ffn_norm.weight | 0x9629b400 | 0x4000 |
|
|
| 227 | blk.24.ffn_up.weight | 0x9629f400 | 0x157c000 |
|
|
| 228 | blk.25.attn_k.weight | 0x9781b400 | 0x1b8000 |
|
|
| 229 | blk.25.attn_norm.weight | 0x979d3400 | 0x4000 |
|
|
| 230 | blk.25.attn_output.weight | 0x979d7400 | 0x880000 |
|
|
| 231 | blk.25.attn_q.weight | 0x98257400 | 0x6e0000 |
|
|
| 232 | blk.25.attn_v.weight | 0x98937400 | 0x240000 |
|
|
| 233 | blk.25.ffn_down.weight | 0x98b77400 | 0x157c000 |
|
|
| 234 | blk.25.ffn_gate.weight | 0x9a0f3400 | 0x1324000 |
|
|
| 235 | blk.25.ffn_norm.weight | 0x9b417400 | 0x4000 |
|
|
| 236 | blk.25.ffn_up.weight | 0x9b41b400 | 0x157c000 |
|
|
| 237 | blk.26.attn_k.weight | 0x9c997400 | 0x1b8000 |
|
|
| 238 | blk.26.attn_norm.weight | 0x9cb4f400 | 0x4000 |
|
|
| 239 | blk.26.attn_output.weight | 0x9cb53400 | 0x880000 |
|
|
| 240 | blk.26.attn_q.weight | 0x9d3d3400 | 0x6e0000 |
|
|
| 241 | blk.26.attn_v.weight | 0x9dab3400 | 0x240000 |
|
|
| 242 | blk.26.ffn_down.weight | 0x9dcf3400 | 0x157c000 |
|
|
| 243 | blk.26.ffn_gate.weight | 0x9f26f400 | 0x1324000 |
|
|
| 244 | blk.26.ffn_norm.weight | 0xa0593400 | 0x4000 |
|
|
| 245 | blk.26.ffn_up.weight | 0xa0597400 | 0x157c000 |
|
|
| 246 | blk.27.attn_k.weight | 0xa1b13400 | 0x1b8000 |
|
|
| 247 | blk.27.attn_norm.weight | 0xa1ccb400 | 0x4000 |
|
|
| 248 | blk.27.attn_output.weight | 0xa1ccf400 | 0x880000 |
|
|
| 249 | blk.27.attn_q.weight | 0xa254f400 | 0x6e0000 |
|
|
| 250 | blk.27.attn_v.weight | 0xa2c2f400 | 0x240000 |
|
|
| 251 | blk.27.ffn_down.weight | 0xa2e6f400 | 0x157c000 |
|
|
| 252 | blk.27.ffn_gate.weight | 0xa43eb400 | 0x157c000 |
|
|
| 253 | blk.27.ffn_norm.weight | 0xa5967400 | 0x4000 |
|
|
| 254 | blk.27.ffn_up.weight | 0xa596b400 | 0x157c000 |
|
|
| 255 | blk.28.attn_k.weight | 0xa6ee7400 | 0x1b8000 |
|
|
| 256 | blk.28.attn_norm.weight | 0xa709f400 | 0x4000 |
|
|
| 257 | blk.28.attn_output.weight | 0xa70a3400 | 0x880000 |
|
|
| 258 | blk.28.attn_q.weight | 0xa7923400 | 0x6e0000 |
|
|
| 259 | blk.28.attn_v.weight | 0xa8003400 | 0x240000 |
|
|
| 260 | blk.28.ffn_down.weight | 0xa8243400 | 0x157c000 |
|
|
| 261 | blk.28.ffn_gate.weight | 0xa97bf400 | 0x157c000 |
|
|
| 262 | blk.28.ffn_norm.weight | 0xaad3b400 | 0x4000 |
|
|
| 263 | blk.28.ffn_up.weight | 0xaad3f400 | 0x157c000 |
|
|
| 264 | blk.29.attn_k.weight | 0xac2bb400 | 0x1b8000 |
|
|
| 265 | blk.29.attn_norm.weight | 0xac473400 | 0x4000 |
|
|
| 266 | blk.29.attn_output.weight | 0xac477400 | 0x880000 |
|
|
| 267 | blk.29.attn_q.weight | 0xaccf7400 | 0x6e0000 |
|
|
| 268 | blk.29.attn_v.weight | 0xad3d7400 | 0x240000 |
|
|
| 269 | blk.29.ffn_down.weight | 0xad617400 | 0x157c000 |
|
|
| 270 | blk.29.ffn_gate.weight | 0xaeb93400 | 0x157c000 |
|
|
| 271 | blk.29.ffn_norm.weight | 0xb010f400 | 0x4000 |
|
|
| 272 | blk.29.ffn_up.weight | 0xb0113400 | 0x157c000 |
|
|
| 273 | blk.30.attn_k.weight | 0xb168f400 | 0x1b8000 |
|
|
| 274 | blk.30.attn_norm.weight | 0xb1847400 | 0x4000 |
|
|
| 275 | blk.30.attn_output.weight | 0xb184b400 | 0x880000 |
|
|
| 276 | blk.30.attn_q.weight | 0xb20cb400 | 0x6e0000 |
|
|
| 277 | blk.30.attn_v.weight | 0xb27ab400 | 0x240000 |
|
|
| 278 | blk.30.ffn_down.weight | 0xb29eb400 | 0x157c000 |
|
|
| 279 | blk.30.ffn_gate.weight | 0xb3f67400 | 0x157c000 |
|
|
| 280 | blk.30.ffn_norm.weight | 0xb54e3400 | 0x4000 |
|
|
| 281 | blk.30.ffn_up.weight | 0xb54e7400 | 0x157c000 |
|
|
| 282 | blk.31.attn_k.weight | 0xb6a63400 | 0x1b8000 |
|
|
| 283 | blk.31.attn_norm.weight | 0xb6c1b400 | 0x4000 |
|
|
| 284 | blk.31.attn_output.weight | 0xb6c1f400 | 0x880000 |
|
|
| 285 | blk.31.attn_q.weight | 0xb749f400 | 0x6e0000 |
|
|
| 286 | blk.31.attn_v.weight | 0xb7b7f400 | 0x240000 |
|
|
| 287 | blk.31.ffn_down.weight | 0xb7dbf400 | 0x157c000 |
|
|
| 288 | blk.31.ffn_gate.weight | 0xb933b400 | 0x157c000 |
|
|
| 289 | blk.31.ffn_norm.weight | 0xba8b7400 | 0x4000 |
|
|
| 290 | blk.31.ffn_up.weight | 0xba8bb400 | 0x157c000 |
|
|
| 291 | blk.32.attn_k.weight | 0xbbe37400 | 0x1b8000 |
|
|
| 292 | blk.32.attn_norm.weight | 0xbbfef400 | 0x4000 |
|
|
| 293 | blk.32.attn_output.weight | 0xbbff3400 | 0x880000 |
|
|
| 294 | blk.32.attn_q.weight | 0xbc873400 | 0x6e0000 |
|
|
| 295 | blk.32.attn_v.weight | 0xbcf53400 | 0x240000 |
|
|
| 296 | blk.32.ffn_down.weight | 0xbd193400 | 0x157c000 |
|
|
| 297 | blk.32.ffn_gate.weight | 0xbe70f400 | 0x157c000 |
|
|
| 298 | blk.32.ffn_norm.weight | 0xbfc8b400 | 0x4000 |
|
|
| 299 | blk.32.ffn_up.weight | 0xbfc8f400 | 0x157c000 |
|
|
| 300 | blk.33.attn_k.weight | 0xc120b400 | 0x1b8000 |
|
|
| 301 | blk.33.attn_norm.weight | 0xc13c3400 | 0x4000 |
|
|
| 302 | blk.33.attn_output.weight | 0xc13c7400 | 0x880000 |
|
|
| 303 | blk.33.attn_q.weight | 0xc1c47400 | 0x6e0000 |
|
|
| 304 | blk.33.attn_v.weight | 0xc2327400 | 0x240000 |
|
|
| 305 | blk.33.ffn_down.weight | 0xc2567400 | 0x157c000 |
|
|
| 306 | blk.33.ffn_gate.weight | 0xc3ae3400 | 0x157c000 |
|
|
| 307 | blk.33.ffn_norm.weight | 0xc505f400 | 0x4000 |
|
|
| 308 | blk.33.ffn_up.weight | 0xc5063400 | 0x157c000 |
|
|
| 309 | blk.34.attn_k.weight | 0xc65df400 | 0x1b8000 |
|
|
| 310 | blk.34.attn_norm.weight | 0xc6797400 | 0x4000 |
|
|
| 311 | blk.34.attn_output.weight | 0xc679b400 | 0x880000 |
|
|
| 312 | blk.34.attn_q.weight | 0xc701b400 | 0x6e0000 |
|
|
| 313 | blk.34.attn_v.weight | 0xc76fb400 | 0x240000 |
|
|
| 314 | blk.34.ffn_down.weight | 0xc793b400 | 0x157c000 |
|
|
| 315 | blk.34.ffn_gate.weight | 0xc8eb7400 | 0x1324000 |
|
|
| 316 | blk.34.ffn_norm.weight | 0xca1db400 | 0x4000 |
|
|
| 317 | blk.34.ffn_up.weight | 0xca1df400 | 0x157c000 |
|
|
| 318 | blk.35.attn_k.weight | 0xcb75b400 | 0x1b8000 |
|
|
| 319 | blk.35.attn_norm.weight | 0xcb913400 | 0x4000 |
|
|
| 320 | blk.35.attn_output.weight | 0xcb917400 | 0x880000 |
|
|
| 321 | blk.35.attn_q.weight | 0xcc197400 | 0x6e0000 |
|
|
| 322 | blk.35.attn_v.weight | 0xcc877400 | 0x220000 |
|
|
| 323 | blk.35.ffn_down.weight | 0xcca97400 | 0x157c000 |
|
|
| 324 | blk.35.ffn_gate.weight | 0xce013400 | 0x157c000 |
|
|
| 325 | blk.35.ffn_norm.weight | 0xcf58f400 | 0x4000 |
|
|
| 326 | blk.35.ffn_up.weight | 0xcf593400 | 0x157c000 |
|
|
| 327 | blk.36.attn_k.weight | 0xd0b0f400 | 0x1b8000 |
|
|
| 328 | blk.36.attn_norm.weight | 0xd0cc7400 | 0x4000 |
|
|
| 329 | blk.36.attn_output.weight | 0xd0ccb400 | 0x880000 |
|
|
| 330 | blk.36.attn_q.weight | 0xd154b400 | 0x6e0000 |
|
|
| 331 | blk.36.attn_v.weight | 0xd1c2b400 | 0x220000 |
|
|
| 332 | blk.36.ffn_down.weight | 0xd1e4b400 | 0x157c000 |
|
|
| 333 | blk.36.ffn_gate.weight | 0xd33c7400 | 0x157c000 |
|
|
| 334 | blk.36.ffn_norm.weight | 0xd4943400 | 0x4000 |
|
|
| 335 | blk.36.ffn_up.weight | 0xd4947400 | 0x157c000 |
|
|
| 336 | blk.37.attn_k.weight | 0xd5ec3400 | 0x1b8000 |
|
|
| 337 | blk.37.attn_norm.weight | 0xd607b400 | 0x4000 |
|
|
| 338 | blk.37.attn_output.weight | 0xd607f400 | 0x880000 |
|
|
| 339 | blk.37.attn_q.weight | 0xd68ff400 | 0x6e0000 |
|
|
| 340 | blk.37.attn_v.weight | 0xd6fdf400 | 0x220000 |
|
|
| 341 | blk.37.ffn_down.weight | 0xd71ff400 | 0x157c000 |
|
|
| 342 | blk.37.ffn_gate.weight | 0xd877b400 | 0x157c000 |
|
|
| 343 | blk.37.ffn_norm.weight | 0xd9cf7400 | 0x4000 |
|
|
| 344 | blk.37.ffn_up.weight | 0xd9cfb400 | 0x157c000 |
|
|
| 345 | blk.38.attn_k.weight | 0xdb277400 | 0x1b8000 |
|
|
| 346 | blk.38.attn_norm.weight | 0xdb42f400 | 0x4000 |
|
|
| 347 | blk.38.attn_output.weight | 0xdb433400 | 0x880000 |
|
|
| 348 | blk.38.attn_q.weight | 0xdbcb3400 | 0x6e0000 |
|
|
| 349 | blk.38.attn_v.weight | 0xdc393400 | 0x220000 |
|
|
| 350 | blk.38.ffn_down.weight | 0xdc5b3400 | 0x157c000 |
|
|
| 351 | blk.38.ffn_gate.weight | 0xddb2f400 | 0x157c000 |
|
|
| 352 | blk.38.ffn_norm.weight | 0xdf0ab400 | 0x4000 |
|
|
| 353 | blk.38.ffn_up.weight | 0xdf0af400 | 0x157c000 |
|
|
| 354 | blk.39.attn_k.weight | 0xe062b400 | 0x1b8000 |
|
|
| 355 | blk.39.attn_norm.weight | 0xe07e3400 | 0x4000 |
|
|
| 356 | blk.39.attn_output.weight | 0xe07e7400 | 0x880000 |
|
|
| 357 | blk.39.attn_q.weight | 0xe1067400 | 0x6e0000 |
|
|
| 358 | blk.39.attn_v.weight | 0xe1747400 | 0x220000 |
|
|
| 359 | blk.39.ffn_down.weight | 0xe1967400 | 0x1324000 |
|
|
| 360 | blk.39.ffn_gate.weight | 0xe2c8b400 | 0x157c000 |
|
|
| 361 | blk.39.ffn_norm.weight | 0xe4207400 | 0x4000 |
|
|
| 362 | blk.39.ffn_up.weight | 0xe420b400 | 0x157c000 |
|
|
|
|
### <a name="base">Base Tensor Group : ~822M Elements</a>
|
|
|
|
| T_ID | Tensor Layer Name | Human Friendly Tensor Layer Name | Elements | Shape | Type | BPW |
|
|
|-----:|:-------------------|:---------------------------------|:------------------|:----------------------|:-----|--------:|
|
|
| 0 | output.weight | Output (W) | (~411M) 411041792 | 4096 x 100352 x 1 x 1 | Q4_K | 4.5000 |
|
|
| 1 | output_norm.weight | Output Normalization (W) | ( ~4K) 4096 | 4096 x 1 x 1 x 1 | F32 | 32.0000 |
|
|
| 2 | token_embd.weight | Token Embedding (W) | (~411M) 411041792 | 4096 x 100352 x 1 x 1 | Q3_K | 3.4375 |
|
|
|
|
- Total elements in base: (~822M) 822087680
|
|
- Percentage of total elements: 9.35%
|
|
- Bits per Weight (BPW) for base: 3.9689 bits
|
|
|
|
|
|
### <a name="blk_0">Block 0 Tensor Group : ~199M Elements</a>
|
|
|
|
| T_ID | Tensor Layer Name | Human Friendly Tensor Layer Name | Elements | Shape | Type | BPW |
|
|
|-----:|:-------------------------|:-----------------------------------------------|:----------------|:----------------------|:--------|--------:|
|
|
| 3 | blk.0.attn_k.weight | Block 0 Attention Key (W) | ( ~4M) 4194304 | 4096 x 1024 x 1 x 1 | IQ2_XS | 2.3125 |
|
|
| 4 | blk.0.attn_norm.weight | Block 0 Attention Normalization (W) | ( ~4K) 4096 | 4096 x 1 x 1 x 1 | F32 | 32.0000 |
|
|
| 5 | blk.0.attn_output.weight | Block 0 Attention Output (W) | (~17M) 16777216 | 4096 x 4096 x 1 x 1 | IQ3_XXS | 3.0625 |
|
|
| 6 | blk.0.attn_q.weight | Block 0 Attention Query (W) | (~17M) 16777216 | 4096 x 4096 x 1 x 1 | IQ2_XS | 2.3125 |
|
|
| 7 | blk.0.attn_v.weight | Block 0 Attention Value (W) | ( ~4M) 4194304 | 4096 x 1024 x 1 x 1 | IQ3_XXS | 3.0625 |
|
|
| 8 | blk.0.ffn_down.weight | Block 0 Feed-Forward Network "Down" (W) | (~52M) 52428800 | 12800 x 4096 x 1 x 1 | Q2_K | 2.6250 |
|
|
| 9 | blk.0.ffn_gate.weight | Block 0 Feed-Forward Network "Gate" (W) | (~52M) 52428800 | 4096 x 12800 x 1 x 1 | IQ2_XXS | 2.0625 |
|
|
| 10 | blk.0.ffn_norm.weight | Block 0 Feed-Forward Network Normalization (W) | ( ~4K) 4096 | 4096 x 1 x 1 x 1 | F32 | 32.0000 |
|
|
| 11 | blk.0.ffn_up.weight | Block 0 Feed-Forward Network "Up" (W) | (~52M) 52428800 | 4096 x 12800 x 1 x 1 | IQ3_XXS | 3.0625 |
|
|
|
|
- Total elements in blk.0: (~199M) 199237632
|
|
- Percentage of total elements: 2.27%
|
|
- Bits per Weight (BPW) for blk.0: 2.6065 bits
|
|
|
|
|
|
### <a name="blk_1">Block 1 Tensor Group : ~199M Elements</a>
|
|
|
|
| T_ID | Tensor Layer Name | Human Friendly Tensor Layer Name | Elements | Shape | Type | BPW |
|
|
|-----:|:-------------------------|:-----------------------------------------------|:----------------|:----------------------|:--------|--------:|
|
|
| 12 | blk.1.attn_k.weight | Block 1 Attention Key (W) | ( ~4M) 4194304 | 4096 x 1024 x 1 x 1 | IQ3_XXS | 3.0625 |
|
|
| 13 | blk.1.attn_norm.weight | Block 1 Attention Normalization (W) | ( ~4K) 4096 | 4096 x 1 x 1 x 1 | F32 | 32.0000 |
|
|
| 14 | blk.1.attn_output.weight | Block 1 Attention Output (W) | (~17M) 16777216 | 4096 x 4096 x 1 x 1 | IQ4_XS | 4.2500 |
|
|
| 15 | blk.1.attn_q.weight | Block 1 Attention Query (W) | (~17M) 16777216 | 4096 x 4096 x 1 x 1 | IQ3_S | 3.4375 |
|
|
| 16 | blk.1.attn_v.weight | Block 1 Attention Value (W) | ( ~4M) 4194304 | 4096 x 1024 x 1 x 1 | Q4_K | 4.5000 |
|
|
| 17 | blk.1.ffn_down.weight | Block 1 Feed-Forward Network "Down" (W) | (~52M) 52428800 | 12800 x 4096 x 1 x 1 | IQ3_S | 3.4375 |
|
|
| 18 | blk.1.ffn_gate.weight | Block 1 Feed-Forward Network "Gate" (W) | (~52M) 52428800 | 4096 x 12800 x 1 x 1 | IQ3_XXS | 3.0625 |
|
|
| 19 | blk.1.ffn_norm.weight | Block 1 Feed-Forward Network Normalization (W) | ( ~4K) 4096 | 4096 x 1 x 1 x 1 | F32 | 32.0000 |
|
|
| 20 | blk.1.ffn_up.weight | Block 1 Feed-Forward Network "Up" (W) | (~52M) 52428800 | 4096 x 12800 x 1 x 1 | IQ4_XS | 4.2500 |
|
|
|
|
- Total elements in blk.1: (~199M) 199237632
|
|
- Percentage of total elements: 2.27%
|
|
- Bits per Weight (BPW) for blk.1: 3.6367 bits
|
|
|
|
|
|
### <a name="blk_2">Block 2 Tensor Group : ~199M Elements</a>
|
|
|
|
| T_ID | Tensor Layer Name | Human Friendly Tensor Layer Name | Elements | Shape | Type | BPW |
|
|
|-----:|:-------------------------|:-----------------------------------------------|:----------------|:----------------------|:--------|--------:|
|
|
| 21 | blk.2.attn_k.weight | Block 2 Attention Key (W) | ( ~4M) 4194304 | 4096 x 1024 x 1 x 1 | IQ3_S | 3.4375 |
|
|
| 22 | blk.2.attn_norm.weight | Block 2 Attention Normalization (W) | ( ~4K) 4096 | 4096 x 1 x 1 x 1 | F32 | 32.0000 |
|
|
| 23 | blk.2.attn_output.weight | Block 2 Attention Output (W) | (~17M) 16777216 | 4096 x 4096 x 1 x 1 | IQ4_XS | 4.2500 |
|
|
| 24 | blk.2.attn_q.weight | Block 2 Attention Query (W) | (~17M) 16777216 | 4096 x 4096 x 1 x 1 | IQ3_S | 3.4375 |
|
|
| 25 | blk.2.attn_v.weight | Block 2 Attention Value (W) | ( ~4M) 4194304 | 4096 x 1024 x 1 x 1 | IQ4_XS | 4.2500 |
|
|
| 26 | blk.2.ffn_down.weight | Block 2 Feed-Forward Network "Down" (W) | (~52M) 52428800 | 12800 x 4096 x 1 x 1 | IQ3_S | 3.4375 |
|
|
| 27 | blk.2.ffn_gate.weight | Block 2 Feed-Forward Network "Gate" (W) | (~52M) 52428800 | 4096 x 12800 x 1 x 1 | IQ3_XXS | 3.0625 |
|
|
| 28 | blk.2.ffn_norm.weight | Block 2 Feed-Forward Network Normalization (W) | ( ~4K) 4096 | 4096 x 1 x 1 x 1 | F32 | 32.0000 |
|
|
| 29 | blk.2.ffn_up.weight | Block 2 Feed-Forward Network "Up" (W) | (~52M) 52428800 | 4096 x 12800 x 1 x 1 | IQ4_XS | 4.2500 |
|
|
|
|
- Total elements in blk.2: (~199M) 199237632
|
|
- Percentage of total elements: 2.27%
|
|
- Bits per Weight (BPW) for blk.2: 3.6393 bits
|
|
|
|
|
|
### <a name="blk_3">Block 3 Tensor Group : ~199M Elements</a>
|
|
|
|
| T_ID | Tensor Layer Name | Human Friendly Tensor Layer Name | Elements | Shape | Type | BPW |
|
|
|-----:|:-------------------------|:-----------------------------------------------|:----------------|:----------------------|:--------|--------:|
|
|
| 30 | blk.3.attn_k.weight | Block 3 Attention Key (W) | ( ~4M) 4194304 | 4096 x 1024 x 1 x 1 | IQ3_XXS | 3.0625 |
|
|
| 31 | blk.3.attn_norm.weight | Block 3 Attention Normalization (W) | ( ~4K) 4096 | 4096 x 1 x 1 x 1 | F32 | 32.0000 |
|
|
| 32 | blk.3.attn_output.weight | Block 3 Attention Output (W) | (~17M) 16777216 | 4096 x 4096 x 1 x 1 | IQ4_XS | 4.2500 |
|
|
| 33 | blk.3.attn_q.weight | Block 3 Attention Query (W) | (~17M) 16777216 | 4096 x 4096 x 1 x 1 | IQ3_S | 3.4375 |
|
|
| 34 | blk.3.attn_v.weight | Block 3 Attention Value (W) | ( ~4M) 4194304 | 4096 x 1024 x 1 x 1 | Q4_K | 4.5000 |
|
|
| 35 | blk.3.ffn_down.weight | Block 3 Feed-Forward Network "Down" (W) | (~52M) 52428800 | 12800 x 4096 x 1 x 1 | IQ3_XXS | 3.0625 |
|
|
| 36 | blk.3.ffn_gate.weight | Block 3 Feed-Forward Network "Gate" (W) | (~52M) 52428800 | 4096 x 12800 x 1 x 1 | IQ3_S | 3.4375 |
|
|
| 37 | blk.3.ffn_norm.weight | Block 3 Feed-Forward Network Normalization (W) | ( ~4K) 4096 | 4096 x 1 x 1 x 1 | F32 | 32.0000 |
|
|
| 38 | blk.3.ffn_up.weight | Block 3 Feed-Forward Network "Up" (W) | (~52M) 52428800 | 4096 x 12800 x 1 x 1 | IQ3_S | 3.4375 |
|
|
|
|
- Total elements in blk.3: (~199M) 199237632
|
|
- Percentage of total elements: 2.27%
|
|
- Bits per Weight (BPW) for blk.3: 3.4229 bits
|
|
|
|
|
|
### <a name="blk_4">Block 4 Tensor Group : ~199M Elements</a>
|
|
|
|
| T_ID | Tensor Layer Name | Human Friendly Tensor Layer Name | Elements | Shape | Type | BPW |
|
|
|-----:|:-------------------------|:-----------------------------------------------|:----------------|:----------------------|:-------|--------:|
|
|
| 39 | blk.4.attn_k.weight | Block 4 Attention Key (W) | ( ~4M) 4194304 | 4096 x 1024 x 1 x 1 | IQ3_S | 3.4375 |
|
|
| 40 | blk.4.attn_norm.weight | Block 4 Attention Normalization (W) | ( ~4K) 4096 | 4096 x 1 x 1 x 1 | F32 | 32.0000 |
|
|
| 41 | blk.4.attn_output.weight | Block 4 Attention Output (W) | (~17M) 16777216 | 4096 x 4096 x 1 x 1 | IQ4_XS | 4.2500 |
|
|
| 42 | blk.4.attn_q.weight | Block 4 Attention Query (W) | (~17M) 16777216 | 4096 x 4096 x 1 x 1 | IQ3_S | 3.4375 |
|
|
| 43 | blk.4.attn_v.weight | Block 4 Attention Value (W) | ( ~4M) 4194304 | 4096 x 1024 x 1 x 1 | Q4_K | 4.5000 |
|
|
| 44 | blk.4.ffn_down.weight | Block 4 Feed-Forward Network "Down" (W) | (~52M) 52428800 | 12800 x 4096 x 1 x 1 | IQ3_S | 3.4375 |
|
|
| 45 | blk.4.ffn_gate.weight | Block 4 Feed-Forward Network "Gate" (W) | (~52M) 52428800 | 4096 x 12800 x 1 x 1 | IQ3_S | 3.4375 |
|
|
| 46 | blk.4.ffn_norm.weight | Block 4 Feed-Forward Network Normalization (W) | ( ~4K) 4096 | 4096 x 1 x 1 x 1 | F32 | 32.0000 |
|
|
| 47 | blk.4.ffn_up.weight | Block 4 Feed-Forward Network "Up" (W) | (~52M) 52428800 | 4096 x 12800 x 1 x 1 | IQ3_S | 3.4375 |
|
|
|
|
- Total elements in blk.4: (~199M) 199237632
|
|
- Percentage of total elements: 2.27%
|
|
- Bits per Weight (BPW) for blk.4: 3.5295 bits
|
|
|
|
|
|
### <a name="blk_5">Block 5 Tensor Group : ~199M Elements</a>
|
|
|
|
| T_ID | Tensor Layer Name | Human Friendly Tensor Layer Name | Elements | Shape | Type | BPW |
|
|
|-----:|:-------------------------|:-----------------------------------------------|:----------------|:----------------------|:--------|--------:|
|
|
| 48 | blk.5.attn_k.weight | Block 5 Attention Key (W) | ( ~4M) 4194304 | 4096 x 1024 x 1 x 1 | IQ3_S | 3.4375 |
|
|
| 49 | blk.5.attn_norm.weight | Block 5 Attention Normalization (W) | ( ~4K) 4096 | 4096 x 1 x 1 x 1 | F32 | 32.0000 |
|
|
| 50 | blk.5.attn_output.weight | Block 5 Attention Output (W) | (~17M) 16777216 | 4096 x 4096 x 1 x 1 | IQ4_XS | 4.2500 |
|
|
| 51 | blk.5.attn_q.weight | Block 5 Attention Query (W) | (~17M) 16777216 | 4096 x 4096 x 1 x 1 | IQ3_S | 3.4375 |
|
|
| 52 | blk.5.attn_v.weight | Block 5 Attention Value (W) | ( ~4M) 4194304 | 4096 x 1024 x 1 x 1 | Q4_K | 4.5000 |
|
|
| 53 | blk.5.ffn_down.weight | Block 5 Feed-Forward Network "Down" (W) | (~52M) 52428800 | 12800 x 4096 x 1 x 1 | IQ3_XXS | 3.0625 |
|
|
| 54 | blk.5.ffn_gate.weight | Block 5 Feed-Forward Network "Gate" (W) | (~52M) 52428800 | 4096 x 12800 x 1 x 1 | IQ3_S | 3.4375 |
|
|
| 55 | blk.5.ffn_norm.weight | Block 5 Feed-Forward Network Normalization (W) | ( ~4K) 4096 | 4096 x 1 x 1 x 1 | F32 | 32.0000 |
|
|
| 56 | blk.5.ffn_up.weight | Block 5 Feed-Forward Network "Up" (W) | (~52M) 52428800 | 4096 x 12800 x 1 x 1 | IQ3_S | 3.4375 |
|
|
|
|
- Total elements in blk.5: (~199M) 199237632
|
|
- Percentage of total elements: 2.27%
|
|
- Bits per Weight (BPW) for blk.5: 3.4308 bits
|
|
|
|
|
|
### <a name="blk_6">Block 6 Tensor Group : ~199M Elements</a>
|
|
|
|
| T_ID | Tensor Layer Name | Human Friendly Tensor Layer Name | Elements | Shape | Type | BPW |
|
|
|-----:|:-------------------------|:-----------------------------------------------|:----------------|:----------------------|:--------|--------:|
|
|
| 57 | blk.6.attn_k.weight | Block 6 Attention Key (W) | ( ~4M) 4194304 | 4096 x 1024 x 1 x 1 | IQ3_S | 3.4375 |
|
|
| 58 | blk.6.attn_norm.weight | Block 6 Attention Normalization (W) | ( ~4K) 4096 | 4096 x 1 x 1 x 1 | F32 | 32.0000 |
|
|
| 59 | blk.6.attn_output.weight | Block 6 Attention Output (W) | (~17M) 16777216 | 4096 x 4096 x 1 x 1 | IQ4_XS | 4.2500 |
|
|
| 60 | blk.6.attn_q.weight | Block 6 Attention Query (W) | (~17M) 16777216 | 4096 x 4096 x 1 x 1 | IQ3_S | 3.4375 |
|
|
| 61 | blk.6.attn_v.weight | Block 6 Attention Value (W) | ( ~4M) 4194304 | 4096 x 1024 x 1 x 1 | Q4_K | 4.5000 |
|
|
| 62 | blk.6.ffn_down.weight | Block 6 Feed-Forward Network "Down" (W) | (~52M) 52428800 | 12800 x 4096 x 1 x 1 | IQ3_S | 3.4375 |
|
|
| 63 | blk.6.ffn_gate.weight | Block 6 Feed-Forward Network "Gate" (W) | (~52M) 52428800 | 4096 x 12800 x 1 x 1 | IQ3_XXS | 3.0625 |
|
|
| 64 | blk.6.ffn_norm.weight | Block 6 Feed-Forward Network Normalization (W) | ( ~4K) 4096 | 4096 x 1 x 1 x 1 | F32 | 32.0000 |
|
|
| 65 | blk.6.ffn_up.weight | Block 6 Feed-Forward Network "Up" (W) | (~52M) 52428800 | 4096 x 12800 x 1 x 1 | IQ3_S | 3.4375 |
|
|
|
|
- Total elements in blk.6: (~199M) 199237632
|
|
- Percentage of total elements: 2.27%
|
|
- Bits per Weight (BPW) for blk.6: 3.4308 bits
|
|
|
|
|
|
### <a name="blk_7">Block 7 Tensor Group : ~199M Elements</a>
|
|
|
|
| T_ID | Tensor Layer Name | Human Friendly Tensor Layer Name | Elements | Shape | Type | BPW |
|
|
|-----:|:-------------------------|:-----------------------------------------------|:----------------|:----------------------|:--------|--------:|
|
|
| 66 | blk.7.attn_k.weight | Block 7 Attention Key (W) | ( ~4M) 4194304 | 4096 x 1024 x 1 x 1 | IQ3_S | 3.4375 |
|
|
| 67 | blk.7.attn_norm.weight | Block 7 Attention Normalization (W) | ( ~4K) 4096 | 4096 x 1 x 1 x 1 | F32 | 32.0000 |
|
|
| 68 | blk.7.attn_output.weight | Block 7 Attention Output (W) | (~17M) 16777216 | 4096 x 4096 x 1 x 1 | IQ4_XS | 4.2500 |
|
|
| 69 | blk.7.attn_q.weight | Block 7 Attention Query (W) | (~17M) 16777216 | 4096 x 4096 x 1 x 1 | IQ3_S | 3.4375 |
|
|
| 70 | blk.7.attn_v.weight | Block 7 Attention Value (W) | ( ~4M) 4194304 | 4096 x 1024 x 1 x 1 | Q4_K | 4.5000 |
|
|
| 71 | blk.7.ffn_down.weight | Block 7 Feed-Forward Network "Down" (W) | (~52M) 52428800 | 12800 x 4096 x 1 x 1 | IQ3_S | 3.4375 |
|
|
| 72 | blk.7.ffn_gate.weight | Block 7 Feed-Forward Network "Gate" (W) | (~52M) 52428800 | 4096 x 12800 x 1 x 1 | IQ3_XXS | 3.0625 |
|
|
| 73 | blk.7.ffn_norm.weight | Block 7 Feed-Forward Network Normalization (W) | ( ~4K) 4096 | 4096 x 1 x 1 x 1 | F32 | 32.0000 |
|
|
| 74 | blk.7.ffn_up.weight | Block 7 Feed-Forward Network "Up" (W) | (~52M) 52428800 | 4096 x 12800 x 1 x 1 | IQ3_S | 3.4375 |
|
|
|
|
- Total elements in blk.7: (~199M) 199237632
|
|
- Percentage of total elements: 2.27%
|
|
- Bits per Weight (BPW) for blk.7: 3.4308 bits
|
|
|
|
|
|
### <a name="blk_8">Block 8 Tensor Group : ~199M Elements</a>
|
|
|
|
| T_ID | Tensor Layer Name | Human Friendly Tensor Layer Name | Elements | Shape | Type | BPW |
|
|
|-----:|:-------------------------|:-----------------------------------------------|:----------------|:----------------------|:--------|--------:|
|
|
| 75 | blk.8.attn_k.weight | Block 8 Attention Key (W) | ( ~4M) 4194304 | 4096 x 1024 x 1 x 1 | IQ3_S | 3.4375 |
|
|
| 76 | blk.8.attn_norm.weight | Block 8 Attention Normalization (W) | ( ~4K) 4096 | 4096 x 1 x 1 x 1 | F32 | 32.0000 |
|
|
| 77 | blk.8.attn_output.weight | Block 8 Attention Output (W) | (~17M) 16777216 | 4096 x 4096 x 1 x 1 | IQ4_XS | 4.2500 |
|
|
| 78 | blk.8.attn_q.weight | Block 8 Attention Query (W) | (~17M) 16777216 | 4096 x 4096 x 1 x 1 | IQ3_S | 3.4375 |
|
|
| 79 | blk.8.attn_v.weight | Block 8 Attention Value (W) | ( ~4M) 4194304 | 4096 x 1024 x 1 x 1 | Q4_K | 4.5000 |
|
|
| 80 | blk.8.ffn_down.weight | Block 8 Feed-Forward Network "Down" (W) | (~52M) 52428800 | 12800 x 4096 x 1 x 1 | IQ3_S | 3.4375 |
|
|
| 81 | blk.8.ffn_gate.weight | Block 8 Feed-Forward Network "Gate" (W) | (~52M) 52428800 | 4096 x 12800 x 1 x 1 | IQ3_XXS | 3.0625 |
|
|
| 82 | blk.8.ffn_norm.weight | Block 8 Feed-Forward Network Normalization (W) | ( ~4K) 4096 | 4096 x 1 x 1 x 1 | F32 | 32.0000 |
|
|
| 83 | blk.8.ffn_up.weight | Block 8 Feed-Forward Network "Up" (W) | (~52M) 52428800 | 4096 x 12800 x 1 x 1 | IQ3_S | 3.4375 |
|
|
|
|
- Total elements in blk.8: (~199M) 199237632
|
|
- Percentage of total elements: 2.27%
|
|
- Bits per Weight (BPW) for blk.8: 3.4308 bits
|
|
|
|
|
|
### <a name="blk_9">Block 9 Tensor Group : ~199M Elements</a>
|
|
|
|
| T_ID | Tensor Layer Name | Human Friendly Tensor Layer Name | Elements | Shape | Type | BPW |
|
|
|-----:|:-------------------------|:-----------------------------------------------|:----------------|:----------------------|:--------|--------:|
|
|
| 84 | blk.9.attn_k.weight | Block 9 Attention Key (W) | ( ~4M) 4194304 | 4096 x 1024 x 1 x 1 | IQ3_S | 3.4375 |
|
|
| 85 | blk.9.attn_norm.weight | Block 9 Attention Normalization (W) | ( ~4K) 4096 | 4096 x 1 x 1 x 1 | F32 | 32.0000 |
|
|
| 86 | blk.9.attn_output.weight | Block 9 Attention Output (W) | (~17M) 16777216 | 4096 x 4096 x 1 x 1 | IQ4_XS | 4.2500 |
|
|
| 87 | blk.9.attn_q.weight | Block 9 Attention Query (W) | (~17M) 16777216 | 4096 x 4096 x 1 x 1 | IQ3_S | 3.4375 |
|
|
| 88 | blk.9.attn_v.weight | Block 9 Attention Value (W) | ( ~4M) 4194304 | 4096 x 1024 x 1 x 1 | Q4_K | 4.5000 |
|
|
| 89 | blk.9.ffn_down.weight | Block 9 Feed-Forward Network "Down" (W) | (~52M) 52428800 | 12800 x 4096 x 1 x 1 | IQ3_S | 3.4375 |
|
|
| 90 | blk.9.ffn_gate.weight | Block 9 Feed-Forward Network "Gate" (W) | (~52M) 52428800 | 4096 x 12800 x 1 x 1 | IQ3_XXS | 3.0625 |
|
|
| 91 | blk.9.ffn_norm.weight | Block 9 Feed-Forward Network Normalization (W) | ( ~4K) 4096 | 4096 x 1 x 1 x 1 | F32 | 32.0000 |
|
|
| 92 | blk.9.ffn_up.weight | Block 9 Feed-Forward Network "Up" (W) | (~52M) 52428800 | 4096 x 12800 x 1 x 1 | IQ3_S | 3.4375 |
|
|
|
|
- Total elements in blk.9: (~199M) 199237632
|
|
- Percentage of total elements: 2.27%
|
|
- Bits per Weight (BPW) for blk.9: 3.4308 bits
|
|
|
|
|
|
### <a name="blk_10">Block 10 Tensor Group : ~199M Elements</a>
|
|
|
|
| T_ID | Tensor Layer Name | Human Friendly Tensor Layer Name | Elements | Shape | Type | BPW |
|
|
|-----:|:--------------------------|:------------------------------------------------|:----------------|:----------------------|:--------|--------:|
|
|
| 93 | blk.10.attn_k.weight | Block 10 Attention Key (W) | ( ~4M) 4194304 | 4096 x 1024 x 1 x 1 | IQ3_S | 3.4375 |
|
|
| 94 | blk.10.attn_norm.weight | Block 10 Attention Normalization (W) | ( ~4K) 4096 | 4096 x 1 x 1 x 1 | F32 | 32.0000 |
|
|
| 95 | blk.10.attn_output.weight | Block 10 Attention Output (W) | (~17M) 16777216 | 4096 x 4096 x 1 x 1 | IQ4_XS | 4.2500 |
|
|
| 96 | blk.10.attn_q.weight | Block 10 Attention Query (W) | (~17M) 16777216 | 4096 x 4096 x 1 x 1 | IQ3_S | 3.4375 |
|
|
| 97 | blk.10.attn_v.weight | Block 10 Attention Value (W) | ( ~4M) 4194304 | 4096 x 1024 x 1 x 1 | Q4_K | 4.5000 |
|
|
| 98 | blk.10.ffn_down.weight | Block 10 Feed-Forward Network "Down" (W) | (~52M) 52428800 | 12800 x 4096 x 1 x 1 | IQ3_S | 3.4375 |
|
|
| 99 | blk.10.ffn_gate.weight | Block 10 Feed-Forward Network "Gate" (W) | (~52M) 52428800 | 4096 x 12800 x 1 x 1 | IQ3_XXS | 3.0625 |
|
|
| 100 | blk.10.ffn_norm.weight | Block 10 Feed-Forward Network Normalization (W) | ( ~4K) 4096 | 4096 x 1 x 1 x 1 | F32 | 32.0000 |
|
|
| 101 | blk.10.ffn_up.weight | Block 10 Feed-Forward Network "Up" (W) | (~52M) 52428800 | 4096 x 12800 x 1 x 1 | IQ3_S | 3.4375 |
|
|
|
|
- Total elements in blk.10: (~199M) 199237632
|
|
- Percentage of total elements: 2.27%
|
|
- Bits per Weight (BPW) for blk.10: 3.4308 bits
|
|
|
|
|
|
### <a name="blk_11">Block 11 Tensor Group : ~199M Elements</a>
|
|
|
|
| T_ID | Tensor Layer Name | Human Friendly Tensor Layer Name | Elements | Shape | Type | BPW |
|
|
|-----:|:--------------------------|:------------------------------------------------|:----------------|:----------------------|:--------|--------:|
|
|
| 102 | blk.11.attn_k.weight | Block 11 Attention Key (W) | ( ~4M) 4194304 | 4096 x 1024 x 1 x 1 | IQ3_S | 3.4375 |
|
|
| 103 | blk.11.attn_norm.weight | Block 11 Attention Normalization (W) | ( ~4K) 4096 | 4096 x 1 x 1 x 1 | F32 | 32.0000 |
|
|
| 104 | blk.11.attn_output.weight | Block 11 Attention Output (W) | (~17M) 16777216 | 4096 x 4096 x 1 x 1 | IQ4_XS | 4.2500 |
|
|
| 105 | blk.11.attn_q.weight | Block 11 Attention Query (W) | (~17M) 16777216 | 4096 x 4096 x 1 x 1 | IQ3_S | 3.4375 |
|
|
| 106 | blk.11.attn_v.weight | Block 11 Attention Value (W) | ( ~4M) 4194304 | 4096 x 1024 x 1 x 1 | IQ4_XS | 4.2500 |
|
|
| 107 | blk.11.ffn_down.weight | Block 11 Feed-Forward Network "Down" (W) | (~52M) 52428800 | 12800 x 4096 x 1 x 1 | IQ3_S | 3.4375 |
|
|
| 108 | blk.11.ffn_gate.weight | Block 11 Feed-Forward Network "Gate" (W) | (~52M) 52428800 | 4096 x 12800 x 1 x 1 | IQ3_XXS | 3.0625 |
|
|
| 109 | blk.11.ffn_norm.weight | Block 11 Feed-Forward Network Normalization (W) | ( ~4K) 4096 | 4096 x 1 x 1 x 1 | F32 | 32.0000 |
|
|
| 110 | blk.11.ffn_up.weight | Block 11 Feed-Forward Network "Up" (W) | (~52M) 52428800 | 4096 x 12800 x 1 x 1 | IQ3_S | 3.4375 |
|
|
|
|
- Total elements in blk.11: (~199M) 199237632
|
|
- Percentage of total elements: 2.27%
|
|
- Bits per Weight (BPW) for blk.11: 3.4255 bits
|
|
|
|
|
|
### <a name="blk_12">Block 12 Tensor Group : ~199M Elements</a>
|
|
|
|
| T_ID | Tensor Layer Name | Human Friendly Tensor Layer Name | Elements | Shape | Type | BPW |
|
|
|-----:|:--------------------------|:------------------------------------------------|:----------------|:----------------------|:--------|--------:|
|
|
| 111 | blk.12.attn_k.weight | Block 12 Attention Key (W) | ( ~4M) 4194304 | 4096 x 1024 x 1 x 1 | IQ3_S | 3.4375 |
|
|
| 112 | blk.12.attn_norm.weight | Block 12 Attention Normalization (W) | ( ~4K) 4096 | 4096 x 1 x 1 x 1 | F32 | 32.0000 |
|
|
| 113 | blk.12.attn_output.weight | Block 12 Attention Output (W) | (~17M) 16777216 | 4096 x 4096 x 1 x 1 | IQ4_XS | 4.2500 |
|
|
| 114 | blk.12.attn_q.weight | Block 12 Attention Query (W) | (~17M) 16777216 | 4096 x 4096 x 1 x 1 | IQ3_S | 3.4375 |
|
|
| 115 | blk.12.attn_v.weight | Block 12 Attention Value (W) | ( ~4M) 4194304 | 4096 x 1024 x 1 x 1 | Q4_K | 4.5000 |
|
|
| 116 | blk.12.ffn_down.weight | Block 12 Feed-Forward Network "Down" (W) | (~52M) 52428800 | 12800 x 4096 x 1 x 1 | IQ3_S | 3.4375 |
|
|
| 117 | blk.12.ffn_gate.weight | Block 12 Feed-Forward Network "Gate" (W) | (~52M) 52428800 | 4096 x 12800 x 1 x 1 | IQ3_XXS | 3.0625 |
|
|
| 118 | blk.12.ffn_norm.weight | Block 12 Feed-Forward Network Normalization (W) | ( ~4K) 4096 | 4096 x 1 x 1 x 1 | F32 | 32.0000 |
|
|
| 119 | blk.12.ffn_up.weight | Block 12 Feed-Forward Network "Up" (W) | (~52M) 52428800 | 4096 x 12800 x 1 x 1 | IQ3_S | 3.4375 |
|
|
|
|
- Total elements in blk.12: (~199M) 199237632
|
|
- Percentage of total elements: 2.27%
|
|
- Bits per Weight (BPW) for blk.12: 3.4308 bits
|
|
|
|
|
|
### <a name="blk_13">Block 13 Tensor Group : ~199M Elements</a>
|
|
|
|
| T_ID | Tensor Layer Name | Human Friendly Tensor Layer Name | Elements | Shape | Type | BPW |
|
|
|-----:|:--------------------------|:------------------------------------------------|:----------------|:----------------------|:--------|--------:|
|
|
| 120 | blk.13.attn_k.weight | Block 13 Attention Key (W) | ( ~4M) 4194304 | 4096 x 1024 x 1 x 1 | IQ3_S | 3.4375 |
|
|
| 121 | blk.13.attn_norm.weight | Block 13 Attention Normalization (W) | ( ~4K) 4096 | 4096 x 1 x 1 x 1 | F32 | 32.0000 |
|
|
| 122 | blk.13.attn_output.weight | Block 13 Attention Output (W) | (~17M) 16777216 | 4096 x 4096 x 1 x 1 | IQ4_XS | 4.2500 |
|
|
| 123 | blk.13.attn_q.weight | Block 13 Attention Query (W) | (~17M) 16777216 | 4096 x 4096 x 1 x 1 | IQ3_S | 3.4375 |
|
|
| 124 | blk.13.attn_v.weight | Block 13 Attention Value (W) | ( ~4M) 4194304 | 4096 x 1024 x 1 x 1 | Q4_K | 4.5000 |
|
|
| 125 | blk.13.ffn_down.weight | Block 13 Feed-Forward Network "Down" (W) | (~52M) 52428800 | 12800 x 4096 x 1 x 1 | IQ3_S | 3.4375 |
|
|
| 126 | blk.13.ffn_gate.weight | Block 13 Feed-Forward Network "Gate" (W) | (~52M) 52428800 | 4096 x 12800 x 1 x 1 | IQ3_XXS | 3.0625 |
|
|
| 127 | blk.13.ffn_norm.weight | Block 13 Feed-Forward Network Normalization (W) | ( ~4K) 4096 | 4096 x 1 x 1 x 1 | F32 | 32.0000 |
|
|
| 128 | blk.13.ffn_up.weight | Block 13 Feed-Forward Network "Up" (W) | (~52M) 52428800 | 4096 x 12800 x 1 x 1 | IQ3_S | 3.4375 |
|
|
|
|
- Total elements in blk.13: (~199M) 199237632
|
|
- Percentage of total elements: 2.27%
|
|
- Bits per Weight (BPW) for blk.13: 3.4308 bits
|
|
|
|
|
|
### <a name="blk_14">Block 14 Tensor Group : ~199M Elements</a>
|
|
|
|
| T_ID | Tensor Layer Name | Human Friendly Tensor Layer Name | Elements | Shape | Type | BPW |
|
|
|-----:|:--------------------------|:------------------------------------------------|:----------------|:----------------------|:--------|--------:|
|
|
| 129 | blk.14.attn_k.weight | Block 14 Attention Key (W) | ( ~4M) 4194304 | 4096 x 1024 x 1 x 1 | IQ3_S | 3.4375 |
|
|
| 130 | blk.14.attn_norm.weight | Block 14 Attention Normalization (W) | ( ~4K) 4096 | 4096 x 1 x 1 x 1 | F32 | 32.0000 |
|
|
| 131 | blk.14.attn_output.weight | Block 14 Attention Output (W) | (~17M) 16777216 | 4096 x 4096 x 1 x 1 | IQ4_XS | 4.2500 |
|
|
| 132 | blk.14.attn_q.weight | Block 14 Attention Query (W) | (~17M) 16777216 | 4096 x 4096 x 1 x 1 | IQ3_S | 3.4375 |
|
|
| 133 | blk.14.attn_v.weight | Block 14 Attention Value (W) | ( ~4M) 4194304 | 4096 x 1024 x 1 x 1 | Q4_K | 4.5000 |
|
|
| 134 | blk.14.ffn_down.weight | Block 14 Feed-Forward Network "Down" (W) | (~52M) 52428800 | 12800 x 4096 x 1 x 1 | IQ3_S | 3.4375 |
|
|
| 135 | blk.14.ffn_gate.weight | Block 14 Feed-Forward Network "Gate" (W) | (~52M) 52428800 | 4096 x 12800 x 1 x 1 | IQ3_XXS | 3.0625 |
|
|
| 136 | blk.14.ffn_norm.weight | Block 14 Feed-Forward Network Normalization (W) | ( ~4K) 4096 | 4096 x 1 x 1 x 1 | F32 | 32.0000 |
|
|
| 137 | blk.14.ffn_up.weight | Block 14 Feed-Forward Network "Up" (W) | (~52M) 52428800 | 4096 x 12800 x 1 x 1 | IQ3_S | 3.4375 |
|
|
|
|
- Total elements in blk.14: (~199M) 199237632
|
|
- Percentage of total elements: 2.27%
|
|
- Bits per Weight (BPW) for blk.14: 3.4308 bits
|
|
|
|
|
|
### <a name="blk_15">Block 15 Tensor Group : ~199M Elements</a>
|
|
|
|
| T_ID | Tensor Layer Name | Human Friendly Tensor Layer Name | Elements | Shape | Type | BPW |
|
|
|-----:|:--------------------------|:------------------------------------------------|:----------------|:----------------------|:-------|--------:|
|
|
| 138 | blk.15.attn_k.weight | Block 15 Attention Key (W) | ( ~4M) 4194304 | 4096 x 1024 x 1 x 1 | IQ3_S | 3.4375 |
|
|
| 139 | blk.15.attn_norm.weight | Block 15 Attention Normalization (W) | ( ~4K) 4096 | 4096 x 1 x 1 x 1 | F32 | 32.0000 |
|
|
| 140 | blk.15.attn_output.weight | Block 15 Attention Output (W) | (~17M) 16777216 | 4096 x 4096 x 1 x 1 | IQ4_XS | 4.2500 |
|
|
| 141 | blk.15.attn_q.weight | Block 15 Attention Query (W) | (~17M) 16777216 | 4096 x 4096 x 1 x 1 | IQ3_S | 3.4375 |
|
|
| 142 | blk.15.attn_v.weight | Block 15 Attention Value (W) | ( ~4M) 4194304 | 4096 x 1024 x 1 x 1 | Q4_K | 4.5000 |
|
|
| 143 | blk.15.ffn_down.weight | Block 15 Feed-Forward Network "Down" (W) | (~52M) 52428800 | 12800 x 4096 x 1 x 1 | IQ3_S | 3.4375 |
|
|
| 144 | blk.15.ffn_gate.weight | Block 15 Feed-Forward Network "Gate" (W) | (~52M) 52428800 | 4096 x 12800 x 1 x 1 | IQ3_S | 3.4375 |
|
|
| 145 | blk.15.ffn_norm.weight | Block 15 Feed-Forward Network Normalization (W) | ( ~4K) 4096 | 4096 x 1 x 1 x 1 | F32 | 32.0000 |
|
|
| 146 | blk.15.ffn_up.weight | Block 15 Feed-Forward Network "Up" (W) | (~52M) 52428800 | 4096 x 12800 x 1 x 1 | IQ3_S | 3.4375 |
|
|
|
|
- Total elements in blk.15: (~199M) 199237632
|
|
- Percentage of total elements: 2.27%
|
|
- Bits per Weight (BPW) for blk.15: 3.5295 bits
|
|
|
|
|
|
### <a name="blk_16">Block 16 Tensor Group : ~199M Elements</a>
|
|
|
|
| T_ID | Tensor Layer Name | Human Friendly Tensor Layer Name | Elements | Shape | Type | BPW |
|
|
|-----:|:--------------------------|:------------------------------------------------|:----------------|:----------------------|:--------|--------:|
|
|
| 147 | blk.16.attn_k.weight | Block 16 Attention Key (W) | ( ~4M) 4194304 | 4096 x 1024 x 1 x 1 | IQ3_S | 3.4375 |
|
|
| 148 | blk.16.attn_norm.weight | Block 16 Attention Normalization (W) | ( ~4K) 4096 | 4096 x 1 x 1 x 1 | F32 | 32.0000 |
|
|
| 149 | blk.16.attn_output.weight | Block 16 Attention Output (W) | (~17M) 16777216 | 4096 x 4096 x 1 x 1 | IQ4_XS | 4.2500 |
|
|
| 150 | blk.16.attn_q.weight | Block 16 Attention Query (W) | (~17M) 16777216 | 4096 x 4096 x 1 x 1 | IQ3_S | 3.4375 |
|
|
| 151 | blk.16.attn_v.weight | Block 16 Attention Value (W) | ( ~4M) 4194304 | 4096 x 1024 x 1 x 1 | Q4_K | 4.5000 |
|
|
| 152 | blk.16.ffn_down.weight | Block 16 Feed-Forward Network "Down" (W) | (~52M) 52428800 | 12800 x 4096 x 1 x 1 | IQ3_S | 3.4375 |
|
|
| 153 | blk.16.ffn_gate.weight | Block 16 Feed-Forward Network "Gate" (W) | (~52M) 52428800 | 4096 x 12800 x 1 x 1 | IQ3_XXS | 3.0625 |
|
|
| 154 | blk.16.ffn_norm.weight | Block 16 Feed-Forward Network Normalization (W) | ( ~4K) 4096 | 4096 x 1 x 1 x 1 | F32 | 32.0000 |
|
|
| 155 | blk.16.ffn_up.weight | Block 16 Feed-Forward Network "Up" (W) | (~52M) 52428800 | 4096 x 12800 x 1 x 1 | IQ3_S | 3.4375 |
|
|
|
|
- Total elements in blk.16: (~199M) 199237632
|
|
- Percentage of total elements: 2.27%
|
|
- Bits per Weight (BPW) for blk.16: 3.4308 bits
|
|
|
|
|
|
### <a name="blk_17">Block 17 Tensor Group : ~199M Elements</a>
|
|
|
|
| T_ID | Tensor Layer Name | Human Friendly Tensor Layer Name | Elements | Shape | Type | BPW |
|
|
|-----:|:--------------------------|:------------------------------------------------|:----------------|:----------------------|:--------|--------:|
|
|
| 156 | blk.17.attn_k.weight | Block 17 Attention Key (W) | ( ~4M) 4194304 | 4096 x 1024 x 1 x 1 | IQ3_S | 3.4375 |
|
|
| 157 | blk.17.attn_norm.weight | Block 17 Attention Normalization (W) | ( ~4K) 4096 | 4096 x 1 x 1 x 1 | F32 | 32.0000 |
|
|
| 158 | blk.17.attn_output.weight | Block 17 Attention Output (W) | (~17M) 16777216 | 4096 x 4096 x 1 x 1 | IQ4_XS | 4.2500 |
|
|
| 159 | blk.17.attn_q.weight | Block 17 Attention Query (W) | (~17M) 16777216 | 4096 x 4096 x 1 x 1 | IQ3_S | 3.4375 |
|
|
| 160 | blk.17.attn_v.weight | Block 17 Attention Value (W) | ( ~4M) 4194304 | 4096 x 1024 x 1 x 1 | Q4_K | 4.5000 |
|
|
| 161 | blk.17.ffn_down.weight | Block 17 Feed-Forward Network "Down" (W) | (~52M) 52428800 | 12800 x 4096 x 1 x 1 | IQ3_S | 3.4375 |
|
|
| 162 | blk.17.ffn_gate.weight | Block 17 Feed-Forward Network "Gate" (W) | (~52M) 52428800 | 4096 x 12800 x 1 x 1 | IQ3_XXS | 3.0625 |
|
|
| 163 | blk.17.ffn_norm.weight | Block 17 Feed-Forward Network Normalization (W) | ( ~4K) 4096 | 4096 x 1 x 1 x 1 | F32 | 32.0000 |
|
|
| 164 | blk.17.ffn_up.weight | Block 17 Feed-Forward Network "Up" (W) | (~52M) 52428800 | 4096 x 12800 x 1 x 1 | IQ3_S | 3.4375 |
|
|
|
|
- Total elements in blk.17: (~199M) 199237632
|
|
- Percentage of total elements: 2.27%
|
|
- Bits per Weight (BPW) for blk.17: 3.4308 bits
|
|
|
|
|
|
### <a name="blk_18">Block 18 Tensor Group : ~199M Elements</a>
|
|
|
|
| T_ID | Tensor Layer Name | Human Friendly Tensor Layer Name | Elements | Shape | Type | BPW |
|
|
|-----:|:--------------------------|:------------------------------------------------|:----------------|:----------------------|:--------|--------:|
|
|
| 165 | blk.18.attn_k.weight | Block 18 Attention Key (W) | ( ~4M) 4194304 | 4096 x 1024 x 1 x 1 | IQ3_S | 3.4375 |
|
|
| 166 | blk.18.attn_norm.weight | Block 18 Attention Normalization (W) | ( ~4K) 4096 | 4096 x 1 x 1 x 1 | F32 | 32.0000 |
|
|
| 167 | blk.18.attn_output.weight | Block 18 Attention Output (W) | (~17M) 16777216 | 4096 x 4096 x 1 x 1 | IQ4_XS | 4.2500 |
|
|
| 168 | blk.18.attn_q.weight | Block 18 Attention Query (W) | (~17M) 16777216 | 4096 x 4096 x 1 x 1 | IQ3_S | 3.4375 |
|
|
| 169 | blk.18.attn_v.weight | Block 18 Attention Value (W) | ( ~4M) 4194304 | 4096 x 1024 x 1 x 1 | Q4_K | 4.5000 |
|
|
| 170 | blk.18.ffn_down.weight | Block 18 Feed-Forward Network "Down" (W) | (~52M) 52428800 | 12800 x 4096 x 1 x 1 | IQ3_S | 3.4375 |
|
|
| 171 | blk.18.ffn_gate.weight | Block 18 Feed-Forward Network "Gate" (W) | (~52M) 52428800 | 4096 x 12800 x 1 x 1 | IQ3_XXS | 3.0625 |
|
|
| 172 | blk.18.ffn_norm.weight | Block 18 Feed-Forward Network Normalization (W) | ( ~4K) 4096 | 4096 x 1 x 1 x 1 | F32 | 32.0000 |
|
|
| 173 | blk.18.ffn_up.weight | Block 18 Feed-Forward Network "Up" (W) | (~52M) 52428800 | 4096 x 12800 x 1 x 1 | IQ3_S | 3.4375 |
|
|
|
|
- Total elements in blk.18: (~199M) 199237632
|
|
- Percentage of total elements: 2.27%
|
|
- Bits per Weight (BPW) for blk.18: 3.4308 bits
|
|
|
|
|
|
### <a name="blk_19">Block 19 Tensor Group : ~199M Elements</a>
|
|
|
|
| T_ID | Tensor Layer Name | Human Friendly Tensor Layer Name | Elements | Shape | Type | BPW |
|
|
|-----:|:--------------------------|:------------------------------------------------|:----------------|:----------------------|:--------|--------:|
|
|
| 174 | blk.19.attn_k.weight | Block 19 Attention Key (W) | ( ~4M) 4194304 | 4096 x 1024 x 1 x 1 | IQ3_S | 3.4375 |
|
|
| 175 | blk.19.attn_norm.weight | Block 19 Attention Normalization (W) | ( ~4K) 4096 | 4096 x 1 x 1 x 1 | F32 | 32.0000 |
|
|
| 176 | blk.19.attn_output.weight | Block 19 Attention Output (W) | (~17M) 16777216 | 4096 x 4096 x 1 x 1 | IQ4_XS | 4.2500 |
|
|
| 177 | blk.19.attn_q.weight | Block 19 Attention Query (W) | (~17M) 16777216 | 4096 x 4096 x 1 x 1 | IQ3_S | 3.4375 |
|
|
| 178 | blk.19.attn_v.weight | Block 19 Attention Value (W) | ( ~4M) 4194304 | 4096 x 1024 x 1 x 1 | Q4_K | 4.5000 |
|
|
| 179 | blk.19.ffn_down.weight | Block 19 Feed-Forward Network "Down" (W) | (~52M) 52428800 | 12800 x 4096 x 1 x 1 | IQ3_S | 3.4375 |
|
|
| 180 | blk.19.ffn_gate.weight | Block 19 Feed-Forward Network "Gate" (W) | (~52M) 52428800 | 4096 x 12800 x 1 x 1 | IQ3_XXS | 3.0625 |
|
|
| 181 | blk.19.ffn_norm.weight | Block 19 Feed-Forward Network Normalization (W) | ( ~4K) 4096 | 4096 x 1 x 1 x 1 | F32 | 32.0000 |
|
|
| 182 | blk.19.ffn_up.weight | Block 19 Feed-Forward Network "Up" (W) | (~52M) 52428800 | 4096 x 12800 x 1 x 1 | IQ3_S | 3.4375 |
|
|
|
|
- Total elements in blk.19: (~199M) 199237632
|
|
- Percentage of total elements: 2.27%
|
|
- Bits per Weight (BPW) for blk.19: 3.4308 bits
|
|
|
|
|
|
### <a name="blk_20">Block 20 Tensor Group : ~199M Elements</a>
|
|
|
|
| T_ID | Tensor Layer Name | Human Friendly Tensor Layer Name | Elements | Shape | Type | BPW |
|
|
|-----:|:--------------------------|:------------------------------------------------|:----------------|:----------------------|:--------|--------:|
|
|
| 183 | blk.20.attn_k.weight | Block 20 Attention Key (W) | ( ~4M) 4194304 | 4096 x 1024 x 1 x 1 | IQ3_S | 3.4375 |
|
|
| 184 | blk.20.attn_norm.weight | Block 20 Attention Normalization (W) | ( ~4K) 4096 | 4096 x 1 x 1 x 1 | F32 | 32.0000 |
|
|
| 185 | blk.20.attn_output.weight | Block 20 Attention Output (W) | (~17M) 16777216 | 4096 x 4096 x 1 x 1 | IQ4_XS | 4.2500 |
|
|
| 186 | blk.20.attn_q.weight | Block 20 Attention Query (W) | (~17M) 16777216 | 4096 x 4096 x 1 x 1 | IQ3_S | 3.4375 |
|
|
| 187 | blk.20.attn_v.weight | Block 20 Attention Value (W) | ( ~4M) 4194304 | 4096 x 1024 x 1 x 1 | Q4_K | 4.5000 |
|
|
| 188 | blk.20.ffn_down.weight | Block 20 Feed-Forward Network "Down" (W) | (~52M) 52428800 | 12800 x 4096 x 1 x 1 | IQ3_S | 3.4375 |
|
|
| 189 | blk.20.ffn_gate.weight | Block 20 Feed-Forward Network "Gate" (W) | (~52M) 52428800 | 4096 x 12800 x 1 x 1 | IQ3_XXS | 3.0625 |
|
|
| 190 | blk.20.ffn_norm.weight | Block 20 Feed-Forward Network Normalization (W) | ( ~4K) 4096 | 4096 x 1 x 1 x 1 | F32 | 32.0000 |
|
|
| 191 | blk.20.ffn_up.weight | Block 20 Feed-Forward Network "Up" (W) | (~52M) 52428800 | 4096 x 12800 x 1 x 1 | IQ3_S | 3.4375 |
|
|
|
|
- Total elements in blk.20: (~199M) 199237632
|
|
- Percentage of total elements: 2.27%
|
|
- Bits per Weight (BPW) for blk.20: 3.4308 bits
|
|
|
|
|
|
### <a name="blk_21">Block 21 Tensor Group : ~199M Elements</a>
|
|
|
|
| T_ID | Tensor Layer Name | Human Friendly Tensor Layer Name | Elements | Shape | Type | BPW |
|
|
|-----:|:--------------------------|:------------------------------------------------|:----------------|:----------------------|:--------|--------:|
|
|
| 192 | blk.21.attn_k.weight | Block 21 Attention Key (W) | ( ~4M) 4194304 | 4096 x 1024 x 1 x 1 | IQ3_S | 3.4375 |
|
|
| 193 | blk.21.attn_norm.weight | Block 21 Attention Normalization (W) | ( ~4K) 4096 | 4096 x 1 x 1 x 1 | F32 | 32.0000 |
|
|
| 194 | blk.21.attn_output.weight | Block 21 Attention Output (W) | (~17M) 16777216 | 4096 x 4096 x 1 x 1 | IQ4_XS | 4.2500 |
|
|
| 195 | blk.21.attn_q.weight | Block 21 Attention Query (W) | (~17M) 16777216 | 4096 x 4096 x 1 x 1 | IQ3_S | 3.4375 |
|
|
| 196 | blk.21.attn_v.weight | Block 21 Attention Value (W) | ( ~4M) 4194304 | 4096 x 1024 x 1 x 1 | Q4_K | 4.5000 |
|
|
| 197 | blk.21.ffn_down.weight | Block 21 Feed-Forward Network "Down" (W) | (~52M) 52428800 | 12800 x 4096 x 1 x 1 | IQ3_S | 3.4375 |
|
|
| 198 | blk.21.ffn_gate.weight | Block 21 Feed-Forward Network "Gate" (W) | (~52M) 52428800 | 4096 x 12800 x 1 x 1 | IQ3_XXS | 3.0625 |
|
|
| 199 | blk.21.ffn_norm.weight | Block 21 Feed-Forward Network Normalization (W) | ( ~4K) 4096 | 4096 x 1 x 1 x 1 | F32 | 32.0000 |
|
|
| 200 | blk.21.ffn_up.weight | Block 21 Feed-Forward Network "Up" (W) | (~52M) 52428800 | 4096 x 12800 x 1 x 1 | IQ3_S | 3.4375 |
|
|
|
|
- Total elements in blk.21: (~199M) 199237632
|
|
- Percentage of total elements: 2.27%
|
|
- Bits per Weight (BPW) for blk.21: 3.4308 bits
|
|
|
|
|
|
### <a name="blk_22">Block 22 Tensor Group : ~199M Elements</a>
|
|
|
|
| T_ID | Tensor Layer Name | Human Friendly Tensor Layer Name | Elements | Shape | Type | BPW |
|
|
|-----:|:--------------------------|:------------------------------------------------|:----------------|:----------------------|:--------|--------:|
|
|
| 201 | blk.22.attn_k.weight | Block 22 Attention Key (W) | ( ~4M) 4194304 | 4096 x 1024 x 1 x 1 | IQ3_S | 3.4375 |
|
|
| 202 | blk.22.attn_norm.weight | Block 22 Attention Normalization (W) | ( ~4K) 4096 | 4096 x 1 x 1 x 1 | F32 | 32.0000 |
|
|
| 203 | blk.22.attn_output.weight | Block 22 Attention Output (W) | (~17M) 16777216 | 4096 x 4096 x 1 x 1 | IQ4_XS | 4.2500 |
|
|
| 204 | blk.22.attn_q.weight | Block 22 Attention Query (W) | (~17M) 16777216 | 4096 x 4096 x 1 x 1 | IQ3_S | 3.4375 |
|
|
| 205 | blk.22.attn_v.weight | Block 22 Attention Value (W) | ( ~4M) 4194304 | 4096 x 1024 x 1 x 1 | Q4_K | 4.5000 |
|
|
| 206 | blk.22.ffn_down.weight | Block 22 Feed-Forward Network "Down" (W) | (~52M) 52428800 | 12800 x 4096 x 1 x 1 | IQ3_S | 3.4375 |
|
|
| 207 | blk.22.ffn_gate.weight | Block 22 Feed-Forward Network "Gate" (W) | (~52M) 52428800 | 4096 x 12800 x 1 x 1 | IQ3_XXS | 3.0625 |
|
|
| 208 | blk.22.ffn_norm.weight | Block 22 Feed-Forward Network Normalization (W) | ( ~4K) 4096 | 4096 x 1 x 1 x 1 | F32 | 32.0000 |
|
|
| 209 | blk.22.ffn_up.weight | Block 22 Feed-Forward Network "Up" (W) | (~52M) 52428800 | 4096 x 12800 x 1 x 1 | IQ3_S | 3.4375 |
|
|
|
|
- Total elements in blk.22: (~199M) 199237632
|
|
- Percentage of total elements: 2.27%
|
|
- Bits per Weight (BPW) for blk.22: 3.4308 bits
|
|
|
|
|
|
### <a name="blk_23">Block 23 Tensor Group : ~199M Elements</a>
|
|
|
|
| T_ID | Tensor Layer Name | Human Friendly Tensor Layer Name | Elements | Shape | Type | BPW |
|
|
|-----:|:--------------------------|:------------------------------------------------|:----------------|:----------------------|:--------|--------:|
|
|
| 210 | blk.23.attn_k.weight | Block 23 Attention Key (W) | ( ~4M) 4194304 | 4096 x 1024 x 1 x 1 | IQ3_S | 3.4375 |
|
|
| 211 | blk.23.attn_norm.weight | Block 23 Attention Normalization (W) | ( ~4K) 4096 | 4096 x 1 x 1 x 1 | F32 | 32.0000 |
|
|
| 212 | blk.23.attn_output.weight | Block 23 Attention Output (W) | (~17M) 16777216 | 4096 x 4096 x 1 x 1 | IQ4_XS | 4.2500 |
|
|
| 213 | blk.23.attn_q.weight | Block 23 Attention Query (W) | (~17M) 16777216 | 4096 x 4096 x 1 x 1 | IQ3_S | 3.4375 |
|
|
| 214 | blk.23.attn_v.weight | Block 23 Attention Value (W) | ( ~4M) 4194304 | 4096 x 1024 x 1 x 1 | Q4_K | 4.5000 |
|
|
| 215 | blk.23.ffn_down.weight | Block 23 Feed-Forward Network "Down" (W) | (~52M) 52428800 | 12800 x 4096 x 1 x 1 | IQ3_S | 3.4375 |
|
|
| 216 | blk.23.ffn_gate.weight | Block 23 Feed-Forward Network "Gate" (W) | (~52M) 52428800 | 4096 x 12800 x 1 x 1 | IQ3_XXS | 3.0625 |
|
|
| 217 | blk.23.ffn_norm.weight | Block 23 Feed-Forward Network Normalization (W) | ( ~4K) 4096 | 4096 x 1 x 1 x 1 | F32 | 32.0000 |
|
|
| 218 | blk.23.ffn_up.weight | Block 23 Feed-Forward Network "Up" (W) | (~52M) 52428800 | 4096 x 12800 x 1 x 1 | IQ3_S | 3.4375 |
|
|
|
|
- Total elements in blk.23: (~199M) 199237632
|
|
- Percentage of total elements: 2.27%
|
|
- Bits per Weight (BPW) for blk.23: 3.4308 bits
|
|
|
|
|
|
### <a name="blk_24">Block 24 Tensor Group : ~199M Elements</a>
|
|
|
|
| T_ID | Tensor Layer Name | Human Friendly Tensor Layer Name | Elements | Shape | Type | BPW |
|
|
|-----:|:--------------------------|:------------------------------------------------|:----------------|:----------------------|:--------|--------:|
|
|
| 219 | blk.24.attn_k.weight | Block 24 Attention Key (W) | ( ~4M) 4194304 | 4096 x 1024 x 1 x 1 | IQ3_S | 3.4375 |
|
|
| 220 | blk.24.attn_norm.weight | Block 24 Attention Normalization (W) | ( ~4K) 4096 | 4096 x 1 x 1 x 1 | F32 | 32.0000 |
|
|
| 221 | blk.24.attn_output.weight | Block 24 Attention Output (W) | (~17M) 16777216 | 4096 x 4096 x 1 x 1 | IQ4_XS | 4.2500 |
|
|
| 222 | blk.24.attn_q.weight | Block 24 Attention Query (W) | (~17M) 16777216 | 4096 x 4096 x 1 x 1 | IQ3_S | 3.4375 |
|
|
| 223 | blk.24.attn_v.weight | Block 24 Attention Value (W) | ( ~4M) 4194304 | 4096 x 1024 x 1 x 1 | Q4_K | 4.5000 |
|
|
| 224 | blk.24.ffn_down.weight | Block 24 Feed-Forward Network "Down" (W) | (~52M) 52428800 | 12800 x 4096 x 1 x 1 | IQ3_S | 3.4375 |
|
|
| 225 | blk.24.ffn_gate.weight | Block 24 Feed-Forward Network "Gate" (W) | (~52M) 52428800 | 4096 x 12800 x 1 x 1 | IQ3_XXS | 3.0625 |
|
|
| 226 | blk.24.ffn_norm.weight | Block 24 Feed-Forward Network Normalization (W) | ( ~4K) 4096 | 4096 x 1 x 1 x 1 | F32 | 32.0000 |
|
|
| 227 | blk.24.ffn_up.weight | Block 24 Feed-Forward Network "Up" (W) | (~52M) 52428800 | 4096 x 12800 x 1 x 1 | IQ3_S | 3.4375 |
|
|
|
|
- Total elements in blk.24: (~199M) 199237632
|
|
- Percentage of total elements: 2.27%
|
|
- Bits per Weight (BPW) for blk.24: 3.4308 bits
|
|
|
|
|
|
### <a name="blk_25">Block 25 Tensor Group : ~199M Elements</a>
|
|
|
|
| T_ID | Tensor Layer Name | Human Friendly Tensor Layer Name | Elements | Shape | Type | BPW |
|
|
|-----:|:--------------------------|:------------------------------------------------|:----------------|:----------------------|:--------|--------:|
|
|
| 228 | blk.25.attn_k.weight | Block 25 Attention Key (W) | ( ~4M) 4194304 | 4096 x 1024 x 1 x 1 | IQ3_S | 3.4375 |
|
|
| 229 | blk.25.attn_norm.weight | Block 25 Attention Normalization (W) | ( ~4K) 4096 | 4096 x 1 x 1 x 1 | F32 | 32.0000 |
|
|
| 230 | blk.25.attn_output.weight | Block 25 Attention Output (W) | (~17M) 16777216 | 4096 x 4096 x 1 x 1 | IQ4_XS | 4.2500 |
|
|
| 231 | blk.25.attn_q.weight | Block 25 Attention Query (W) | (~17M) 16777216 | 4096 x 4096 x 1 x 1 | IQ3_S | 3.4375 |
|
|
| 232 | blk.25.attn_v.weight | Block 25 Attention Value (W) | ( ~4M) 4194304 | 4096 x 1024 x 1 x 1 | Q4_K | 4.5000 |
|
|
| 233 | blk.25.ffn_down.weight | Block 25 Feed-Forward Network "Down" (W) | (~52M) 52428800 | 12800 x 4096 x 1 x 1 | IQ3_S | 3.4375 |
|
|
| 234 | blk.25.ffn_gate.weight | Block 25 Feed-Forward Network "Gate" (W) | (~52M) 52428800 | 4096 x 12800 x 1 x 1 | IQ3_XXS | 3.0625 |
|
|
| 235 | blk.25.ffn_norm.weight | Block 25 Feed-Forward Network Normalization (W) | ( ~4K) 4096 | 4096 x 1 x 1 x 1 | F32 | 32.0000 |
|
|
| 236 | blk.25.ffn_up.weight | Block 25 Feed-Forward Network "Up" (W) | (~52M) 52428800 | 4096 x 12800 x 1 x 1 | IQ3_S | 3.4375 |
|
|
|
|
- Total elements in blk.25: (~199M) 199237632
|
|
- Percentage of total elements: 2.27%
|
|
- Bits per Weight (BPW) for blk.25: 3.4308 bits
|
|
|
|
|
|
### <a name="blk_26">Block 26 Tensor Group : ~199M Elements</a>
|
|
|
|
| T_ID | Tensor Layer Name | Human Friendly Tensor Layer Name | Elements | Shape | Type | BPW |
|
|
|-----:|:--------------------------|:------------------------------------------------|:----------------|:----------------------|:--------|--------:|
|
|
| 237 | blk.26.attn_k.weight | Block 26 Attention Key (W) | ( ~4M) 4194304 | 4096 x 1024 x 1 x 1 | IQ3_S | 3.4375 |
|
|
| 238 | blk.26.attn_norm.weight | Block 26 Attention Normalization (W) | ( ~4K) 4096 | 4096 x 1 x 1 x 1 | F32 | 32.0000 |
|
|
| 239 | blk.26.attn_output.weight | Block 26 Attention Output (W) | (~17M) 16777216 | 4096 x 4096 x 1 x 1 | IQ4_XS | 4.2500 |
|
|
| 240 | blk.26.attn_q.weight | Block 26 Attention Query (W) | (~17M) 16777216 | 4096 x 4096 x 1 x 1 | IQ3_S | 3.4375 |
|
|
| 241 | blk.26.attn_v.weight | Block 26 Attention Value (W) | ( ~4M) 4194304 | 4096 x 1024 x 1 x 1 | Q4_K | 4.5000 |
|
|
| 242 | blk.26.ffn_down.weight | Block 26 Feed-Forward Network "Down" (W) | (~52M) 52428800 | 12800 x 4096 x 1 x 1 | IQ3_S | 3.4375 |
|
|
| 243 | blk.26.ffn_gate.weight | Block 26 Feed-Forward Network "Gate" (W) | (~52M) 52428800 | 4096 x 12800 x 1 x 1 | IQ3_XXS | 3.0625 |
|
|
| 244 | blk.26.ffn_norm.weight | Block 26 Feed-Forward Network Normalization (W) | ( ~4K) 4096 | 4096 x 1 x 1 x 1 | F32 | 32.0000 |
|
|
| 245 | blk.26.ffn_up.weight | Block 26 Feed-Forward Network "Up" (W) | (~52M) 52428800 | 4096 x 12800 x 1 x 1 | IQ3_S | 3.4375 |
|
|
|
|
- Total elements in blk.26: (~199M) 199237632
|
|
- Percentage of total elements: 2.27%
|
|
- Bits per Weight (BPW) for blk.26: 3.4308 bits
|
|
|
|
|
|
### <a name="blk_27">Block 27 Tensor Group : ~199M Elements</a>
|
|
|
|
| T_ID | Tensor Layer Name | Human Friendly Tensor Layer Name | Elements | Shape | Type | BPW |
|
|
|-----:|:--------------------------|:------------------------------------------------|:----------------|:----------------------|:-------|--------:|
|
|
| 246 | blk.27.attn_k.weight | Block 27 Attention Key (W) | ( ~4M) 4194304 | 4096 x 1024 x 1 x 1 | IQ3_S | 3.4375 |
|
|
| 247 | blk.27.attn_norm.weight | Block 27 Attention Normalization (W) | ( ~4K) 4096 | 4096 x 1 x 1 x 1 | F32 | 32.0000 |
|
|
| 248 | blk.27.attn_output.weight | Block 27 Attention Output (W) | (~17M) 16777216 | 4096 x 4096 x 1 x 1 | IQ4_XS | 4.2500 |
|
|
| 249 | blk.27.attn_q.weight | Block 27 Attention Query (W) | (~17M) 16777216 | 4096 x 4096 x 1 x 1 | IQ3_S | 3.4375 |
|
|
| 250 | blk.27.attn_v.weight | Block 27 Attention Value (W) | ( ~4M) 4194304 | 4096 x 1024 x 1 x 1 | Q4_K | 4.5000 |
|
|
| 251 | blk.27.ffn_down.weight | Block 27 Feed-Forward Network "Down" (W) | (~52M) 52428800 | 12800 x 4096 x 1 x 1 | IQ3_S | 3.4375 |
|
|
| 252 | blk.27.ffn_gate.weight | Block 27 Feed-Forward Network "Gate" (W) | (~52M) 52428800 | 4096 x 12800 x 1 x 1 | IQ3_S | 3.4375 |
|
|
| 253 | blk.27.ffn_norm.weight | Block 27 Feed-Forward Network Normalization (W) | ( ~4K) 4096 | 4096 x 1 x 1 x 1 | F32 | 32.0000 |
|
|
| 254 | blk.27.ffn_up.weight | Block 27 Feed-Forward Network "Up" (W) | (~52M) 52428800 | 4096 x 12800 x 1 x 1 | IQ3_S | 3.4375 |
|
|
|
|
- Total elements in blk.27: (~199M) 199237632
|
|
- Percentage of total elements: 2.27%
|
|
- Bits per Weight (BPW) for blk.27: 3.5295 bits
|
|
|
|
|
|
### <a name="blk_28">Block 28 Tensor Group : ~199M Elements</a>
|
|
|
|
| T_ID | Tensor Layer Name | Human Friendly Tensor Layer Name | Elements | Shape | Type | BPW |
|
|
|-----:|:--------------------------|:------------------------------------------------|:----------------|:----------------------|:-------|--------:|
|
|
| 255 | blk.28.attn_k.weight | Block 28 Attention Key (W) | ( ~4M) 4194304 | 4096 x 1024 x 1 x 1 | IQ3_S | 3.4375 |
|
|
| 256 | blk.28.attn_norm.weight | Block 28 Attention Normalization (W) | ( ~4K) 4096 | 4096 x 1 x 1 x 1 | F32 | 32.0000 |
|
|
| 257 | blk.28.attn_output.weight | Block 28 Attention Output (W) | (~17M) 16777216 | 4096 x 4096 x 1 x 1 | IQ4_XS | 4.2500 |
|
|
| 258 | blk.28.attn_q.weight | Block 28 Attention Query (W) | (~17M) 16777216 | 4096 x 4096 x 1 x 1 | IQ3_S | 3.4375 |
|
|
| 259 | blk.28.attn_v.weight | Block 28 Attention Value (W) | ( ~4M) 4194304 | 4096 x 1024 x 1 x 1 | Q4_K | 4.5000 |
|
|
| 260 | blk.28.ffn_down.weight | Block 28 Feed-Forward Network "Down" (W) | (~52M) 52428800 | 12800 x 4096 x 1 x 1 | IQ3_S | 3.4375 |
|
|
| 261 | blk.28.ffn_gate.weight | Block 28 Feed-Forward Network "Gate" (W) | (~52M) 52428800 | 4096 x 12800 x 1 x 1 | IQ3_S | 3.4375 |
|
|
| 262 | blk.28.ffn_norm.weight | Block 28 Feed-Forward Network Normalization (W) | ( ~4K) 4096 | 4096 x 1 x 1 x 1 | F32 | 32.0000 |
|
|
| 263 | blk.28.ffn_up.weight | Block 28 Feed-Forward Network "Up" (W) | (~52M) 52428800 | 4096 x 12800 x 1 x 1 | IQ3_S | 3.4375 |
|
|
|
|
- Total elements in blk.28: (~199M) 199237632
|
|
- Percentage of total elements: 2.27%
|
|
- Bits per Weight (BPW) for blk.28: 3.5295 bits
|
|
|
|
|
|
### <a name="blk_29">Block 29 Tensor Group : ~199M Elements</a>
|
|
|
|
| T_ID | Tensor Layer Name | Human Friendly Tensor Layer Name | Elements | Shape | Type | BPW |
|
|
|-----:|:--------------------------|:------------------------------------------------|:----------------|:----------------------|:-------|--------:|
|
|
| 264 | blk.29.attn_k.weight | Block 29 Attention Key (W) | ( ~4M) 4194304 | 4096 x 1024 x 1 x 1 | IQ3_S | 3.4375 |
|
|
| 265 | blk.29.attn_norm.weight | Block 29 Attention Normalization (W) | ( ~4K) 4096 | 4096 x 1 x 1 x 1 | F32 | 32.0000 |
|
|
| 266 | blk.29.attn_output.weight | Block 29 Attention Output (W) | (~17M) 16777216 | 4096 x 4096 x 1 x 1 | IQ4_XS | 4.2500 |
|
|
| 267 | blk.29.attn_q.weight | Block 29 Attention Query (W) | (~17M) 16777216 | 4096 x 4096 x 1 x 1 | IQ3_S | 3.4375 |
|
|
| 268 | blk.29.attn_v.weight | Block 29 Attention Value (W) | ( ~4M) 4194304 | 4096 x 1024 x 1 x 1 | Q4_K | 4.5000 |
|
|
| 269 | blk.29.ffn_down.weight | Block 29 Feed-Forward Network "Down" (W) | (~52M) 52428800 | 12800 x 4096 x 1 x 1 | IQ3_S | 3.4375 |
|
|
| 270 | blk.29.ffn_gate.weight | Block 29 Feed-Forward Network "Gate" (W) | (~52M) 52428800 | 4096 x 12800 x 1 x 1 | IQ3_S | 3.4375 |
|
|
| 271 | blk.29.ffn_norm.weight | Block 29 Feed-Forward Network Normalization (W) | ( ~4K) 4096 | 4096 x 1 x 1 x 1 | F32 | 32.0000 |
|
|
| 272 | blk.29.ffn_up.weight | Block 29 Feed-Forward Network "Up" (W) | (~52M) 52428800 | 4096 x 12800 x 1 x 1 | IQ3_S | 3.4375 |
|
|
|
|
- Total elements in blk.29: (~199M) 199237632
|
|
- Percentage of total elements: 2.27%
|
|
- Bits per Weight (BPW) for blk.29: 3.5295 bits
|
|
|
|
|
|
### <a name="blk_30">Block 30 Tensor Group : ~199M Elements</a>
|
|
|
|
| T_ID | Tensor Layer Name | Human Friendly Tensor Layer Name | Elements | Shape | Type | BPW |
|
|
|-----:|:--------------------------|:------------------------------------------------|:----------------|:----------------------|:-------|--------:|
|
|
| 273 | blk.30.attn_k.weight | Block 30 Attention Key (W) | ( ~4M) 4194304 | 4096 x 1024 x 1 x 1 | IQ3_S | 3.4375 |
|
|
| 274 | blk.30.attn_norm.weight | Block 30 Attention Normalization (W) | ( ~4K) 4096 | 4096 x 1 x 1 x 1 | F32 | 32.0000 |
|
|
| 275 | blk.30.attn_output.weight | Block 30 Attention Output (W) | (~17M) 16777216 | 4096 x 4096 x 1 x 1 | IQ4_XS | 4.2500 |
|
|
| 276 | blk.30.attn_q.weight | Block 30 Attention Query (W) | (~17M) 16777216 | 4096 x 4096 x 1 x 1 | IQ3_S | 3.4375 |
|
|
| 277 | blk.30.attn_v.weight | Block 30 Attention Value (W) | ( ~4M) 4194304 | 4096 x 1024 x 1 x 1 | Q4_K | 4.5000 |
|
|
| 278 | blk.30.ffn_down.weight | Block 30 Feed-Forward Network "Down" (W) | (~52M) 52428800 | 12800 x 4096 x 1 x 1 | IQ3_S | 3.4375 |
|
|
| 279 | blk.30.ffn_gate.weight | Block 30 Feed-Forward Network "Gate" (W) | (~52M) 52428800 | 4096 x 12800 x 1 x 1 | IQ3_S | 3.4375 |
|
|
| 280 | blk.30.ffn_norm.weight | Block 30 Feed-Forward Network Normalization (W) | ( ~4K) 4096 | 4096 x 1 x 1 x 1 | F32 | 32.0000 |
|
|
| 281 | blk.30.ffn_up.weight | Block 30 Feed-Forward Network "Up" (W) | (~52M) 52428800 | 4096 x 12800 x 1 x 1 | IQ3_S | 3.4375 |
|
|
|
|
- Total elements in blk.30: (~199M) 199237632
|
|
- Percentage of total elements: 2.27%
|
|
- Bits per Weight (BPW) for blk.30: 3.5295 bits
|
|
|
|
|
|
### <a name="blk_31">Block 31 Tensor Group : ~199M Elements</a>
|
|
|
|
| T_ID | Tensor Layer Name | Human Friendly Tensor Layer Name | Elements | Shape | Type | BPW |
|
|
|-----:|:--------------------------|:------------------------------------------------|:----------------|:----------------------|:-------|--------:|
|
|
| 282 | blk.31.attn_k.weight | Block 31 Attention Key (W) | ( ~4M) 4194304 | 4096 x 1024 x 1 x 1 | IQ3_S | 3.4375 |
|
|
| 283 | blk.31.attn_norm.weight | Block 31 Attention Normalization (W) | ( ~4K) 4096 | 4096 x 1 x 1 x 1 | F32 | 32.0000 |
|
|
| 284 | blk.31.attn_output.weight | Block 31 Attention Output (W) | (~17M) 16777216 | 4096 x 4096 x 1 x 1 | IQ4_XS | 4.2500 |
|
|
| 285 | blk.31.attn_q.weight | Block 31 Attention Query (W) | (~17M) 16777216 | 4096 x 4096 x 1 x 1 | IQ3_S | 3.4375 |
|
|
| 286 | blk.31.attn_v.weight | Block 31 Attention Value (W) | ( ~4M) 4194304 | 4096 x 1024 x 1 x 1 | Q4_K | 4.5000 |
|
|
| 287 | blk.31.ffn_down.weight | Block 31 Feed-Forward Network "Down" (W) | (~52M) 52428800 | 12800 x 4096 x 1 x 1 | IQ3_S | 3.4375 |
|
|
| 288 | blk.31.ffn_gate.weight | Block 31 Feed-Forward Network "Gate" (W) | (~52M) 52428800 | 4096 x 12800 x 1 x 1 | IQ3_S | 3.4375 |
|
|
| 289 | blk.31.ffn_norm.weight | Block 31 Feed-Forward Network Normalization (W) | ( ~4K) 4096 | 4096 x 1 x 1 x 1 | F32 | 32.0000 |
|
|
| 290 | blk.31.ffn_up.weight | Block 31 Feed-Forward Network "Up" (W) | (~52M) 52428800 | 4096 x 12800 x 1 x 1 | IQ3_S | 3.4375 |
|
|
|
|
- Total elements in blk.31: (~199M) 199237632
|
|
- Percentage of total elements: 2.27%
|
|
- Bits per Weight (BPW) for blk.31: 3.5295 bits
|
|
|
|
|
|
### <a name="blk_32">Block 32 Tensor Group : ~199M Elements</a>
|
|
|
|
| T_ID | Tensor Layer Name | Human Friendly Tensor Layer Name | Elements | Shape | Type | BPW |
|
|
|-----:|:--------------------------|:------------------------------------------------|:----------------|:----------------------|:-------|--------:|
|
|
| 291 | blk.32.attn_k.weight | Block 32 Attention Key (W) | ( ~4M) 4194304 | 4096 x 1024 x 1 x 1 | IQ3_S | 3.4375 |
|
|
| 292 | blk.32.attn_norm.weight | Block 32 Attention Normalization (W) | ( ~4K) 4096 | 4096 x 1 x 1 x 1 | F32 | 32.0000 |
|
|
| 293 | blk.32.attn_output.weight | Block 32 Attention Output (W) | (~17M) 16777216 | 4096 x 4096 x 1 x 1 | IQ4_XS | 4.2500 |
|
|
| 294 | blk.32.attn_q.weight | Block 32 Attention Query (W) | (~17M) 16777216 | 4096 x 4096 x 1 x 1 | IQ3_S | 3.4375 |
|
|
| 295 | blk.32.attn_v.weight | Block 32 Attention Value (W) | ( ~4M) 4194304 | 4096 x 1024 x 1 x 1 | Q4_K | 4.5000 |
|
|
| 296 | blk.32.ffn_down.weight | Block 32 Feed-Forward Network "Down" (W) | (~52M) 52428800 | 12800 x 4096 x 1 x 1 | IQ3_S | 3.4375 |
|
|
| 297 | blk.32.ffn_gate.weight | Block 32 Feed-Forward Network "Gate" (W) | (~52M) 52428800 | 4096 x 12800 x 1 x 1 | IQ3_S | 3.4375 |
|
|
| 298 | blk.32.ffn_norm.weight | Block 32 Feed-Forward Network Normalization (W) | ( ~4K) 4096 | 4096 x 1 x 1 x 1 | F32 | 32.0000 |
|
|
| 299 | blk.32.ffn_up.weight | Block 32 Feed-Forward Network "Up" (W) | (~52M) 52428800 | 4096 x 12800 x 1 x 1 | IQ3_S | 3.4375 |
|
|
|
|
- Total elements in blk.32: (~199M) 199237632
|
|
- Percentage of total elements: 2.27%
|
|
- Bits per Weight (BPW) for blk.32: 3.5295 bits
|
|
|
|
|
|
### <a name="blk_33">Block 33 Tensor Group : ~199M Elements</a>
|
|
|
|
| T_ID | Tensor Layer Name | Human Friendly Tensor Layer Name | Elements | Shape | Type | BPW |
|
|
|-----:|:--------------------------|:------------------------------------------------|:----------------|:----------------------|:-------|--------:|
|
|
| 300 | blk.33.attn_k.weight | Block 33 Attention Key (W) | ( ~4M) 4194304 | 4096 x 1024 x 1 x 1 | IQ3_S | 3.4375 |
|
|
| 301 | blk.33.attn_norm.weight | Block 33 Attention Normalization (W) | ( ~4K) 4096 | 4096 x 1 x 1 x 1 | F32 | 32.0000 |
|
|
| 302 | blk.33.attn_output.weight | Block 33 Attention Output (W) | (~17M) 16777216 | 4096 x 4096 x 1 x 1 | IQ4_XS | 4.2500 |
|
|
| 303 | blk.33.attn_q.weight | Block 33 Attention Query (W) | (~17M) 16777216 | 4096 x 4096 x 1 x 1 | IQ3_S | 3.4375 |
|
|
| 304 | blk.33.attn_v.weight | Block 33 Attention Value (W) | ( ~4M) 4194304 | 4096 x 1024 x 1 x 1 | Q4_K | 4.5000 |
|
|
| 305 | blk.33.ffn_down.weight | Block 33 Feed-Forward Network "Down" (W) | (~52M) 52428800 | 12800 x 4096 x 1 x 1 | IQ3_S | 3.4375 |
|
|
| 306 | blk.33.ffn_gate.weight | Block 33 Feed-Forward Network "Gate" (W) | (~52M) 52428800 | 4096 x 12800 x 1 x 1 | IQ3_S | 3.4375 |
|
|
| 307 | blk.33.ffn_norm.weight | Block 33 Feed-Forward Network Normalization (W) | ( ~4K) 4096 | 4096 x 1 x 1 x 1 | F32 | 32.0000 |
|
|
| 308 | blk.33.ffn_up.weight | Block 33 Feed-Forward Network "Up" (W) | (~52M) 52428800 | 4096 x 12800 x 1 x 1 | IQ3_S | 3.4375 |
|
|
|
|
- Total elements in blk.33: (~199M) 199237632
|
|
- Percentage of total elements: 2.27%
|
|
- Bits per Weight (BPW) for blk.33: 3.5295 bits
|
|
|
|
|
|
### <a name="blk_34">Block 34 Tensor Group : ~199M Elements</a>
|
|
|
|
| T_ID | Tensor Layer Name | Human Friendly Tensor Layer Name | Elements | Shape | Type | BPW |
|
|
|-----:|:--------------------------|:------------------------------------------------|:----------------|:----------------------|:--------|--------:|
|
|
| 309 | blk.34.attn_k.weight | Block 34 Attention Key (W) | ( ~4M) 4194304 | 4096 x 1024 x 1 x 1 | IQ3_S | 3.4375 |
|
|
| 310 | blk.34.attn_norm.weight | Block 34 Attention Normalization (W) | ( ~4K) 4096 | 4096 x 1 x 1 x 1 | F32 | 32.0000 |
|
|
| 311 | blk.34.attn_output.weight | Block 34 Attention Output (W) | (~17M) 16777216 | 4096 x 4096 x 1 x 1 | IQ4_XS | 4.2500 |
|
|
| 312 | blk.34.attn_q.weight | Block 34 Attention Query (W) | (~17M) 16777216 | 4096 x 4096 x 1 x 1 | IQ3_S | 3.4375 |
|
|
| 313 | blk.34.attn_v.weight | Block 34 Attention Value (W) | ( ~4M) 4194304 | 4096 x 1024 x 1 x 1 | Q4_K | 4.5000 |
|
|
| 314 | blk.34.ffn_down.weight | Block 34 Feed-Forward Network "Down" (W) | (~52M) 52428800 | 12800 x 4096 x 1 x 1 | IQ3_S | 3.4375 |
|
|
| 315 | blk.34.ffn_gate.weight | Block 34 Feed-Forward Network "Gate" (W) | (~52M) 52428800 | 4096 x 12800 x 1 x 1 | IQ3_XXS | 3.0625 |
|
|
| 316 | blk.34.ffn_norm.weight | Block 34 Feed-Forward Network Normalization (W) | ( ~4K) 4096 | 4096 x 1 x 1 x 1 | F32 | 32.0000 |
|
|
| 317 | blk.34.ffn_up.weight | Block 34 Feed-Forward Network "Up" (W) | (~52M) 52428800 | 4096 x 12800 x 1 x 1 | IQ3_S | 3.4375 |
|
|
|
|
- Total elements in blk.34: (~199M) 199237632
|
|
- Percentage of total elements: 2.27%
|
|
- Bits per Weight (BPW) for blk.34: 3.4308 bits
|
|
|
|
|
|
### <a name="blk_35">Block 35 Tensor Group : ~199M Elements</a>
|
|
|
|
| T_ID | Tensor Layer Name | Human Friendly Tensor Layer Name | Elements | Shape | Type | BPW |
|
|
|-----:|:--------------------------|:------------------------------------------------|:----------------|:----------------------|:-------|--------:|
|
|
| 318 | blk.35.attn_k.weight | Block 35 Attention Key (W) | ( ~4M) 4194304 | 4096 x 1024 x 1 x 1 | IQ3_S | 3.4375 |
|
|
| 319 | blk.35.attn_norm.weight | Block 35 Attention Normalization (W) | ( ~4K) 4096 | 4096 x 1 x 1 x 1 | F32 | 32.0000 |
|
|
| 320 | blk.35.attn_output.weight | Block 35 Attention Output (W) | (~17M) 16777216 | 4096 x 4096 x 1 x 1 | IQ4_XS | 4.2500 |
|
|
| 321 | blk.35.attn_q.weight | Block 35 Attention Query (W) | (~17M) 16777216 | 4096 x 4096 x 1 x 1 | IQ3_S | 3.4375 |
|
|
| 322 | blk.35.attn_v.weight | Block 35 Attention Value (W) | ( ~4M) 4194304 | 4096 x 1024 x 1 x 1 | IQ4_XS | 4.2500 |
|
|
| 323 | blk.35.ffn_down.weight | Block 35 Feed-Forward Network "Down" (W) | (~52M) 52428800 | 12800 x 4096 x 1 x 1 | IQ3_S | 3.4375 |
|
|
| 324 | blk.35.ffn_gate.weight | Block 35 Feed-Forward Network "Gate" (W) | (~52M) 52428800 | 4096 x 12800 x 1 x 1 | IQ3_S | 3.4375 |
|
|
| 325 | blk.35.ffn_norm.weight | Block 35 Feed-Forward Network Normalization (W) | ( ~4K) 4096 | 4096 x 1 x 1 x 1 | F32 | 32.0000 |
|
|
| 326 | blk.35.ffn_up.weight | Block 35 Feed-Forward Network "Up" (W) | (~52M) 52428800 | 4096 x 12800 x 1 x 1 | IQ3_S | 3.4375 |
|
|
|
|
- Total elements in blk.35: (~199M) 199237632
|
|
- Percentage of total elements: 2.27%
|
|
- Bits per Weight (BPW) for blk.35: 3.5242 bits
|
|
|
|
|
|
### <a name="blk_36">Block 36 Tensor Group : ~199M Elements</a>
|
|
|
|
| T_ID | Tensor Layer Name | Human Friendly Tensor Layer Name | Elements | Shape | Type | BPW |
|
|
|-----:|:--------------------------|:------------------------------------------------|:----------------|:----------------------|:-------|--------:|
|
|
| 327 | blk.36.attn_k.weight | Block 36 Attention Key (W) | ( ~4M) 4194304 | 4096 x 1024 x 1 x 1 | IQ3_S | 3.4375 |
|
|
| 328 | blk.36.attn_norm.weight | Block 36 Attention Normalization (W) | ( ~4K) 4096 | 4096 x 1 x 1 x 1 | F32 | 32.0000 |
|
|
| 329 | blk.36.attn_output.weight | Block 36 Attention Output (W) | (~17M) 16777216 | 4096 x 4096 x 1 x 1 | IQ4_XS | 4.2500 |
|
|
| 330 | blk.36.attn_q.weight | Block 36 Attention Query (W) | (~17M) 16777216 | 4096 x 4096 x 1 x 1 | IQ3_S | 3.4375 |
|
|
| 331 | blk.36.attn_v.weight | Block 36 Attention Value (W) | ( ~4M) 4194304 | 4096 x 1024 x 1 x 1 | IQ4_XS | 4.2500 |
|
|
| 332 | blk.36.ffn_down.weight | Block 36 Feed-Forward Network "Down" (W) | (~52M) 52428800 | 12800 x 4096 x 1 x 1 | IQ3_S | 3.4375 |
|
|
| 333 | blk.36.ffn_gate.weight | Block 36 Feed-Forward Network "Gate" (W) | (~52M) 52428800 | 4096 x 12800 x 1 x 1 | IQ3_S | 3.4375 |
|
|
| 334 | blk.36.ffn_norm.weight | Block 36 Feed-Forward Network Normalization (W) | ( ~4K) 4096 | 4096 x 1 x 1 x 1 | F32 | 32.0000 |
|
|
| 335 | blk.36.ffn_up.weight | Block 36 Feed-Forward Network "Up" (W) | (~52M) 52428800 | 4096 x 12800 x 1 x 1 | IQ3_S | 3.4375 |
|
|
|
|
- Total elements in blk.36: (~199M) 199237632
|
|
- Percentage of total elements: 2.27%
|
|
- Bits per Weight (BPW) for blk.36: 3.5242 bits
|
|
|
|
|
|
### <a name="blk_37">Block 37 Tensor Group : ~199M Elements</a>
|
|
|
|
| T_ID | Tensor Layer Name | Human Friendly Tensor Layer Name | Elements | Shape | Type | BPW |
|
|
|-----:|:--------------------------|:------------------------------------------------|:----------------|:----------------------|:-------|--------:|
|
|
| 336 | blk.37.attn_k.weight | Block 37 Attention Key (W) | ( ~4M) 4194304 | 4096 x 1024 x 1 x 1 | IQ3_S | 3.4375 |
|
|
| 337 | blk.37.attn_norm.weight | Block 37 Attention Normalization (W) | ( ~4K) 4096 | 4096 x 1 x 1 x 1 | F32 | 32.0000 |
|
|
| 338 | blk.37.attn_output.weight | Block 37 Attention Output (W) | (~17M) 16777216 | 4096 x 4096 x 1 x 1 | IQ4_XS | 4.2500 |
|
|
| 339 | blk.37.attn_q.weight | Block 37 Attention Query (W) | (~17M) 16777216 | 4096 x 4096 x 1 x 1 | IQ3_S | 3.4375 |
|
|
| 340 | blk.37.attn_v.weight | Block 37 Attention Value (W) | ( ~4M) 4194304 | 4096 x 1024 x 1 x 1 | IQ4_XS | 4.2500 |
|
|
| 341 | blk.37.ffn_down.weight | Block 37 Feed-Forward Network "Down" (W) | (~52M) 52428800 | 12800 x 4096 x 1 x 1 | IQ3_S | 3.4375 |
|
|
| 342 | blk.37.ffn_gate.weight | Block 37 Feed-Forward Network "Gate" (W) | (~52M) 52428800 | 4096 x 12800 x 1 x 1 | IQ3_S | 3.4375 |
|
|
| 343 | blk.37.ffn_norm.weight | Block 37 Feed-Forward Network Normalization (W) | ( ~4K) 4096 | 4096 x 1 x 1 x 1 | F32 | 32.0000 |
|
|
| 344 | blk.37.ffn_up.weight | Block 37 Feed-Forward Network "Up" (W) | (~52M) 52428800 | 4096 x 12800 x 1 x 1 | IQ3_S | 3.4375 |
|
|
|
|
- Total elements in blk.37: (~199M) 199237632
|
|
- Percentage of total elements: 2.27%
|
|
- Bits per Weight (BPW) for blk.37: 3.5242 bits
|
|
|
|
|
|
### <a name="blk_38">Block 38 Tensor Group : ~199M Elements</a>
|
|
|
|
| T_ID | Tensor Layer Name | Human Friendly Tensor Layer Name | Elements | Shape | Type | BPW |
|
|
|-----:|:--------------------------|:------------------------------------------------|:----------------|:----------------------|:-------|--------:|
|
|
| 345 | blk.38.attn_k.weight | Block 38 Attention Key (W) | ( ~4M) 4194304 | 4096 x 1024 x 1 x 1 | IQ3_S | 3.4375 |
|
|
| 346 | blk.38.attn_norm.weight | Block 38 Attention Normalization (W) | ( ~4K) 4096 | 4096 x 1 x 1 x 1 | F32 | 32.0000 |
|
|
| 347 | blk.38.attn_output.weight | Block 38 Attention Output (W) | (~17M) 16777216 | 4096 x 4096 x 1 x 1 | IQ4_XS | 4.2500 |
|
|
| 348 | blk.38.attn_q.weight | Block 38 Attention Query (W) | (~17M) 16777216 | 4096 x 4096 x 1 x 1 | IQ3_S | 3.4375 |
|
|
| 349 | blk.38.attn_v.weight | Block 38 Attention Value (W) | ( ~4M) 4194304 | 4096 x 1024 x 1 x 1 | IQ4_XS | 4.2500 |
|
|
| 350 | blk.38.ffn_down.weight | Block 38 Feed-Forward Network "Down" (W) | (~52M) 52428800 | 12800 x 4096 x 1 x 1 | IQ3_S | 3.4375 |
|
|
| 351 | blk.38.ffn_gate.weight | Block 38 Feed-Forward Network "Gate" (W) | (~52M) 52428800 | 4096 x 12800 x 1 x 1 | IQ3_S | 3.4375 |
|
|
| 352 | blk.38.ffn_norm.weight | Block 38 Feed-Forward Network Normalization (W) | ( ~4K) 4096 | 4096 x 1 x 1 x 1 | F32 | 32.0000 |
|
|
| 353 | blk.38.ffn_up.weight | Block 38 Feed-Forward Network "Up" (W) | (~52M) 52428800 | 4096 x 12800 x 1 x 1 | IQ3_S | 3.4375 |
|
|
|
|
- Total elements in blk.38: (~199M) 199237632
|
|
- Percentage of total elements: 2.27%
|
|
- Bits per Weight (BPW) for blk.38: 3.5242 bits
|
|
|
|
|
|
### <a name="blk_39">Block 39 Tensor Group : ~199M Elements</a>
|
|
|
|
| T_ID | Tensor Layer Name | Human Friendly Tensor Layer Name | Elements | Shape | Type | BPW |
|
|
|-----:|:--------------------------|:------------------------------------------------|:----------------|:----------------------|:--------|--------:|
|
|
| 354 | blk.39.attn_k.weight | Block 39 Attention Key (W) | ( ~4M) 4194304 | 4096 x 1024 x 1 x 1 | IQ3_S | 3.4375 |
|
|
| 355 | blk.39.attn_norm.weight | Block 39 Attention Normalization (W) | ( ~4K) 4096 | 4096 x 1 x 1 x 1 | F32 | 32.0000 |
|
|
| 356 | blk.39.attn_output.weight | Block 39 Attention Output (W) | (~17M) 16777216 | 4096 x 4096 x 1 x 1 | IQ4_XS | 4.2500 |
|
|
| 357 | blk.39.attn_q.weight | Block 39 Attention Query (W) | (~17M) 16777216 | 4096 x 4096 x 1 x 1 | IQ3_S | 3.4375 |
|
|
| 358 | blk.39.attn_v.weight | Block 39 Attention Value (W) | ( ~4M) 4194304 | 4096 x 1024 x 1 x 1 | IQ4_XS | 4.2500 |
|
|
| 359 | blk.39.ffn_down.weight | Block 39 Feed-Forward Network "Down" (W) | (~52M) 52428800 | 12800 x 4096 x 1 x 1 | IQ3_XXS | 3.0625 |
|
|
| 360 | blk.39.ffn_gate.weight | Block 39 Feed-Forward Network "Gate" (W) | (~52M) 52428800 | 4096 x 12800 x 1 x 1 | IQ3_S | 3.4375 |
|
|
| 361 | blk.39.ffn_norm.weight | Block 39 Feed-Forward Network Normalization (W) | ( ~4K) 4096 | 4096 x 1 x 1 x 1 | F32 | 32.0000 |
|
|
| 362 | blk.39.ffn_up.weight | Block 39 Feed-Forward Network "Up" (W) | (~52M) 52428800 | 4096 x 12800 x 1 x 1 | IQ3_S | 3.4375 |
|
|
|
|
- Total elements in blk.39: (~199M) 199237632
|
|
- Percentage of total elements: 2.27%
|
|
- Bits per Weight (BPW) for blk.39: 3.4255 bits
|
|
|
|
|
|
Total BPW for granite-4.1-8b-Q3_K.gguf: 3.5000 bits
|