mradermacher/DataVortexS-10.7B-dpo-v1.0-i1-GGUF
1
0
Fork 0
Code Issues Pull Requests Actions Projects Releases Wiki Activity

Compare commits

base: mradermacher:34667d918a13b52adb1d2d527ea14f528166562d
Branches Tags
mradermacher:main
..
compare: mradermacher:main
Branches Tags
mradermacher:main

10 Commits
34667d918a ... main

Author SHA1 Message Date
Michael Radermacher
4be5501c78 auto-patch README.md 2024-11-02 18:57:10 +00:00
Michael Radermacher
006581fee6 uploaded from nethype/db3 2024-11-02 18:56:45 +00:00
Michael Radermacher
5ecb874123 uploaded from nethype/db3 2024-11-02 18:52:16 +00:00
Michael Radermacher
d7e9de1989 uploaded from nethype/db3 2024-11-02 18:52:01 +00:00
Michael Radermacher
737a02fa57 uploaded from nethype/db3 2024-11-02 18:50:53 +00:00
Michael Radermacher
9c96f49d84 uploaded from nethype/db3 2024-11-02 18:44:49 +00:00
Michael Radermacher
f140eee3e4 uploaded from nethype/db3 2024-11-02 18:44:46 +00:00
Michael Radermacher
36c12a8684 uploaded from nethype/db3 2024-11-02 18:39:45 +00:00
Michael Radermacher
7c179d7a5c uploaded from nethype/db3 2024-11-02 18:37:55 +00:00
Michael Radermacher
4138cbcad5 uploaded from nethype/db3 2024-11-02 18:36:18 +00:00
11 changed files with 108 additions and 0 deletions
Expand all files Collapse all files

9
.gitattributes vendored
View File

@@ -49,3 +49,12 @@ DataVortexS-10.7B-dpo-v1.0.i1-IQ2_XXS.gguf filter=lfs diff=lfs merge=lfs -text
DataVortexS-10.7B-dpo-v1.0.i1-Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text DataVortexS-10.7B-dpo-v1.0.i1-Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text
DataVortexS-10.7B-dpo-v1.0.i1-IQ2_XS.gguf filter=lfs diff=lfs merge=lfs -text DataVortexS-10.7B-dpo-v1.0.i1-IQ2_XS.gguf filter=lfs diff=lfs merge=lfs -text
DataVortexS-10.7B-dpo-v1.0.i1-Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text DataVortexS-10.7B-dpo-v1.0.i1-Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text
DataVortexS-10.7B-dpo-v1.0.i1-IQ2_S.gguf filter=lfs diff=lfs merge=lfs -text
DataVortexS-10.7B-dpo-v1.0.i1-Q4_0_4_4.gguf filter=lfs diff=lfs merge=lfs -text
DataVortexS-10.7B-dpo-v1.0.i1-IQ1_S.gguf filter=lfs diff=lfs merge=lfs -text
DataVortexS-10.7B-dpo-v1.0.i1-Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text
DataVortexS-10.7B-dpo-v1.0.i1-Q4_0.gguf filter=lfs diff=lfs merge=lfs -text
DataVortexS-10.7B-dpo-v1.0.i1-IQ3_XS.gguf filter=lfs diff=lfs merge=lfs -text
DataVortexS-10.7B-dpo-v1.0.i1-Q4_0_4_8.gguf filter=lfs diff=lfs merge=lfs -text
DataVortexS-10.7B-dpo-v1.0.i1-Q4_0_8_8.gguf filter=lfs diff=lfs merge=lfs -text
DataVortexS-10.7B-dpo-v1.0.i1-IQ3_S.gguf filter=lfs diff=lfs merge=lfs -text

3
DataVortexS-10.7B-dpo-v1.0.i1-IQ1_S.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:9cec338a769824b779eda74a15a3476acd0984e24767cb23d6562bb37030ee40
size 2351227008

3
DataVortexS-10.7B-dpo-v1.0.i1-IQ2_S.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:260635c77a1efc4a8c31a9ccd844ee2c071169326b2b4c50d01fe22f6f53b2ac
size 3392798848

3
DataVortexS-10.7B-dpo-v1.0.i1-IQ3_S.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:cb74c8feb91f455478b40665345d81391500eb482f67aa85a6af2d6829d9d17b
size 4691304576

3
DataVortexS-10.7B-dpo-v1.0.i1-IQ3_XS.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:dfc161c361218bbf61651163145c75c91f99fca840b96de83e0760887809047d
size 4445937792

3
DataVortexS-10.7B-dpo-v1.0.i1-Q4_0.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:0543802b3cf283c2b6d40de8abf0be6d8e3dfd58ba6a4e85afb8a720a7fd3315
size 6094405760

3
DataVortexS-10.7B-dpo-v1.0.i1-Q4_0_4_4.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:8091c675d0bd18f124d38c376560f0eff2ae40450e3f134f8fa74319d309b9c1
size 6072385664

3
DataVortexS-10.7B-dpo-v1.0.i1-Q4_0_4_8.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:e0ce990b7cfd8ad5dd7aa03e47454dfae0dcb3a7d21c0798a5358b70435e53b3
size 6072385664

3
DataVortexS-10.7B-dpo-v1.0.i1-Q4_0_8_8.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:1b8f65f128f40ebd04c2323378c05f419483dd8c44d2b406807cec84f70768d8
size 6072385664

3
DataVortexS-10.7B-dpo-v1.0.i1-Q5_K_M.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:a879bb288f4b106fa03c7165eaea11824b4b08666a83f0f67c6064cb5043d745
size 7597932672

72
README.md
View File

@@ -1,6 +1,78 @@
---
base_model: Edentns/DataVortexS-10.7B-dpo-v1.0
language:
- ko
library_name: transformers
license: cc-by-nc-sa-4.0
quantized_by: mradermacher
tags:
- text-generation
---
## About
<!-- ### quantize_version: 2 --> <!-- ### quantize_version: 2 -->
<!-- ### output_tensor_quantised: 1 --> <!-- ### output_tensor_quantised: 1 -->
<!-- ### convert_type: hf --> <!-- ### convert_type: hf -->
<!-- ### vocab_type: --> <!-- ### vocab_type: -->
<!-- ### tags: nicoboss --> <!-- ### tags: nicoboss -->
weighted/imatrix quants of https://huggingface.co/Edentns/DataVortexS-10.7B-dpo-v1.0 weighted/imatrix quants of https://huggingface.co/Edentns/DataVortexS-10.7B-dpo-v1.0
<!-- provided-files -->
static quants are available at https://huggingface.co/mradermacher/DataVortexS-10.7B-dpo-v1.0-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/DataVortexS-10.7B-dpo-v1.0-i1-GGUF/resolve/main/DataVortexS-10.7B-dpo-v1.0.i1-IQ1_S.gguf) | i1-IQ1_S | 2.5 | for the desperate |
| [GGUF](https://huggingface.co/mradermacher/DataVortexS-10.7B-dpo-v1.0-i1-GGUF/resolve/main/DataVortexS-10.7B-dpo-v1.0.i1-IQ1_M.gguf) | i1-IQ1_M | 2.7 | mostly desperate |
| [GGUF](https://huggingface.co/mradermacher/DataVortexS-10.7B-dpo-v1.0-i1-GGUF/resolve/main/DataVortexS-10.7B-dpo-v1.0.i1-IQ2_XXS.gguf) | i1-IQ2_XXS | 3.0 | |
| [GGUF](https://huggingface.co/mradermacher/DataVortexS-10.7B-dpo-v1.0-i1-GGUF/resolve/main/DataVortexS-10.7B-dpo-v1.0.i1-IQ2_XS.gguf) | i1-IQ2_XS | 3.3 | |
| [GGUF](https://huggingface.co/mradermacher/DataVortexS-10.7B-dpo-v1.0-i1-GGUF/resolve/main/DataVortexS-10.7B-dpo-v1.0.i1-IQ2_S.gguf) | i1-IQ2_S | 3.5 | |
| [GGUF](https://huggingface.co/mradermacher/DataVortexS-10.7B-dpo-v1.0-i1-GGUF/resolve/main/DataVortexS-10.7B-dpo-v1.0.i1-IQ2_M.gguf) | i1-IQ2_M | 3.8 | |
| [GGUF](https://huggingface.co/mradermacher/DataVortexS-10.7B-dpo-v1.0-i1-GGUF/resolve/main/DataVortexS-10.7B-dpo-v1.0.i1-Q2_K.gguf) | i1-Q2_K | 4.1 | IQ3_XXS probably better |
| [GGUF](https://huggingface.co/mradermacher/DataVortexS-10.7B-dpo-v1.0-i1-GGUF/resolve/main/DataVortexS-10.7B-dpo-v1.0.i1-IQ3_XXS.gguf) | i1-IQ3_XXS | 4.3 | lower quality |
| [GGUF](https://huggingface.co/mradermacher/DataVortexS-10.7B-dpo-v1.0-i1-GGUF/resolve/main/DataVortexS-10.7B-dpo-v1.0.i1-IQ3_XS.gguf) | i1-IQ3_XS | 4.5 | |
| [GGUF](https://huggingface.co/mradermacher/DataVortexS-10.7B-dpo-v1.0-i1-GGUF/resolve/main/DataVortexS-10.7B-dpo-v1.0.i1-Q3_K_S.gguf) | i1-Q3_K_S | 4.8 | IQ3_XS probably better |
| [GGUF](https://huggingface.co/mradermacher/DataVortexS-10.7B-dpo-v1.0-i1-GGUF/resolve/main/DataVortexS-10.7B-dpo-v1.0.i1-IQ3_S.gguf) | i1-IQ3_S | 4.8 | beats Q3_K* |
| [GGUF](https://huggingface.co/mradermacher/DataVortexS-10.7B-dpo-v1.0-i1-GGUF/resolve/main/DataVortexS-10.7B-dpo-v1.0.i1-IQ3_M.gguf) | i1-IQ3_M | 4.9 | |
| [GGUF](https://huggingface.co/mradermacher/DataVortexS-10.7B-dpo-v1.0-i1-GGUF/resolve/main/DataVortexS-10.7B-dpo-v1.0.i1-Q3_K_M.gguf) | i1-Q3_K_M | 5.3 | IQ3_S probably better |
| [GGUF](https://huggingface.co/mradermacher/DataVortexS-10.7B-dpo-v1.0-i1-GGUF/resolve/main/DataVortexS-10.7B-dpo-v1.0.i1-Q3_K_L.gguf) | i1-Q3_K_L | 5.8 | IQ3_M probably better |
| [GGUF](https://huggingface.co/mradermacher/DataVortexS-10.7B-dpo-v1.0-i1-GGUF/resolve/main/DataVortexS-10.7B-dpo-v1.0.i1-IQ4_XS.gguf) | i1-IQ4_XS | 5.9 | |
| [GGUF](https://huggingface.co/mradermacher/DataVortexS-10.7B-dpo-v1.0-i1-GGUF/resolve/main/DataVortexS-10.7B-dpo-v1.0.i1-Q4_0_4_4.gguf) | i1-Q4_0_4_4 | 6.2 | fast on arm, low quality |
| [GGUF](https://huggingface.co/mradermacher/DataVortexS-10.7B-dpo-v1.0-i1-GGUF/resolve/main/DataVortexS-10.7B-dpo-v1.0.i1-Q4_0_4_8.gguf) | i1-Q4_0_4_8 | 6.2 | fast on arm+i8mm, low quality |
| [GGUF](https://huggingface.co/mradermacher/DataVortexS-10.7B-dpo-v1.0-i1-GGUF/resolve/main/DataVortexS-10.7B-dpo-v1.0.i1-Q4_0_8_8.gguf) | i1-Q4_0_8_8 | 6.2 | fast on arm+sve, low quality |
| [GGUF](https://huggingface.co/mradermacher/DataVortexS-10.7B-dpo-v1.0-i1-GGUF/resolve/main/DataVortexS-10.7B-dpo-v1.0.i1-Q4_0.gguf) | i1-Q4_0 | 6.2 | fast, low quality |
| [GGUF](https://huggingface.co/mradermacher/DataVortexS-10.7B-dpo-v1.0-i1-GGUF/resolve/main/DataVortexS-10.7B-dpo-v1.0.i1-Q4_K_S.gguf) | i1-Q4_K_S | 6.2 | optimal size/speed/quality |
| [GGUF](https://huggingface.co/mradermacher/DataVortexS-10.7B-dpo-v1.0-i1-GGUF/resolve/main/DataVortexS-10.7B-dpo-v1.0.i1-Q4_K_M.gguf) | i1-Q4_K_M | 6.6 | fast, recommended |
| [GGUF](https://huggingface.co/mradermacher/DataVortexS-10.7B-dpo-v1.0-i1-GGUF/resolve/main/DataVortexS-10.7B-dpo-v1.0.i1-Q5_K_S.gguf) | i1-Q5_K_S | 7.5 | |
| [GGUF](https://huggingface.co/mradermacher/DataVortexS-10.7B-dpo-v1.0-i1-GGUF/resolve/main/DataVortexS-10.7B-dpo-v1.0.i1-Q5_K_M.gguf) | i1-Q5_K_M | 7.7 | |
| [GGUF](https://huggingface.co/mradermacher/DataVortexS-10.7B-dpo-v1.0-i1-GGUF/resolve/main/DataVortexS-10.7B-dpo-v1.0.i1-Q6_K.gguf) | i1-Q6_K | 8.9 | 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 -->