Koshkasa/TheDrummer_Snowpiercer-15B-v4-IQ5_K-GGUF overview

---

license: mit

base_model:

• TheDrummer/Snowpiercer-15B-v4

library_name: ik_llama.cpp

pipeline_tag: text-generation

tags:

• gguf
• quantized
• ik_llama.cpp
• iq5_k
• 5 bit
• roleplay
• mixed precision

quantized_by: Koshkasa

base_model_relation: quantized

---

What's that?

The goal: Q5_K_M+ quality (allegedly) at Q5_K_S size using SOTA quant types from ik_llama.cpp.

The result: Mixed precision quantization of TheDrummer/Big-Alice-28B-v1 utilizing IQ5_K for ffn and embeddings, and IQ6_K for output and attention.

quantized with ik_llama.cpp build: 9d07d868

imatrix by bartowski

incompatible with mainline llama.cpp

Layout

| Layer | Dims | Dims | Quant |

| --- | --- | --- | --- |

| token\_embd | 5120 | 131072.0 | iq5\_k |

| | | | |

| | blk| 50| |

| attn\_k | 5120 | 1024 | iq6\_k |

| attn\_norm | 5120 | 1 | f32 |

| attn\_q | 5120 | 4096 | iq6\_k |

| attn\_v | 5120 | 1024 | iq6\_k |

| attn\_output | 4096 | 5120 | iq6\_k |

| ffn\_down | 14336 | 5120 | iq5\_k |

| ffn\_gate | 5120 | 14336 | iq5\_k |

| ffn\_norm | 5120 | 1 | f32 |

| ffn\_up | 5120 | 14336 | iq5\_k |

| | | | |

| output | 5120 | 131072 | iq6\_k |

| output\_norm | 5120 | 1 | f32 |

Cheers

SillyTilly - for the base model.

TheDrummer - for the finetuned model.

bartowski - for the imatrix + the myriad of quants we all benefit from.

ikawrakow and contributors of ik_llama.cpp - I probably misused your ingenious creation.