mradermacher's picture
Upload README.md with huggingface_hub
6e5d5af verified
|
raw
history blame
2.68 kB
metadata
library_name: transformers

Weighted imatrix quantize of https://huggingface.co/sophosympatheia/Midnight-Rose-103B-v2.0.3

The weight was calculated using an experimental (potentially crappy) method that is iterative (thus the "i1"), using 270k semi-random english tokens.

Provided Quants

Link Type Size/GB Notes
GGUF i1-IQ2_XXS 27.6
GGUF i1-IQ2_XS 30.7
GGUF i1-Q2_K 38.2
GGUF i1-IQ3_XXS 40.5 fast, lower quality
GGUF i1-Q3_K_XS 42.3
GGUF i1-Q3_K_S 44.8
PART 1 PART 2 i1-Q3_K_M 49.9 lower quality
PART 1 PART 2 i1-Q3_K_L 54.4
PART 1 PART 2 i1-Q4_K_S 58.9 fast, medium quality
PART 1 PART 2 i1-Q4_K_M 62.2 fast, medium quality