|
--- |
|
base_model: |
|
- cognitivecomputations/dolphin-2.2-70b |
|
- WizardLM/WizardMath-70B-V1.0 |
|
- migtissera/SynthIA-70B-v1.2b |
|
- epfl-llm/meditron-70b |
|
exported_from: abacusai/TheProfessor-155b |
|
language: |
|
- en |
|
library_name: transformers |
|
license: llama2 |
|
quantized_by: mradermacher |
|
tags: |
|
- mergekit |
|
- merge |
|
--- |
|
## About |
|
|
|
weighted/imatrix quants of https://huggingface.co/abacusai/TheProfessor-155b |
|
|
|
<!-- provided-files --> |
|
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](https://huggingface.co/TheBloke/KafkaLM-70B-German-V0.1-GGUF) 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](https://huggingface.co/mradermacher/TheProfessor-155b-i1-GGUF/resolve/main/TheProfessor-155b.i1-IQ1_S.gguf) | i1-IQ1_S | 32.8 | for the desperate | |
|
| [GGUF](https://huggingface.co/mradermacher/TheProfessor-155b-i1-GGUF/resolve/main/TheProfessor-155b.i1-IQ2_XXS.gguf) | i1-IQ2_XXS | 41.3 | | |
|
| [GGUF](https://huggingface.co/mradermacher/TheProfessor-155b-i1-GGUF/resolve/main/TheProfessor-155b.i1-IQ2_XS.gguf) | i1-IQ2_XS | 45.9 | | |
|
| [GGUF](https://huggingface.co/mradermacher/TheProfessor-155b-i1-GGUF/resolve/main/TheProfessor-155b.i1-IQ2_S.gguf) | i1-IQ2_S | 48.1 | | |
|
| [PART 1](https://huggingface.co/mradermacher/TheProfessor-155b-i1-GGUF/resolve/main/TheProfessor-155b.i1-IQ2_M.gguf.part1of2) [PART 2](https://huggingface.co/mradermacher/TheProfessor-155b-i1-GGUF/resolve/main/TheProfessor-155b.i1-IQ2_M.gguf.part2of2) | i1-IQ2_M | 52.3 | | |
|
| [PART 1](https://huggingface.co/mradermacher/TheProfessor-155b-i1-GGUF/resolve/main/TheProfessor-155b.i1-Q2_K.gguf.split-aa) [PART 2](https://huggingface.co/mradermacher/TheProfessor-155b-i1-GGUF/resolve/main/TheProfessor-155b.i1-Q2_K.gguf.split-ab) | i1-Q2_K | 57.1 | IQ3_XXS probably better | |
|
| [PART 1](https://huggingface.co/mradermacher/TheProfessor-155b-i1-GGUF/resolve/main/TheProfessor-155b.i1-IQ3_XXS.gguf.split-aa) [PART 2](https://huggingface.co/mradermacher/TheProfessor-155b-i1-GGUF/resolve/main/TheProfessor-155b.i1-IQ3_XXS.gguf.split-ab) | i1-IQ3_XXS | 60.6 | lower quality | |
|
| [PART 1](https://huggingface.co/mradermacher/TheProfessor-155b-i1-GGUF/resolve/main/TheProfessor-155b.i1-Q3_K_XS.gguf.split-aa) [PART 2](https://huggingface.co/mradermacher/TheProfessor-155b-i1-GGUF/resolve/main/TheProfessor-155b.i1-Q3_K_XS.gguf.split-ab) | i1-Q3_K_XS | 63.2 | | |
|
| [PART 1](https://huggingface.co/mradermacher/TheProfessor-155b-i1-GGUF/resolve/main/TheProfessor-155b.i1-IQ3_XS.gguf.part1of2) [PART 2](https://huggingface.co/mradermacher/TheProfessor-155b-i1-GGUF/resolve/main/TheProfessor-155b.i1-IQ3_XS.gguf.part2of2) | i1-IQ3_XS | 63.3 | | |
|
| [PART 1](https://huggingface.co/mradermacher/TheProfessor-155b-i1-GGUF/resolve/main/TheProfessor-155b.i1-Q3_K_S.gguf.split-aa) [PART 2](https://huggingface.co/mradermacher/TheProfessor-155b-i1-GGUF/resolve/main/TheProfessor-155b.i1-Q3_K_S.gguf.split-ab) | i1-Q3_K_S | 66.9 | IQ3_XS probably better | |
|
| [PART 1](https://huggingface.co/mradermacher/TheProfessor-155b-i1-GGUF/resolve/main/TheProfessor-155b.i1-IQ3_S.gguf.part1of2) [PART 2](https://huggingface.co/mradermacher/TheProfessor-155b-i1-GGUF/resolve/main/TheProfessor-155b.i1-IQ3_S.gguf.part2of2) | i1-IQ3_S | 67.1 | beats Q3_K* | |
|
| [PART 1](https://huggingface.co/mradermacher/TheProfessor-155b-i1-GGUF/resolve/main/TheProfessor-155b.i1-IQ3_M.gguf.part1of2) [PART 2](https://huggingface.co/mradermacher/TheProfessor-155b-i1-GGUF/resolve/main/TheProfessor-155b.i1-IQ3_M.gguf.part2of2) | i1-IQ3_M | 69.4 | | |
|
| [PART 1](https://huggingface.co/mradermacher/TheProfessor-155b-i1-GGUF/resolve/main/TheProfessor-155b.i1-Q3_K_M.gguf.split-aa) [PART 2](https://huggingface.co/mradermacher/TheProfessor-155b-i1-GGUF/resolve/main/TheProfessor-155b.i1-Q3_K_M.gguf.split-ab) | i1-Q3_K_M | 74.7 | IQ3_S probably better | |
|
| [PART 1](https://huggingface.co/mradermacher/TheProfessor-155b-i1-GGUF/resolve/main/TheProfessor-155b.i1-Q3_K_L.gguf.split-aa) [PART 2](https://huggingface.co/mradermacher/TheProfessor-155b-i1-GGUF/resolve/main/TheProfessor-155b.i1-Q3_K_L.gguf.split-ab) | i1-Q3_K_L | 81.3 | IQ3_M probably better | |
|
| [PART 1](https://huggingface.co/mradermacher/TheProfessor-155b-i1-GGUF/resolve/main/TheProfessor-155b.i1-IQ4_XS.gguf.part1of2) [PART 2](https://huggingface.co/mradermacher/TheProfessor-155b-i1-GGUF/resolve/main/TheProfessor-155b.i1-IQ4_XS.gguf.part2of2) | i1-IQ4_XS | 82.8 | | |
|
| [PART 1](https://huggingface.co/mradermacher/TheProfessor-155b-i1-GGUF/resolve/main/TheProfessor-155b.i1-Q4_0.gguf.part1of2) [PART 2](https://huggingface.co/mradermacher/TheProfessor-155b-i1-GGUF/resolve/main/TheProfessor-155b.i1-Q4_0.gguf.part2of2) | i1-Q4_0 | 87.7 | | |
|
| [PART 1](https://huggingface.co/mradermacher/TheProfessor-155b-i1-GGUF/resolve/main/TheProfessor-155b.i1-Q4_K_S.gguf.split-aa) [PART 2](https://huggingface.co/mradermacher/TheProfessor-155b-i1-GGUF/resolve/main/TheProfessor-155b.i1-Q4_K_S.gguf.split-ab) | i1-Q4_K_S | 88.1 | optimal size/speed/quality | |
|
| [PART 1](https://huggingface.co/mradermacher/TheProfessor-155b-i1-GGUF/resolve/main/TheProfessor-155b.i1-Q4_K_M.gguf.split-aa) [PART 2](https://huggingface.co/mradermacher/TheProfessor-155b-i1-GGUF/resolve/main/TheProfessor-155b.i1-Q4_K_M.gguf.split-ab) | i1-Q4_K_M | 93.1 | fast, recommended | |
|
| [PART 1](https://huggingface.co/mradermacher/TheProfessor-155b-i1-GGUF/resolve/main/TheProfessor-155b.i1-Q5_K_S.gguf.part1of3) [PART 2](https://huggingface.co/mradermacher/TheProfessor-155b-i1-GGUF/resolve/main/TheProfessor-155b.i1-Q5_K_S.gguf.part2of3) [PART 3](https://huggingface.co/mradermacher/TheProfessor-155b-i1-GGUF/resolve/main/TheProfessor-155b.i1-Q5_K_S.gguf.part3of3) | i1-Q5_K_S | 106.7 | | |
|
| [PART 1](https://huggingface.co/mradermacher/TheProfessor-155b-i1-GGUF/resolve/main/TheProfessor-155b.i1-Q5_K_M.gguf.part1of3) [PART 2](https://huggingface.co/mradermacher/TheProfessor-155b-i1-GGUF/resolve/main/TheProfessor-155b.i1-Q5_K_M.gguf.part2of3) [PART 3](https://huggingface.co/mradermacher/TheProfessor-155b-i1-GGUF/resolve/main/TheProfessor-155b.i1-Q5_K_M.gguf.part3of3) | i1-Q5_K_M | 109.6 | | |
|
| [PART 1](https://huggingface.co/mradermacher/TheProfessor-155b-i1-GGUF/resolve/main/TheProfessor-155b.i1-Q6_K.gguf.part1of3) [PART 2](https://huggingface.co/mradermacher/TheProfessor-155b-i1-GGUF/resolve/main/TheProfessor-155b.i1-Q6_K.gguf.part2of3) [PART 3](https://huggingface.co/mradermacher/TheProfessor-155b-i1-GGUF/resolve/main/TheProfessor-155b.i1-Q6_K.gguf.part3of3) | 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): |
|
|
|
![image.png](https://www.nethype.de/huggingface_embed/quantpplgraph.png) |
|
|
|
And here are Artefact2's thoughts on the matter: |
|
https://gist.github.com/Artefact2/b5f810600771265fc1e39442288e8ec9 |
|
|
|
## Thanks |
|
|
|
I thank my company, [nethype GmbH](https://www.nethype.de/), for letting |
|
me use its servers and providing upgrades to my workstation to enable |
|
this work in my free time. |
|
|
|
<!-- end --> |
|
|