65 lines
3.6 KiB
Markdown
65 lines
3.6 KiB
Markdown
---
|
|
base_model: gabrielmbmb/Upcycled-Qwen1.5-MoE2.7B
|
|
language:
|
|
- en
|
|
library_name: transformers
|
|
quantized_by: mradermacher
|
|
tags: []
|
|
---
|
|
## About
|
|
|
|
<!-- ### quantize_version: 2 -->
|
|
<!-- ### output_tensor_quantised: 1 -->
|
|
<!-- ### convert_type: hf -->
|
|
<!-- ### vocab_type: -->
|
|
<!-- ### tags: nicoboss -->
|
|
static quants of https://huggingface.co/gabrielmbmb/Upcycled-Qwen1.5-MoE2.7B
|
|
|
|
<!-- provided-files -->
|
|
weighted/imatrix quants are available at https://huggingface.co/mradermacher/Upcycled-Qwen1.5-MoE2.7B-i1-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/Upcycled-Qwen1.5-MoE2.7B-GGUF/resolve/main/Upcycled-Qwen1.5-MoE2.7B.Q2_K.gguf) | Q2_K | 5.9 | |
|
|
| [GGUF](https://huggingface.co/mradermacher/Upcycled-Qwen1.5-MoE2.7B-GGUF/resolve/main/Upcycled-Qwen1.5-MoE2.7B.Q3_K_S.gguf) | Q3_K_S | 6.8 | |
|
|
| [GGUF](https://huggingface.co/mradermacher/Upcycled-Qwen1.5-MoE2.7B-GGUF/resolve/main/Upcycled-Qwen1.5-MoE2.7B.Q3_K_M.gguf) | Q3_K_M | 7.4 | lower quality |
|
|
| [GGUF](https://huggingface.co/mradermacher/Upcycled-Qwen1.5-MoE2.7B-GGUF/resolve/main/Upcycled-Qwen1.5-MoE2.7B.Q3_K_L.gguf) | Q3_K_L | 7.7 | |
|
|
| [GGUF](https://huggingface.co/mradermacher/Upcycled-Qwen1.5-MoE2.7B-GGUF/resolve/main/Upcycled-Qwen1.5-MoE2.7B.IQ4_XS.gguf) | IQ4_XS | 7.9 | |
|
|
| [GGUF](https://huggingface.co/mradermacher/Upcycled-Qwen1.5-MoE2.7B-GGUF/resolve/main/Upcycled-Qwen1.5-MoE2.7B.Q4_0_4_4.gguf) | Q4_0_4_4 | 8.1 | fast on arm, low quality |
|
|
| [GGUF](https://huggingface.co/mradermacher/Upcycled-Qwen1.5-MoE2.7B-GGUF/resolve/main/Upcycled-Qwen1.5-MoE2.7B.Q4_K_S.gguf) | Q4_K_S | 8.7 | fast, recommended |
|
|
| [GGUF](https://huggingface.co/mradermacher/Upcycled-Qwen1.5-MoE2.7B-GGUF/resolve/main/Upcycled-Qwen1.5-MoE2.7B.Q4_K_M.gguf) | Q4_K_M | 9.4 | fast, recommended |
|
|
| [GGUF](https://huggingface.co/mradermacher/Upcycled-Qwen1.5-MoE2.7B-GGUF/resolve/main/Upcycled-Qwen1.5-MoE2.7B.Q5_K_S.gguf) | Q5_K_S | 10.1 | |
|
|
| [GGUF](https://huggingface.co/mradermacher/Upcycled-Qwen1.5-MoE2.7B-GGUF/resolve/main/Upcycled-Qwen1.5-MoE2.7B.Q5_K_M.gguf) | Q5_K_M | 10.7 | |
|
|
| [GGUF](https://huggingface.co/mradermacher/Upcycled-Qwen1.5-MoE2.7B-GGUF/resolve/main/Upcycled-Qwen1.5-MoE2.7B.Q6_K.gguf) | Q6_K | 12.7 | very good quality |
|
|
| [GGUF](https://huggingface.co/mradermacher/Upcycled-Qwen1.5-MoE2.7B-GGUF/resolve/main/Upcycled-Qwen1.5-MoE2.7B.Q8_0.gguf) | Q8_0 | 15.0 | 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](https://www.nethype.de/), for letting
|
|
me use its servers and providing upgrades to my workstation to enable
|
|
this work in my free time. Additional thanks to [@nicoboss](https://huggingface.co/nicoboss) for giving me access to his private supercomputer, enabling me to provide many more imatrix quants, at much higher quality, than I would otherwise be able to.
|
|
|
|
<!-- end -->
|