base_model: ludis/tsukasa-120b-qlora
datasets:
- PygmalionAI/PIPPA
- lemonilia/LimaRP
language:
- en
library_name: transformers
no_imatrix: 'GGML_ASSERT: llama.cpp/ggml-quants.c:10645: grid_index >= 0'
quantized_by: mradermacher
About
weighted/imatrix quants of https://huggingface.co/ludis/tsukasa-120b-qlora
No more quants incoming, as llmama.cpp crashes when trying to generate them.
static quants are available at https://huggingface.co/mradermacher/tsukasa-120b-qlora-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-Q2_K | 43.3 | IQ3_XXS probably better |
| PART 1 PART 2 | i1-Q3_K_S | 50.8 | IQ3_XS probably better |
| PART 1 PART 2 | i1-Q3_K_M | 56.7 | IQ3_S probably better |
| PART 1 PART 2 | i1-Q3_K_L | 61.8 | IQ3_M probably better |
| PART 1 PART 2 | i1-Q4_K_S | 66.9 | optimal size/speed/quality |
| PART 1 PART 2 | i1-Q4_K_M | 70.7 | fast, recommended |
| PART 1 PART 2 | i1-Q5_K_S | 81.1 | |
| PART 1 PART 2 | i1-Q6_K | 96.7 | practically like static Q6_K |
| PART 1 PART 2 PART 3 | i1-Q8_0 | 125.2 | fast, best 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
FAQ / Model Request
See https://huggingface.co/mradermacher/model_requests for some answers to questions you might have and/or if you want some other model quantized.
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.