base_model:
- cognitivecomputations/dolphin-2.2-70b
- WizardLM/WizardMath-70B-V1.0
- migtissera/SynthIA-70B-v1.2b
- epfl-llm/meditron-70b
language:
- en
library_name: transformers
license: llama2
quantized_by: mradermacher
tags:
- mergekit
- merge
About
weighted/imatrix quants of https://huggingface.co/abacusai/TheProfessor-155b
static quants are available at https://huggingface.co/mradermacher/TheProfessor-155b-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-IQ1_S | 32.8 | for the desperate |
GGUF | i1-IQ2_XXS | 41.3 | |
GGUF | i1-IQ2_XS | 45.9 | |
PART 1 PART 2 | i1-IQ2_M | 52.3 | |
PART 1 PART 2 | i1-Q2_K | 57.1 | IQ3_XXS probably better |
PART 1 PART 2 | i1-IQ3_XXS | 60.6 | fast, lower quality |
PART 1 PART 2 | i1-Q3_K_XS | 63.2 | |
PART 1 PART 2 | i1-IQ3_XS | 63.3 | |
PART 1 PART 2 | i1-Q3_K_S | 66.9 | IQ3_XS probably better |
PART 1 PART 2 | i1-IQ3_S | 67.1 | fast, beats Q3_K* |
PART 1 PART 2 | i1-IQ3_M | 69.4 | |
PART 1 PART 2 | i1-Q3_K_M | 74.7 | IQ3_S probably better |
PART 1 PART 2 | i1-Q3_K_L | 81.3 | IQ3_M probably better |
PART 1 PART 2 | i1-Q4_K_S | 88.1 | optimal size/speed/quality |
PART 1 PART 2 | i1-Q4_K_M | 93.1 | fast, medium quality |
PART 1 PART 2 PART 3 | i1-Q5_K_S | 106.7 | |
PART 1 PART 2 PART 3 | i1-Q5_K_M | 109.6 | |
PART 1 PART 2 PART 3 | i1-Q6_K | 127.2 | 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.