language:
- en
library_name: transformers
license: llama2
model_type: llama
quantized_by: mradermacher
tags:
- shining-valiant
- valiant
- valiant-labs
- llama
- llama-2
- llama-2-chat
- 13b
About
weighted/imatrix quants of https://huggingface.co/ValiantLabs/ShiningValiantXS
static quants are available at https://huggingface.co/mradermacher/ShiningValiantXS-GGUF
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-Q3_K_S | 6.3 | IQ3_XS probably better |
| GGUF | i1-Q3_K_M | 7.0 | IQ3_S probably better |
| GGUF | i1-Q3_K_L | 7.6 | IQ3_M probably better |
| GGUF | i1-Q4_K_S | 8.0 | optimal size/speed/quality |
| GGUF | i1-Q4_K_M | 8.5 | fast, recommended |
| GGUF | i1-Q5_K_S | 9.6 | |
| GGUF | i1-Q6_K | 11.3 | practically like static Q6_K |
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
Thanks
I thank my company, nethype GmbH, for letting me use its servers and providing upgrades to my workstation to enable this work in my free time.