Commit
•
e4e1773
1
Parent(s):
efcb07b
auto-patch README.md
Browse files
README.md
CHANGED
|
@@ -1 +1,54 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
static quants of https://huggingface.co/saltlux/luxia-21.4b-alignment-v1.0
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
exported_from: saltlux/luxia-21.4b-alignment-v1.0
|
| 3 |
+
language:
|
| 4 |
+
- en
|
| 5 |
+
library_name: transformers
|
| 6 |
+
license: apache-2.0
|
| 7 |
+
quantized_by: mradermacher
|
| 8 |
+
---
|
| 9 |
+
## About
|
| 10 |
+
|
| 11 |
static quants of https://huggingface.co/saltlux/luxia-21.4b-alignment-v1.0
|
| 12 |
+
|
| 13 |
+
|
| 14 |
+
<!-- provided-files -->
|
| 15 |
+
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.
|
| 16 |
+
## Usage
|
| 17 |
+
|
| 18 |
+
If you are unsure how to use GGUF files, refer to one of [TheBloke's
|
| 19 |
+
READMEs](https://huggingface.co/TheBloke/KafkaLM-70B-German-V0.1-GGUF) for
|
| 20 |
+
more details, including on how to concatenate multi-part files.
|
| 21 |
+
|
| 22 |
+
## Provided Quants
|
| 23 |
+
|
| 24 |
+
(sorted by size, not necessarily quality. IQ-quants are often preferable over similar sized non-IQ quants)
|
| 25 |
+
|
| 26 |
+
| Link | Type | Size/GB | Notes |
|
| 27 |
+
|:-----|:-----|--------:|:------|
|
| 28 |
+
| [GGUF](https://huggingface.co/mradermacher/luxia-21.4b-alignment-v1.0-GGUF/resolve/main/luxia-21.4b-alignment-v1.0.Q2_K.gguf) | Q2_K | 8.9 | |
|
| 29 |
+
| [GGUF](https://huggingface.co/mradermacher/luxia-21.4b-alignment-v1.0-GGUF/resolve/main/luxia-21.4b-alignment-v1.0.Q3_K_S.gguf) | Q3_K_S | 10.2 | |
|
| 30 |
+
| [GGUF](https://huggingface.co/mradermacher/luxia-21.4b-alignment-v1.0-GGUF/resolve/main/luxia-21.4b-alignment-v1.0.Q3_K_M.gguf) | Q3_K_M | 11.2 | lower quality |
|
| 31 |
+
| [GGUF](https://huggingface.co/mradermacher/luxia-21.4b-alignment-v1.0-GGUF/resolve/main/luxia-21.4b-alignment-v1.0.Q3_K_L.gguf) | Q3_K_L | 12.1 | |
|
| 32 |
+
| [GGUF](https://huggingface.co/mradermacher/luxia-21.4b-alignment-v1.0-GGUF/resolve/main/luxia-21.4b-alignment-v1.0.Q4_K_S.gguf) | Q4_K_S | 13.0 | fast, recommended |
|
| 33 |
+
| [GGUF](https://huggingface.co/mradermacher/luxia-21.4b-alignment-v1.0-GGUF/resolve/main/luxia-21.4b-alignment-v1.0.Q4_K_M.gguf) | Q4_K_M | 13.7 | fast, recommended |
|
| 34 |
+
| [GGUF](https://huggingface.co/mradermacher/luxia-21.4b-alignment-v1.0-GGUF/resolve/main/luxia-21.4b-alignment-v1.0.Q5_K_S.gguf) | Q5_K_S | 15.6 | |
|
| 35 |
+
| [GGUF](https://huggingface.co/mradermacher/luxia-21.4b-alignment-v1.0-GGUF/resolve/main/luxia-21.4b-alignment-v1.0.Q5_K_M.gguf) | Q5_K_M | 15.9 | |
|
| 36 |
+
| [GGUF](https://huggingface.co/mradermacher/luxia-21.4b-alignment-v1.0-GGUF/resolve/main/luxia-21.4b-alignment-v1.0.Q6_K.gguf) | Q6_K | 18.3 | very good quality |
|
| 37 |
+
| [GGUF](https://huggingface.co/mradermacher/luxia-21.4b-alignment-v1.0-GGUF/resolve/main/luxia-21.4b-alignment-v1.0.Q8_0.gguf) | Q8_0 | 23.4 | fast, best quality |
|
| 38 |
+
|
| 39 |
+
|
| 40 |
+
Here is a handy graph by ikawrakow comparing some lower-quality quant
|
| 41 |
+
types (lower is better):
|
| 42 |
+
|
| 43 |
+
|
| 44 |
+
|
| 45 |
+
And here are Artefact2's thoughts on the matter:
|
| 46 |
+
https://gist.github.com/Artefact2/b5f810600771265fc1e39442288e8ec9
|
| 47 |
+
|
| 48 |
+
## Thanks
|
| 49 |
+
|
| 50 |
+
I thank my company, [nethype GmbH](https://www.nethype.de/), for letting
|
| 51 |
+
me use its servers and providing upgrades to my workstation to enable
|
| 52 |
+
this work in my free time.
|
| 53 |
+
|
| 54 |
+
<!-- end -->
|