|
--- |
|
license: mit |
|
language: |
|
- nl |
|
tags: |
|
- gguf |
|
--- |
|
|
|
This repository contains quantized versions of [BramVanroy/fietje-2-chat](https://huggingface.co/BramVanroy/fietje-2-chat). |
|
|
|
Available quantization types and expected performance differences compared to base `f16`, higher perplexity=worse (from llama.cpp): |
|
|
|
``` |
|
Q3_K_M : 3.07G, +0.2496 ppl @ LLaMA-v1-7B |
|
Q4_K_M : 3.80G, +0.0532 ppl @ LLaMA-v1-7B |
|
Q5_K_M : 4.45G, +0.0122 ppl @ LLaMA-v1-7B |
|
Q6_K : 5.15G, +0.0008 ppl @ LLaMA-v1-7B |
|
Q8_0 : 6.70G, +0.0004 ppl @ LLaMA-v1-7B |
|
F16 : 13.00G @ 7B |
|
``` |
|
|
|
Also available on [ollama](https://ollama.com/bramvanroy/fietje-2b-chat). |
|
|
|
Quants were made with release [`b2777`](https://github.com/ggerganov/llama.cpp/releases/tag/b2777) of llama.cpp. |
|
|
