metadata
language:
- en
library_name: transformers
license: llama2
quantized_by: mradermacher
About
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.
Usage
If you are unsure how to use GGUF files, refer to one of TheBloke's READMEs for more details, including on how to concatenate multi-part files.
Provided Quants
(sorted by size, not necessarily quality. IQ-quants are often preferable over similar sized non-IQ quants)
| Link | Type | Size/GB | Notes |
|---|---|---|---|
| GGUF | i1-IQ1_S | 22.0 | |
| GGUF | i1-IQ2_XXS | 27.6 | |
| GGUF | i1-IQ2_XS | 30.7 | |
| GGUF | i1-Q2_K | 38.2 | IQ3_XXS probably better |
| GGUF | i1-IQ3_XXS | 40.5 | fast, lower quality |
| GGUF | i1-Q3_K_XS | 42.3 | |
| GGUF | i1-Q3_K_S | 44.8 | IQ3_XS probably better |
| PART 1 PART 2 | i1-Q3_K_M | 49.9 | IQ3_S probably better |
| PART 1 PART 2 | i1-Q3_K_L | 54.4 | IQ3_M probably better |
| PART 1 PART 2 | i1-Q4_K_S | 58.9 | almost as good as Q4_K_M |
| PART 1 PART 2 | i1-Q4_K_M | 62.2 | fast, medium quality |
Here is a handy graph by ikawrakow comparing some lower-quality quant types (lower is better):
And here are Artefact2's thoughts on the matter: https://gist.github.com/Artefact2/b5f810600771265fc1e39442288e8ec9