# Codestral-22B-v0.1.Q6_K.gguf - GGUF Internal File Dump

- Endian: LITTLE endian

## Key Value Metadata Store

There are 28 key-value pairs in this file

| POS | TYPE      | Count | Key                                    | Value                                                |
|----:|:----------|------:|:---------------------------------------|:-----------------------------------------------------|
|   1 | UINT32    |     1 | GGUF.version                           | 3                                                    |
|   2 | UINT64    |     1 | GGUF.tensor_count                      | 507                                                  |
|   3 | UINT64    |     1 | GGUF.kv_count                          | 25                                                   |
|   4 | STRING    |     1 | general.architecture                   | `llama`                                              |
|   5 | STRING    |     1 | general.name                           | `Codestral-22B-v0.1-hf-FIM-fix`                      |
|   6 | UINT32    |     1 | llama.block_count                      | 56                                                   |
|   7 | UINT32    |     1 | llama.context_length                   | 32768                                                |
|   8 | UINT32    |     1 | llama.embedding_length                 | 6144                                                 |
|   9 | UINT32    |     1 | llama.feed_forward_length              | 16384                                                |
|  10 | UINT32    |     1 | llama.attention.head_count             | 48                                                   |
|  11 | UINT32    |     1 | llama.attention.head_count_kv          | 8                                                    |
|  12 | FLOAT32   |     1 | llama.rope.freq_base                   | 1000000.0                                            |
|  13 | FLOAT32   |     1 | llama.attention.layer_norm_rms_epsilon | 1e-05                                                |
|  14 | UINT32    |     1 | general.file_type                      | 18                                                   |
|  15 | UINT32    |     1 | llama.vocab_size                       | 32768                                                |
|  16 | UINT32    |     1 | llama.rope.dimension_count             | 128                                                  |
|  17 | BOOL      |     1 | tokenizer.ggml.add_space_prefix        | False                                                |
|  18 | STRING    |     1 | tokenizer.ggml.model                   | `llama`                                              |
|  19 | STRING    |     1 | tokenizer.ggml.pre                     | `default`                                            |
|  20 | [STRING]  | 32768 | tokenizer.ggml.tokens                  | [ `<unk>`, `<s>`, `</s>`, `[INST]`, `[/INST]`, ... ] |
|  21 | [FLOAT32] | 32768 | tokenizer.ggml.scores                  | [ 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, ... ]           |
|  22 | [INT32]   | 32768 | tokenizer.ggml.token_type              | [ 2, 3, 3, 3, 3, 3, 3, ... ]                         |
|  23 | UINT32    |     1 | tokenizer.ggml.bos_token_id            | 1                                                    |
|  24 | UINT32    |     1 | tokenizer.ggml.eos_token_id            | 2                                                    |
|  25 | UINT32    |     1 | tokenizer.ggml.unknown_token_id        | 0                                                    |
|  26 | BOOL      |     1 | tokenizer.ggml.add_bos_token           | True                                                 |
|  27 | BOOL      |     1 | tokenizer.ggml.add_eos_token           | False                                                |
|  28 | UINT32    |     1 | general.quantization_version           | 2                                                    |