Compare commits

...

10 Commits

Author SHA1 Message Date
Michael Radermacher
3076693ca7 auto-patch README.md 2024-09-21 13:45:05 +00:00
Michael Radermacher
77aae600d6 uploaded from nethype/db2 2024-09-21 13:44:01 +00:00
Michael Radermacher
c2ba1ab697 uploaded from nethype/db2 2024-09-21 13:33:13 +00:00
Michael Radermacher
7c02109e7a uploaded from nethype/db2 2024-09-21 13:28:59 +00:00
Michael Radermacher
ca05b1e42f uploaded from nethype/db2 2024-09-21 13:22:11 +00:00
Michael Radermacher
a753939467 uploaded from nethype/db2 2024-09-21 13:13:21 +00:00
Michael Radermacher
721df24f02 uploaded from nethype/db2 2024-09-21 13:07:37 +00:00
Michael Radermacher
578a498572 uploaded from nethype/db2 2024-09-21 12:47:38 +00:00
Michael Radermacher
2ce5eda216 uploaded from nethype/db2 2024-09-21 12:39:11 +00:00
Michael Radermacher
ace1fbd97f uploaded from nethype/db2 2024-09-21 12:24:52 +00:00
11 changed files with 105 additions and 0 deletions

9
.gitattributes vendored
View File

@@ -46,3 +46,12 @@ PsyMedLewd_V2.i1-IQ1_M.gguf filter=lfs diff=lfs merge=lfs -text
PsyMedLewd_V2.i1-IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text
PsyMedLewd_V2.i1-Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text
PsyMedLewd_V2.i1-IQ2_XXS.gguf filter=lfs diff=lfs merge=lfs -text
PsyMedLewd_V2.i1-Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text
PsyMedLewd_V2.i1-IQ2_XS.gguf filter=lfs diff=lfs merge=lfs -text
PsyMedLewd_V2.i1-Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text
PsyMedLewd_V2.i1-IQ2_S.gguf filter=lfs diff=lfs merge=lfs -text
PsyMedLewd_V2.i1-IQ1_S.gguf filter=lfs diff=lfs merge=lfs -text
PsyMedLewd_V2.i1-Q4_0.gguf filter=lfs diff=lfs merge=lfs -text
PsyMedLewd_V2.i1-Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text
PsyMedLewd_V2.i1-IQ3_XS.gguf filter=lfs diff=lfs merge=lfs -text
PsyMedLewd_V2.i1-IQ3_S.gguf filter=lfs diff=lfs merge=lfs -text

View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:cf80e48932d1a05330d8bdbe56fe7a01147da0d656c7ae12e019d09ac338b596
size 4393985056

View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:28194b00af71915d2a70e4d5c673f962e21ecbc0e1143614d2c19cdaaca1c920
size 6397860896

View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:c766e007aa602558b03bf459e3490a0cb11ae58ecaac1abccec79fd2f8b89e0c
size 5937275936

View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:b85c05b11f98ceb900e4fd44e642bedb9954e5fe4ce4ac1a8cffd27739fcae36
size 8658371616

View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:8e543d30f56796de0cb3fab40fd8fba1f98f5e77aeee8cf466316dd3d5fa9adb
size 8194130976

View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:659bed6578fc6c10869432fd3741bfb22450739a070c7a8d68a91fee6481879a
size 10627769376

View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:8db36809315c12ed0f51819dcb14816ee99d1fafdefa26e3abd245b3a56b88fa
size 11322993696

View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:be2a05438c71529df0d8f8bba7b33addd6eb2ddd74afd9bfaa04b3027471be7d
size 14157220896

View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:23fd6fc2a4cd4503cd526e83026ecbcebbc5b87495686ebc742d0c430f03833c
size 13770763296

View File

@@ -1,6 +1,75 @@
---
base_model: Elfrino/PsyMedLewd_V2
language:
- en
library_name: transformers
quantized_by: mradermacher
tags:
- mergekit
- merge
---
## About
<!-- ### quantize_version: 2 -->
<!-- ### output_tensor_quantised: 1 -->
<!-- ### convert_type: hf -->
<!-- ### vocab_type: -->
<!-- ### tags: nicoboss -->
weighted/imatrix quants of https://huggingface.co/Elfrino/PsyMedLewd_V2
<!-- provided-files -->
static quants are available at https://huggingface.co/mradermacher/PsyMedLewd_V2-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/PsyMedLewd_V2-i1-GGUF/resolve/main/PsyMedLewd_V2.i1-IQ1_S.gguf) | i1-IQ1_S | 4.5 | for the desperate |
| [GGUF](https://huggingface.co/mradermacher/PsyMedLewd_V2-i1-GGUF/resolve/main/PsyMedLewd_V2.i1-IQ1_M.gguf) | i1-IQ1_M | 4.9 | mostly desperate |
| [GGUF](https://huggingface.co/mradermacher/PsyMedLewd_V2-i1-GGUF/resolve/main/PsyMedLewd_V2.i1-IQ2_XXS.gguf) | i1-IQ2_XXS | 5.5 | |
| [GGUF](https://huggingface.co/mradermacher/PsyMedLewd_V2-i1-GGUF/resolve/main/PsyMedLewd_V2.i1-IQ2_XS.gguf) | i1-IQ2_XS | 6.0 | |
| [GGUF](https://huggingface.co/mradermacher/PsyMedLewd_V2-i1-GGUF/resolve/main/PsyMedLewd_V2.i1-IQ2_S.gguf) | i1-IQ2_S | 6.5 | |
| [GGUF](https://huggingface.co/mradermacher/PsyMedLewd_V2-i1-GGUF/resolve/main/PsyMedLewd_V2.i1-IQ2_M.gguf) | i1-IQ2_M | 7.0 | |
| [GGUF](https://huggingface.co/mradermacher/PsyMedLewd_V2-i1-GGUF/resolve/main/PsyMedLewd_V2.i1-Q2_K.gguf) | i1-Q2_K | 7.5 | IQ3_XXS probably better |
| [GGUF](https://huggingface.co/mradermacher/PsyMedLewd_V2-i1-GGUF/resolve/main/PsyMedLewd_V2.i1-IQ3_XXS.gguf) | i1-IQ3_XXS | 7.7 | lower quality |
| [GGUF](https://huggingface.co/mradermacher/PsyMedLewd_V2-i1-GGUF/resolve/main/PsyMedLewd_V2.i1-IQ3_XS.gguf) | i1-IQ3_XS | 8.3 | |
| [GGUF](https://huggingface.co/mradermacher/PsyMedLewd_V2-i1-GGUF/resolve/main/PsyMedLewd_V2.i1-IQ3_S.gguf) | i1-IQ3_S | 8.8 | beats Q3_K* |
| [GGUF](https://huggingface.co/mradermacher/PsyMedLewd_V2-i1-GGUF/resolve/main/PsyMedLewd_V2.i1-Q3_K_S.gguf) | i1-Q3_K_S | 8.8 | IQ3_XS probably better |
| [GGUF](https://huggingface.co/mradermacher/PsyMedLewd_V2-i1-GGUF/resolve/main/PsyMedLewd_V2.i1-IQ3_M.gguf) | i1-IQ3_M | 9.3 | |
| [GGUF](https://huggingface.co/mradermacher/PsyMedLewd_V2-i1-GGUF/resolve/main/PsyMedLewd_V2.i1-Q3_K_M.gguf) | i1-Q3_K_M | 9.8 | IQ3_S probably better |
| [GGUF](https://huggingface.co/mradermacher/PsyMedLewd_V2-i1-GGUF/resolve/main/PsyMedLewd_V2.i1-Q3_K_L.gguf) | i1-Q3_K_L | 10.7 | IQ3_M probably better |
| [GGUF](https://huggingface.co/mradermacher/PsyMedLewd_V2-i1-GGUF/resolve/main/PsyMedLewd_V2.i1-IQ4_XS.gguf) | i1-IQ4_XS | 10.8 | |
| [GGUF](https://huggingface.co/mradermacher/PsyMedLewd_V2-i1-GGUF/resolve/main/PsyMedLewd_V2.i1-Q4_0.gguf) | i1-Q4_0 | 11.4 | fast, low quality |
| [GGUF](https://huggingface.co/mradermacher/PsyMedLewd_V2-i1-GGUF/resolve/main/PsyMedLewd_V2.i1-Q4_K_S.gguf) | i1-Q4_K_S | 11.5 | optimal size/speed/quality |
| [GGUF](https://huggingface.co/mradermacher/PsyMedLewd_V2-i1-GGUF/resolve/main/PsyMedLewd_V2.i1-Q4_K_M.gguf) | i1-Q4_K_M | 12.1 | fast, recommended |
| [GGUF](https://huggingface.co/mradermacher/PsyMedLewd_V2-i1-GGUF/resolve/main/PsyMedLewd_V2.i1-Q5_K_S.gguf) | i1-Q5_K_S | 13.9 | |
| [GGUF](https://huggingface.co/mradermacher/PsyMedLewd_V2-i1-GGUF/resolve/main/PsyMedLewd_V2.i1-Q5_K_M.gguf) | i1-Q5_K_M | 14.3 | |
| [GGUF](https://huggingface.co/mradermacher/PsyMedLewd_V2-i1-GGUF/resolve/main/PsyMedLewd_V2.i1-Q6_K.gguf) | i1-Q6_K | 16.5 | 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
## 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 -->