mradermacher's picture
auto-patch README.md
b6618ff verified
|
raw
history blame
3.97 kB
---
base_model:
- Open-Orca/Mistral-7B-OpenOrca
- NeuralNovel/Mistral-7B-Instruct-v0.2-Neural-Story
- S-miguel/The-Trinity-Coder-7B
- chihoonlee10/T3Q-Mistral-Orca-Math-DPO
exported_from: jambroz/sixtyoneeighty-4x7B-v2
language:
- en
library_name: transformers
license: apache-2.0
quantized_by: mradermacher
tags:
- moe
- frankenmoe
- merge
- mergekit
- lazymergekit
- Open-Orca/Mistral-7B-OpenOrca
- NeuralNovel/Mistral-7B-Instruct-v0.2-Neural-Story
- S-miguel/The-Trinity-Coder-7B
- chihoonlee10/T3Q-Mistral-Orca-Math-DPO
---
## About
<!-- ### quantize_version: 1 -->
<!-- ### output_tensor_quantised: 1 -->
<!-- ### convert_type: -->
<!-- ### vocab_type: -->
static quants of https://huggingface.co/jambroz/sixtyoneeighty-4x7B-v2
<!-- provided-files -->
weighted/imatrix quants seem not to be available (by me) at this time. If they do not show up a week or so after the static ones, I have probably not planned for them. Feel free to request them by opening a Community Discussion.
## 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/sixtyoneeighty-4x7B-v2-GGUF/resolve/main/sixtyoneeighty-4x7B-v2.Q2_K.gguf) | Q2_K | 8.9 | |
| [GGUF](https://huggingface.co/mradermacher/sixtyoneeighty-4x7B-v2-GGUF/resolve/main/sixtyoneeighty-4x7B-v2.IQ3_XS.gguf) | IQ3_XS | 10.0 | |
| [GGUF](https://huggingface.co/mradermacher/sixtyoneeighty-4x7B-v2-GGUF/resolve/main/sixtyoneeighty-4x7B-v2.Q3_K_S.gguf) | Q3_K_S | 10.5 | |
| [GGUF](https://huggingface.co/mradermacher/sixtyoneeighty-4x7B-v2-GGUF/resolve/main/sixtyoneeighty-4x7B-v2.IQ3_S.gguf) | IQ3_S | 10.6 | beats Q3_K* |
| [GGUF](https://huggingface.co/mradermacher/sixtyoneeighty-4x7B-v2-GGUF/resolve/main/sixtyoneeighty-4x7B-v2.IQ3_M.gguf) | IQ3_M | 10.7 | |
| [GGUF](https://huggingface.co/mradermacher/sixtyoneeighty-4x7B-v2-GGUF/resolve/main/sixtyoneeighty-4x7B-v2.Q3_K_M.gguf) | Q3_K_M | 11.7 | lower quality |
| [GGUF](https://huggingface.co/mradermacher/sixtyoneeighty-4x7B-v2-GGUF/resolve/main/sixtyoneeighty-4x7B-v2.Q3_K_L.gguf) | Q3_K_L | 12.6 | |
| [GGUF](https://huggingface.co/mradermacher/sixtyoneeighty-4x7B-v2-GGUF/resolve/main/sixtyoneeighty-4x7B-v2.IQ4_XS.gguf) | IQ4_XS | 13.1 | |
| [GGUF](https://huggingface.co/mradermacher/sixtyoneeighty-4x7B-v2-GGUF/resolve/main/sixtyoneeighty-4x7B-v2.Q4_K_S.gguf) | Q4_K_S | 13.8 | fast, recommended |
| [GGUF](https://huggingface.co/mradermacher/sixtyoneeighty-4x7B-v2-GGUF/resolve/main/sixtyoneeighty-4x7B-v2.Q4_K_M.gguf) | Q4_K_M | 14.7 | fast, recommended |
| [GGUF](https://huggingface.co/mradermacher/sixtyoneeighty-4x7B-v2-GGUF/resolve/main/sixtyoneeighty-4x7B-v2.Q5_K_S.gguf) | Q5_K_S | 16.7 | |
| [GGUF](https://huggingface.co/mradermacher/sixtyoneeighty-4x7B-v2-GGUF/resolve/main/sixtyoneeighty-4x7B-v2.Q5_K_M.gguf) | Q5_K_M | 17.2 | |
| [GGUF](https://huggingface.co/mradermacher/sixtyoneeighty-4x7B-v2-GGUF/resolve/main/sixtyoneeighty-4x7B-v2.Q6_K.gguf) | Q6_K | 19.9 | very good quality |
| [GGUF](https://huggingface.co/mradermacher/sixtyoneeighty-4x7B-v2-GGUF/resolve/main/sixtyoneeighty-4x7B-v2.Q8_0.gguf) | Q8_0 | 25.8 | fast, best quality |
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 -->