Commit
•
609d6db
1
Parent(s):
535af8e
auto-patch README.md
Browse files
README.md
CHANGED
|
@@ -1 +1,68 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
weighted/imatrix quants of https://huggingface.co/Undi95/Emerhyst-20B
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
exported_from: Undi95/Emerhyst-20B
|
| 3 |
+
language:
|
| 4 |
+
- en
|
| 5 |
+
library_name: transformers
|
| 6 |
+
license: cc-by-nc-4.0
|
| 7 |
+
quantized_by: mradermacher
|
| 8 |
+
tags:
|
| 9 |
+
- not-for-all-audiences
|
| 10 |
+
- nsfw
|
| 11 |
+
---
|
| 12 |
+
## About
|
| 13 |
+
|
| 14 |
weighted/imatrix quants of https://huggingface.co/Undi95/Emerhyst-20B
|
| 15 |
+
|
| 16 |
+
|
| 17 |
+
<!-- provided-files -->
|
| 18 |
+
static quants are available at https://huggingface.co/mradermacher/Emerhyst-20B-GGUF
|
| 19 |
+
## Usage
|
| 20 |
+
|
| 21 |
+
If you are unsure how to use GGUF files, refer to one of [TheBloke's
|
| 22 |
+
READMEs](https://huggingface.co/TheBloke/KafkaLM-70B-German-V0.1-GGUF) for
|
| 23 |
+
more details, including on how to concatenate multi-part files.
|
| 24 |
+
|
| 25 |
+
## Provided Quants
|
| 26 |
+
|
| 27 |
+
(sorted by size, not necessarily quality. IQ-quants are often preferable over similar sized non-IQ quants)
|
| 28 |
+
|
| 29 |
+
| Link | Type | Size/GB | Notes |
|
| 30 |
+
|:-----|:-----|--------:|:------|
|
| 31 |
+
| [GGUF](https://huggingface.co/mradermacher/Emerhyst-20B-i1-GGUF/resolve/main/Emerhyst-20B.i1-IQ1_S.gguf) | i1-IQ1_S | 4.7 | for the desperate |
|
| 32 |
+
| [GGUF](https://huggingface.co/mradermacher/Emerhyst-20B-i1-GGUF/resolve/main/Emerhyst-20B.i1-IQ2_XXS.gguf) | i1-IQ2_XXS | 5.7 | |
|
| 33 |
+
| [GGUF](https://huggingface.co/mradermacher/Emerhyst-20B-i1-GGUF/resolve/main/Emerhyst-20B.i1-IQ2_XS.gguf) | i1-IQ2_XS | 6.3 | |
|
| 34 |
+
| [GGUF](https://huggingface.co/mradermacher/Emerhyst-20B-i1-GGUF/resolve/main/Emerhyst-20B.i1-IQ2_S.gguf) | i1-IQ2_S | 6.7 | |
|
| 35 |
+
| [GGUF](https://huggingface.co/mradermacher/Emerhyst-20B-i1-GGUF/resolve/main/Emerhyst-20B.i1-IQ2_M.gguf) | i1-IQ2_M | 7.2 | |
|
| 36 |
+
| [GGUF](https://huggingface.co/mradermacher/Emerhyst-20B-i1-GGUF/resolve/main/Emerhyst-20B.i1-Q2_K.gguf) | i1-Q2_K | 7.7 | IQ3_XXS probably better |
|
| 37 |
+
| [GGUF](https://huggingface.co/mradermacher/Emerhyst-20B-i1-GGUF/resolve/main/Emerhyst-20B.i1-IQ3_XXS.gguf) | i1-IQ3_XXS | 7.9 | lower quality |
|
| 38 |
+
| [GGUF](https://huggingface.co/mradermacher/Emerhyst-20B-i1-GGUF/resolve/main/Emerhyst-20B.i1-IQ3_XS.gguf) | i1-IQ3_XS | 8.5 | |
|
| 39 |
+
| [GGUF](https://huggingface.co/mradermacher/Emerhyst-20B-i1-GGUF/resolve/main/Emerhyst-20B.i1-IQ3_S.gguf) | i1-IQ3_S | 9.0 | beats Q3_K* |
|
| 40 |
+
| [GGUF](https://huggingface.co/mradermacher/Emerhyst-20B-i1-GGUF/resolve/main/Emerhyst-20B.i1-Q3_K_S.gguf) | i1-Q3_K_S | 9.0 | IQ3_XS probably better |
|
| 41 |
+
| [GGUF](https://huggingface.co/mradermacher/Emerhyst-20B-i1-GGUF/resolve/main/Emerhyst-20B.i1-IQ3_M.gguf) | i1-IQ3_M | 9.4 | |
|
| 42 |
+
| [GGUF](https://huggingface.co/mradermacher/Emerhyst-20B-i1-GGUF/resolve/main/Emerhyst-20B.i1-Q3_K_M.gguf) | i1-Q3_K_M | 10.0 | IQ3_S probably better |
|
| 43 |
+
| [GGUF](https://huggingface.co/mradermacher/Emerhyst-20B-i1-GGUF/resolve/main/Emerhyst-20B.i1-Q3_K_L.gguf) | i1-Q3_K_L | 10.9 | IQ3_M probably better |
|
| 44 |
+
| [GGUF](https://huggingface.co/mradermacher/Emerhyst-20B-i1-GGUF/resolve/main/Emerhyst-20B.i1-IQ4_XS.gguf) | i1-IQ4_XS | 11.0 | |
|
| 45 |
+
| [GGUF](https://huggingface.co/mradermacher/Emerhyst-20B-i1-GGUF/resolve/main/Emerhyst-20B.i1-IQ4_NL.gguf) | i1-IQ4_NL | 11.6 | slightly worse than Q4_K_S |
|
| 46 |
+
| [GGUF](https://huggingface.co/mradermacher/Emerhyst-20B-i1-GGUF/resolve/main/Emerhyst-20B.i1-Q4_0.gguf) | i1-Q4_0 | 11.6 | |
|
| 47 |
+
| [GGUF](https://huggingface.co/mradermacher/Emerhyst-20B-i1-GGUF/resolve/main/Emerhyst-20B.i1-Q4_K_S.gguf) | i1-Q4_K_S | 11.7 | optimal size/speed/quality |
|
| 48 |
+
| [GGUF](https://huggingface.co/mradermacher/Emerhyst-20B-i1-GGUF/resolve/main/Emerhyst-20B.i1-Q4_K_M.gguf) | i1-Q4_K_M | 12.3 | fast, recommended |
|
| 49 |
+
| [GGUF](https://huggingface.co/mradermacher/Emerhyst-20B-i1-GGUF/resolve/main/Emerhyst-20B.i1-Q5_K_S.gguf) | i1-Q5_K_S | 14.1 | |
|
| 50 |
+
| [GGUF](https://huggingface.co/mradermacher/Emerhyst-20B-i1-GGUF/resolve/main/Emerhyst-20B.i1-Q5_K_M.gguf) | i1-Q5_K_M | 14.5 | |
|
| 51 |
+
| [GGUF](https://huggingface.co/mradermacher/Emerhyst-20B-i1-GGUF/resolve/main/Emerhyst-20B.i1-Q6_K.gguf) | i1-Q6_K | 16.7 | practically like static Q6_K |
|
| 52 |
+
|
| 53 |
+
|
| 54 |
+
Here is a handy graph by ikawrakow comparing some lower-quality quant
|
| 55 |
+
types (lower is better):
|
| 56 |
+
|
| 57 |
+
|
| 58 |
+
|
| 59 |
+
And here are Artefact2's thoughts on the matter:
|
| 60 |
+
https://gist.github.com/Artefact2/b5f810600771265fc1e39442288e8ec9
|
| 61 |
+
|
| 62 |
+
## Thanks
|
| 63 |
+
|
| 64 |
+
I thank my company, [nethype GmbH](https://www.nethype.de/), for letting
|
| 65 |
+
me use its servers and providing upgrades to my workstation to enable
|
| 66 |
+
this work in my free time.
|
| 67 |
+
|
| 68 |
+
<!-- end -->
|