Compare commits

...

10 Commits

Author SHA1 Message Date
team mradermacher
b079b91313 auto-patch README.md 2025-07-08 14:57:56 +00:00
team mradermacher
efc00b0792 uploaded from marco 2025-07-08 14:42:19 +00:00
team mradermacher
d2ccba27e4 uploaded from marco 2025-07-08 14:38:46 +00:00
team mradermacher
18a5f8bd70 uploaded from marco 2025-07-08 14:33:22 +00:00
team mradermacher
4aff5f1812 uploaded from marco 2025-07-08 14:29:32 +00:00
team mradermacher
2b5d873031 uploaded from marco 2025-07-08 14:27:55 +00:00
team mradermacher
4ee7b5a541 uploaded from marco 2025-07-08 14:19:36 +00:00
team mradermacher
c6b5c51527 uploaded from marco 2025-07-08 14:16:38 +00:00
team mradermacher
da7773916e uploaded from marco 2025-07-08 14:09:53 +00:00
team mradermacher
4ccea45649 uploaded from marco 2025-07-08 14:03:03 +00:00
11 changed files with 116 additions and 0 deletions

9
.gitattributes vendored
View File

@@ -49,3 +49,12 @@ UniReason-Qwen3-14B-no-think-SFT.i1-IQ1_M.gguf filter=lfs diff=lfs merge=lfs -te
UniReason-Qwen3-14B-no-think-SFT.i1-Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text
UniReason-Qwen3-14B-no-think-SFT.i1-IQ2_XXS.gguf filter=lfs diff=lfs merge=lfs -text
UniReason-Qwen3-14B-no-think-SFT.i1-Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text
UniReason-Qwen3-14B-no-think-SFT.i1-IQ2_XS.gguf filter=lfs diff=lfs merge=lfs -text
UniReason-Qwen3-14B-no-think-SFT.i1-Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text
UniReason-Qwen3-14B-no-think-SFT.i1-IQ2_S.gguf filter=lfs diff=lfs merge=lfs -text
UniReason-Qwen3-14B-no-think-SFT.i1-IQ1_S.gguf filter=lfs diff=lfs merge=lfs -text
UniReason-Qwen3-14B-no-think-SFT.i1-Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text
UniReason-Qwen3-14B-no-think-SFT.i1-Q4_0.gguf filter=lfs diff=lfs merge=lfs -text
UniReason-Qwen3-14B-no-think-SFT.i1-IQ3_XS.gguf filter=lfs diff=lfs merge=lfs -text
UniReason-Qwen3-14B-no-think-SFT.i1-Q4_1.gguf filter=lfs diff=lfs merge=lfs -text
UniReason-Qwen3-14B-no-think-SFT.i1-IQ3_S.gguf filter=lfs diff=lfs merge=lfs -text

View File

@@ -1,6 +1,86 @@
---
arxiv: 2507.00432
base_model: ReasoningTransferability/UniReason-Qwen3-14B-no-think-SFT
datasets:
- math
- reasoning
language: en
library_name: transformers
license: apache-2.0
quantized_by: mradermacher
tags:
- text-generation
- math-reasoning
- transferability
- Distill from Qwen3-32B-Instruct (non-thinking mode) through Reject Sampling
- research-paper
- qwen3
---
## About
<!-- ### quantize_version: 2 -->
<!-- ### output_tensor_quantised: 1 -->
<!-- ### convert_type: hf -->
<!-- ### vocab_type: -->
<!-- ### tags: nicoboss -->
weighted/imatrix quants of https://huggingface.co/ReasoningTransferability/UniReason-Qwen3-14B-no-think-SFT
<!-- provided-files -->
static quants are available at https://huggingface.co/mradermacher/UniReason-Qwen3-14B-no-think-SFT-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/UniReason-Qwen3-14B-no-think-SFT-i1-GGUF/resolve/main/UniReason-Qwen3-14B-no-think-SFT.i1-IQ1_S.gguf) | i1-IQ1_S | 3.7 | for the desperate |
| [GGUF](https://huggingface.co/mradermacher/UniReason-Qwen3-14B-no-think-SFT-i1-GGUF/resolve/main/UniReason-Qwen3-14B-no-think-SFT.i1-IQ1_M.gguf) | i1-IQ1_M | 3.9 | mostly desperate |
| [GGUF](https://huggingface.co/mradermacher/UniReason-Qwen3-14B-no-think-SFT-i1-GGUF/resolve/main/UniReason-Qwen3-14B-no-think-SFT.i1-IQ2_XXS.gguf) | i1-IQ2_XXS | 4.4 | |
| [GGUF](https://huggingface.co/mradermacher/UniReason-Qwen3-14B-no-think-SFT-i1-GGUF/resolve/main/UniReason-Qwen3-14B-no-think-SFT.i1-IQ2_XS.gguf) | i1-IQ2_XS | 4.8 | |
| [GGUF](https://huggingface.co/mradermacher/UniReason-Qwen3-14B-no-think-SFT-i1-GGUF/resolve/main/UniReason-Qwen3-14B-no-think-SFT.i1-IQ2_S.gguf) | i1-IQ2_S | 5.1 | |
| [GGUF](https://huggingface.co/mradermacher/UniReason-Qwen3-14B-no-think-SFT-i1-GGUF/resolve/main/UniReason-Qwen3-14B-no-think-SFT.i1-IQ2_M.gguf) | i1-IQ2_M | 5.4 | |
| [GGUF](https://huggingface.co/mradermacher/UniReason-Qwen3-14B-no-think-SFT-i1-GGUF/resolve/main/UniReason-Qwen3-14B-no-think-SFT.i1-Q2_K_S.gguf) | i1-Q2_K_S | 5.5 | very low quality |
| [GGUF](https://huggingface.co/mradermacher/UniReason-Qwen3-14B-no-think-SFT-i1-GGUF/resolve/main/UniReason-Qwen3-14B-no-think-SFT.i1-Q2_K.gguf) | i1-Q2_K | 5.9 | IQ3_XXS probably better |
| [GGUF](https://huggingface.co/mradermacher/UniReason-Qwen3-14B-no-think-SFT-i1-GGUF/resolve/main/UniReason-Qwen3-14B-no-think-SFT.i1-IQ3_XXS.gguf) | i1-IQ3_XXS | 6.0 | lower quality |
| [GGUF](https://huggingface.co/mradermacher/UniReason-Qwen3-14B-no-think-SFT-i1-GGUF/resolve/main/UniReason-Qwen3-14B-no-think-SFT.i1-IQ3_XS.gguf) | i1-IQ3_XS | 6.5 | |
| [GGUF](https://huggingface.co/mradermacher/UniReason-Qwen3-14B-no-think-SFT-i1-GGUF/resolve/main/UniReason-Qwen3-14B-no-think-SFT.i1-Q3_K_S.gguf) | i1-Q3_K_S | 6.8 | IQ3_XS probably better |
| [GGUF](https://huggingface.co/mradermacher/UniReason-Qwen3-14B-no-think-SFT-i1-GGUF/resolve/main/UniReason-Qwen3-14B-no-think-SFT.i1-IQ3_S.gguf) | i1-IQ3_S | 6.8 | beats Q3_K* |
| [GGUF](https://huggingface.co/mradermacher/UniReason-Qwen3-14B-no-think-SFT-i1-GGUF/resolve/main/UniReason-Qwen3-14B-no-think-SFT.i1-IQ3_M.gguf) | i1-IQ3_M | 7.0 | |
| [GGUF](https://huggingface.co/mradermacher/UniReason-Qwen3-14B-no-think-SFT-i1-GGUF/resolve/main/UniReason-Qwen3-14B-no-think-SFT.i1-Q3_K_M.gguf) | i1-Q3_K_M | 7.4 | IQ3_S probably better |
| [GGUF](https://huggingface.co/mradermacher/UniReason-Qwen3-14B-no-think-SFT-i1-GGUF/resolve/main/UniReason-Qwen3-14B-no-think-SFT.i1-Q3_K_L.gguf) | i1-Q3_K_L | 8.0 | IQ3_M probably better |
| [GGUF](https://huggingface.co/mradermacher/UniReason-Qwen3-14B-no-think-SFT-i1-GGUF/resolve/main/UniReason-Qwen3-14B-no-think-SFT.i1-IQ4_XS.gguf) | i1-IQ4_XS | 8.2 | |
| [GGUF](https://huggingface.co/mradermacher/UniReason-Qwen3-14B-no-think-SFT-i1-GGUF/resolve/main/UniReason-Qwen3-14B-no-think-SFT.i1-IQ4_NL.gguf) | i1-IQ4_NL | 8.6 | prefer IQ4_XS |
| [GGUF](https://huggingface.co/mradermacher/UniReason-Qwen3-14B-no-think-SFT-i1-GGUF/resolve/main/UniReason-Qwen3-14B-no-think-SFT.i1-Q4_0.gguf) | i1-Q4_0 | 8.6 | fast, low quality |
| [GGUF](https://huggingface.co/mradermacher/UniReason-Qwen3-14B-no-think-SFT-i1-GGUF/resolve/main/UniReason-Qwen3-14B-no-think-SFT.i1-Q4_K_S.gguf) | i1-Q4_K_S | 8.7 | optimal size/speed/quality |
| [GGUF](https://huggingface.co/mradermacher/UniReason-Qwen3-14B-no-think-SFT-i1-GGUF/resolve/main/UniReason-Qwen3-14B-no-think-SFT.i1-Q4_K_M.gguf) | i1-Q4_K_M | 9.1 | fast, recommended |
| [GGUF](https://huggingface.co/mradermacher/UniReason-Qwen3-14B-no-think-SFT-i1-GGUF/resolve/main/UniReason-Qwen3-14B-no-think-SFT.i1-Q4_1.gguf) | i1-Q4_1 | 9.5 | |
| [GGUF](https://huggingface.co/mradermacher/UniReason-Qwen3-14B-no-think-SFT-i1-GGUF/resolve/main/UniReason-Qwen3-14B-no-think-SFT.i1-Q5_K_S.gguf) | i1-Q5_K_S | 10.4 | |
| [GGUF](https://huggingface.co/mradermacher/UniReason-Qwen3-14B-no-think-SFT-i1-GGUF/resolve/main/UniReason-Qwen3-14B-no-think-SFT.i1-Q5_K_M.gguf) | i1-Q5_K_M | 10.6 | |
| [GGUF](https://huggingface.co/mradermacher/UniReason-Qwen3-14B-no-think-SFT-i1-GGUF/resolve/main/UniReason-Qwen3-14B-no-think-SFT.i1-Q6_K.gguf) | i1-Q6_K | 12.2 | 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 -->

View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:84fa3b3add8e9e6fe6832bffb0d2d9a39d7af09fe45b5300cb114bbcfe09908f
size 3579935392

View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:cf4729a58ce41e79f3dedad7b37fefdc701d1d6d16489aaea3fbc72b0812a459
size 4963313312

View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:0a0d18181f707635ea3d8a33f4ca2d7f7dc096201f250397c09f93cee5faae7c
size 4691589792

View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:edd73c04593ad8842101db840072eb240d7912a146a35c8375895a3a650f9b65
size 6684959392

View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:44977356e08fe718c09fe4485c12cc32ec07ec165e69bd8a7514435635d16bcf
size 6375301792

View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:e24e77b2371325b84d9cd02271fdeae2d7baf167a9f73e5e9ea9f2192b22c4c1
size 8543002272

View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:51535649271e6ae0653369578d5a1c863281cfe2e1218abdc756fd99d77c19e0
size 9389522592

View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:bcf3a54646735c850732165f06ff05c713a5b54cc18828cb7b9546740965baf4
size 10514570912

View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:e93468cc5a42d66acd94c1ccaf5a675d28eac32447b154bb2d9cb5461f291bac
size 10263895712