Hugging Face's logo

mradermacher
/
Huihui-gemma-3-270m-it-abliterated-i1-GGUF

Transformers
GGUF
English
gemma3
gemma
google
Generated from Trainer
trl
sft
abliterated
uncensored
imatrix
conversational
Model card Files
xet
Community
mradermacher commited on
Commit
72832aa
·
verified ·
1 Parent(s): c91f4a7

auto-patch README.md

Browse files
Files changed (1) hide show
  1. README.md +85 -0
README.md CHANGED
@@ -1,3 +1,24 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
  <!-- ### quantize_version: 2 -->
2
  <!-- ### output_tensor_quantised: 1 -->
3
  <!-- ### convert_type: hf -->
@@ -7,3 +28,67 @@
7
  <!-- ### quants_skip: -->
8
  <!-- ### skip_mmproj: -->
9
  weighted/imatrix quants of https://huggingface.co/huihui-ai/Huihui-gemma-3-270m-it-abliterated
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ base_model: huihui-ai/Huihui-gemma-3-270m-it-abliterated
3
+ language:
4
+ - en
5
+ library_name: transformers
6
+ license: gemma
7
+ mradermacher:
8
+ readme_rev: 1
9
+ quantized_by: mradermacher
10
+ tags:
11
+ - gemma3
12
+ - gemma
13
+ - google
14
+ - generated_from_trainer
15
+ - trl
16
+ - sft
17
+ - abliterated
18
+ - uncensored
19
+ ---
20
+ ## About
21
+
22
  <!-- ### quantize_version: 2 -->
23
  <!-- ### output_tensor_quantised: 1 -->
24
  <!-- ### convert_type: hf -->
 
28
  <!-- ### quants_skip: -->
29
  <!-- ### skip_mmproj: -->
30
  weighted/imatrix quants of https://huggingface.co/huihui-ai/Huihui-gemma-3-270m-it-abliterated
31
+
32
+ <!-- provided-files -->
33
+
34
+ ***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#Huihui-gemma-3-270m-it-abliterated-i1-GGUF).***
35
+
36
+ static quants are available at https://huggingface.co/mradermacher/Huihui-gemma-3-270m-it-abliterated-GGUF
37
+ ## Usage
38
+
39
+ If you are unsure how to use GGUF files, refer to one of [TheBloke's
40
+ READMEs](https://huggingface.co/TheBloke/KafkaLM-70B-German-V0.1-GGUF) for
41
+ more details, including on how to concatenate multi-part files.
42
+
43
+ ## Provided Quants
44
+
45
+ (sorted by size, not necessarily quality. IQ-quants are often preferable over similar sized non-IQ quants)
46
+
47
+ | Link | Type | Size/GB | Notes |
48
+ |:-----|:-----|--------:|:------|
49
+ | [GGUF](https://huggingface.co/mradermacher/Huihui-gemma-3-270m-it-abliterated-i1-GGUF/resolve/main/Huihui-gemma-3-270m-it-abliterated.imatrix.gguf) | imatrix | 0.1 | imatrix file (for creating your own qwuants) |
50
+ | [GGUF](https://huggingface.co/mradermacher/Huihui-gemma-3-270m-it-abliterated-i1-GGUF/resolve/main/Huihui-gemma-3-270m-it-abliterated.i1-IQ1_S.gguf) | i1-IQ1_S | 0.3 | for the desperate |
51
+ | [GGUF](https://huggingface.co/mradermacher/Huihui-gemma-3-270m-it-abliterated-i1-GGUF/resolve/main/Huihui-gemma-3-270m-it-abliterated.i1-IQ1_M.gguf) | i1-IQ1_M | 0.3 | mostly desperate |
52
+ | [GGUF](https://huggingface.co/mradermacher/Huihui-gemma-3-270m-it-abliterated-i1-GGUF/resolve/main/Huihui-gemma-3-270m-it-abliterated.i1-IQ2_XXS.gguf) | i1-IQ2_XXS | 0.3 | |
53
+ | [GGUF](https://huggingface.co/mradermacher/Huihui-gemma-3-270m-it-abliterated-i1-GGUF/resolve/main/Huihui-gemma-3-270m-it-abliterated.i1-IQ2_XS.gguf) | i1-IQ2_XS | 0.3 | |
54
+ | [GGUF](https://huggingface.co/mradermacher/Huihui-gemma-3-270m-it-abliterated-i1-GGUF/resolve/main/Huihui-gemma-3-270m-it-abliterated.i1-Q2_K_S.gguf) | i1-Q2_K_S | 0.3 | very low quality |
55
+ | [GGUF](https://huggingface.co/mradermacher/Huihui-gemma-3-270m-it-abliterated-i1-GGUF/resolve/main/Huihui-gemma-3-270m-it-abliterated.i1-IQ2_S.gguf) | i1-IQ2_S | 0.3 | |
56
+ | [GGUF](https://huggingface.co/mradermacher/Huihui-gemma-3-270m-it-abliterated-i1-GGUF/resolve/main/Huihui-gemma-3-270m-it-abliterated.i1-IQ2_M.gguf) | i1-IQ2_M | 0.3 | |
57
+ | [GGUF](https://huggingface.co/mradermacher/Huihui-gemma-3-270m-it-abliterated-i1-GGUF/resolve/main/Huihui-gemma-3-270m-it-abliterated.i1-IQ3_XXS.gguf) | i1-IQ3_XXS | 0.3 | lower quality |
58
+ | [GGUF](https://huggingface.co/mradermacher/Huihui-gemma-3-270m-it-abliterated-i1-GGUF/resolve/main/Huihui-gemma-3-270m-it-abliterated.i1-Q3_K_S.gguf) | i1-Q3_K_S | 0.3 | IQ3_XS probably better |
59
+ | [GGUF](https://huggingface.co/mradermacher/Huihui-gemma-3-270m-it-abliterated-i1-GGUF/resolve/main/Huihui-gemma-3-270m-it-abliterated.i1-IQ3_S.gguf) | i1-IQ3_S | 0.3 | beats Q3_K* |
60
+ | [GGUF](https://huggingface.co/mradermacher/Huihui-gemma-3-270m-it-abliterated-i1-GGUF/resolve/main/Huihui-gemma-3-270m-it-abliterated.i1-IQ3_XS.gguf) | i1-IQ3_XS | 0.3 | |
61
+ | [GGUF](https://huggingface.co/mradermacher/Huihui-gemma-3-270m-it-abliterated-i1-GGUF/resolve/main/Huihui-gemma-3-270m-it-abliterated.i1-Q2_K.gguf) | i1-Q2_K | 0.3 | IQ3_XXS probably better |
62
+ | [GGUF](https://huggingface.co/mradermacher/Huihui-gemma-3-270m-it-abliterated-i1-GGUF/resolve/main/Huihui-gemma-3-270m-it-abliterated.i1-IQ3_M.gguf) | i1-IQ3_M | 0.3 | |
63
+ | [GGUF](https://huggingface.co/mradermacher/Huihui-gemma-3-270m-it-abliterated-i1-GGUF/resolve/main/Huihui-gemma-3-270m-it-abliterated.i1-IQ4_XS.gguf) | i1-IQ4_XS | 0.3 | |
64
+ | [GGUF](https://huggingface.co/mradermacher/Huihui-gemma-3-270m-it-abliterated-i1-GGUF/resolve/main/Huihui-gemma-3-270m-it-abliterated.i1-Q4_0.gguf) | i1-Q4_0 | 0.3 | fast, low quality |
65
+ | [GGUF](https://huggingface.co/mradermacher/Huihui-gemma-3-270m-it-abliterated-i1-GGUF/resolve/main/Huihui-gemma-3-270m-it-abliterated.i1-IQ4_NL.gguf) | i1-IQ4_NL | 0.3 | prefer IQ4_XS |
66
+ | [GGUF](https://huggingface.co/mradermacher/Huihui-gemma-3-270m-it-abliterated-i1-GGUF/resolve/main/Huihui-gemma-3-270m-it-abliterated.i1-Q3_K_M.gguf) | i1-Q3_K_M | 0.3 | IQ3_S probably better |
67
+ | [GGUF](https://huggingface.co/mradermacher/Huihui-gemma-3-270m-it-abliterated-i1-GGUF/resolve/main/Huihui-gemma-3-270m-it-abliterated.i1-Q3_K_L.gguf) | i1-Q3_K_L | 0.3 | IQ3_M probably better |
68
+ | [GGUF](https://huggingface.co/mradermacher/Huihui-gemma-3-270m-it-abliterated-i1-GGUF/resolve/main/Huihui-gemma-3-270m-it-abliterated.i1-Q4_1.gguf) | i1-Q4_1 | 0.3 | |
69
+ | [GGUF](https://huggingface.co/mradermacher/Huihui-gemma-3-270m-it-abliterated-i1-GGUF/resolve/main/Huihui-gemma-3-270m-it-abliterated.i1-Q4_K_S.gguf) | i1-Q4_K_S | 0.3 | optimal size/speed/quality |
70
+ | [GGUF](https://huggingface.co/mradermacher/Huihui-gemma-3-270m-it-abliterated-i1-GGUF/resolve/main/Huihui-gemma-3-270m-it-abliterated.i1-Q4_K_M.gguf) | i1-Q4_K_M | 0.4 | fast, recommended |
71
+ | [GGUF](https://huggingface.co/mradermacher/Huihui-gemma-3-270m-it-abliterated-i1-GGUF/resolve/main/Huihui-gemma-3-270m-it-abliterated.i1-Q5_K_S.gguf) | i1-Q5_K_S | 0.4 | |
72
+ | [GGUF](https://huggingface.co/mradermacher/Huihui-gemma-3-270m-it-abliterated-i1-GGUF/resolve/main/Huihui-gemma-3-270m-it-abliterated.i1-Q5_K_M.gguf) | i1-Q5_K_M | 0.4 | |
73
+ | [GGUF](https://huggingface.co/mradermacher/Huihui-gemma-3-270m-it-abliterated-i1-GGUF/resolve/main/Huihui-gemma-3-270m-it-abliterated.i1-Q6_K.gguf) | i1-Q6_K | 0.4 | practically like static Q6_K |
74
+
75
+ Here is a handy graph by ikawrakow comparing some lower-quality quant
76
+ types (lower is better):
77
+
78
+ ![image.png](https://www.nethype.de/huggingface_embed/quantpplgraph.png)
79
+
80
+ And here are Artefact2's thoughts on the matter:
81
+ https://gist.github.com/Artefact2/b5f810600771265fc1e39442288e8ec9
82
+
83
+ ## FAQ / Model Request
84
+
85
+ See https://huggingface.co/mradermacher/model_requests for some answers to
86
+ questions you might have and/or if you want some other model quantized.
87
+
88
+ ## Thanks
89
+
90
+ I thank my company, [nethype GmbH](https://www.nethype.de/), for letting
91
+ me use its servers and providing upgrades to my workstation to enable
92
+ 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.
93
+
94
+ <!-- end -->