auto-patch README.md

uploaded from marco
2025-12-29 23:40:18 +00:00 · 2025-12-29 15:36:11 +00:00 · 2025-12-29 15:35:42 +00:00 · 2025-12-29 15:33:33 +00:00 · 2025-12-29 15:30:16 +00:00 · 2025-12-29 15:28:42 +00:00
9 changed files with 96 additions and 0 deletions
--- a/.gitattributes
+++ b/.gitattributes
@@ -37,3 +37,10 @@ gemma-3-12b-it-abliterated-refined-novis.Q4_K_S.gguf filter=lfs diff=lfs merge=l
 gemma-3-12b-it-abliterated-refined-novis.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text
 gemma-3-12b-it-abliterated-refined-novis.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text
 gemma-3-12b-it-abliterated-refined-novis.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text
+gemma-3-12b-it-abliterated-refined-novis.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text
+gemma-3-12b-it-abliterated-refined-novis.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text
+gemma-3-12b-it-abliterated-refined-novis.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text
+gemma-3-12b-it-abliterated-refined-novis.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text
+gemma-3-12b-it-abliterated-refined-novis.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text
+gemma-3-12b-it-abliterated-refined-novis.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text
+gemma-3-12b-it-abliterated-refined-novis.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text
--- a/README.md
+++ b/README.md
@@ -1,3 +1,21 @@
+---
+base_model: Nabbers1999/gemma-3-12b-it-abliterated-refined-novis
+language:
+- en
+library_name: transformers
+license: gemma
+mradermacher:
+  readme_rev: 1
+quantized_by: mradermacher
+tags:
+- gemma
+- gemma-3
+- text-generation
+- conversational
+- abliterated
+---
+## About
+
 <!-- ### quantize_version: 2 -->
 <!-- ### output_tensor_quantised: 1 -->
 <!-- ### convert_type: hf -->
@@ -7,3 +25,53 @@
 <!-- ### quants_skip:  -->
 <!-- ### skip_mmproj:  -->
 static quants of https://huggingface.co/Nabbers1999/gemma-3-12b-it-abliterated-refined-novis
+
+<!-- provided-files -->
+
+***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#gemma-3-12b-it-abliterated-refined-novis-GGUF).***
+
+weighted/imatrix quants are available at https://huggingface.co/mradermacher/gemma-3-12b-it-abliterated-refined-novis-i1-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/gemma-3-12b-it-abliterated-refined-novis-GGUF/resolve/main/gemma-3-12b-it-abliterated-refined-novis.Q2_K.gguf) | Q2_K | 4.9 |  |
+| [GGUF](https://huggingface.co/mradermacher/gemma-3-12b-it-abliterated-refined-novis-GGUF/resolve/main/gemma-3-12b-it-abliterated-refined-novis.Q3_K_S.gguf) | Q3_K_S | 5.6 |  |
+| [GGUF](https://huggingface.co/mradermacher/gemma-3-12b-it-abliterated-refined-novis-GGUF/resolve/main/gemma-3-12b-it-abliterated-refined-novis.Q3_K_M.gguf) | Q3_K_M | 6.1 | lower quality |
+| [GGUF](https://huggingface.co/mradermacher/gemma-3-12b-it-abliterated-refined-novis-GGUF/resolve/main/gemma-3-12b-it-abliterated-refined-novis.Q3_K_L.gguf) | Q3_K_L | 6.6 |  |
+| [GGUF](https://huggingface.co/mradermacher/gemma-3-12b-it-abliterated-refined-novis-GGUF/resolve/main/gemma-3-12b-it-abliterated-refined-novis.IQ4_XS.gguf) | IQ4_XS | 6.7 |  |
+| [GGUF](https://huggingface.co/mradermacher/gemma-3-12b-it-abliterated-refined-novis-GGUF/resolve/main/gemma-3-12b-it-abliterated-refined-novis.Q4_K_S.gguf) | Q4_K_S | 7.0 | fast, recommended |
+| [GGUF](https://huggingface.co/mradermacher/gemma-3-12b-it-abliterated-refined-novis-GGUF/resolve/main/gemma-3-12b-it-abliterated-refined-novis.Q4_K_M.gguf) | Q4_K_M | 7.4 | fast, recommended |
+| [GGUF](https://huggingface.co/mradermacher/gemma-3-12b-it-abliterated-refined-novis-GGUF/resolve/main/gemma-3-12b-it-abliterated-refined-novis.Q5_K_S.gguf) | Q5_K_S | 8.3 |  |
+| [GGUF](https://huggingface.co/mradermacher/gemma-3-12b-it-abliterated-refined-novis-GGUF/resolve/main/gemma-3-12b-it-abliterated-refined-novis.Q5_K_M.gguf) | Q5_K_M | 8.5 |  |
+| [GGUF](https://huggingface.co/mradermacher/gemma-3-12b-it-abliterated-refined-novis-GGUF/resolve/main/gemma-3-12b-it-abliterated-refined-novis.Q6_K.gguf) | Q6_K | 9.8 | very good quality |
+| [GGUF](https://huggingface.co/mradermacher/gemma-3-12b-it-abliterated-refined-novis-GGUF/resolve/main/gemma-3-12b-it-abliterated-refined-novis.Q8_0.gguf) | Q8_0 | 12.6 | fast, best quality |
+
+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.
+
+<!-- end -->
--- a/gemma-3-12b-it-abliterated-refined-novis.IQ4_XS.gguf
+++ b/gemma-3-12b-it-abliterated-refined-novis.IQ4_XS.gguf
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6f97c9128b6a9eb5c0db70eb6e3622ae961f0f157e64c143ed656fd06a51984f
+size 6606261344
--- a/gemma-3-12b-it-abliterated-refined-novis.Q3_K_L.gguf
+++ b/gemma-3-12b-it-abliterated-refined-novis.Q3_K_L.gguf
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:780fe7b6d9c55282882bbdbb7a6e5ce1630721a53136f88bae7e7e70dea959db
+size 6480186464
--- a/gemma-3-12b-it-abliterated-refined-novis.Q3_K_M.gguf
+++ b/gemma-3-12b-it-abliterated-refined-novis.Q3_K_M.gguf
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dd431a7158b1435b6057d1a8c06a3dd96af06bc4781d31f9744a19d2cfabe975
+size 6008818784
--- a/gemma-3-12b-it-abliterated-refined-novis.Q3_K_S.gguf
+++ b/gemma-3-12b-it-abliterated-refined-novis.Q3_K_S.gguf
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:13d74de1476dc5bfd09db93c61d2e432b581fb26900994a1f0c7e099359c96af
+size 5458316384
--- a/gemma-3-12b-it-abliterated-refined-novis.Q4_K_M.gguf
+++ b/gemma-3-12b-it-abliterated-refined-novis.Q4_K_M.gguf
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:24101c4f50d9c93212266cb17873fa214259a06043b69153e4c95ef6443cb462
+size 7300779104
--- a/gemma-3-12b-it-abliterated-refined-novis.Q5_K_M.gguf
+++ b/gemma-3-12b-it-abliterated-refined-novis.Q5_K_M.gguf
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e0c08fbb9d220586d11b44408d45952987a3385831731c3a80f55df05c0c6c96
+size 8445037664
--- a/gemma-3-12b-it-abliterated-refined-novis.Q5_K_S.gguf
+++ b/gemma-3-12b-it-abliterated-refined-novis.Q5_K_S.gguf
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:18247abaac22ba68a82ad03da6c4a47687e57594092b5dee1fb806c77b0110d0
+size 8231963744
Author	SHA1	Message	Date
team mradermacher	af54c6eaf6	auto-patch README.md	2025-12-29 23:40:18 +00:00
team mradermacher	a589d71285	auto-patch README.md	2025-12-29 15:36:11 +00:00
team mradermacher	ce5cab4fd4	uploaded from marco	2025-12-29 15:35:42 +00:00
team mradermacher	049686f171	auto-patch README.md	2025-12-29 15:33:33 +00:00
team mradermacher	cacac5eb7c	uploaded from marco	2025-12-29 15:30:16 +00:00
team mradermacher	de28502910	uploaded from marco	2025-12-29 15:28:42 +00:00
team mradermacher	315287ae3a	uploaded from marco	2025-12-29 15:24:33 +00:00
team mradermacher	7fd304a94f	uploaded from marco	2025-12-29 15:23:04 +00:00
team mradermacher	0541a69358	uploaded from marco	2025-12-29 15:19:58 +00:00
team mradermacher	b796ba3f8a	uploaded from marco	2025-12-29 15:18:23 +00:00