Hugging Face's logo

mradermacher
/
Qwen2.5-VL-3B-Abliterated-Caption-it-i1-GGUF

Image-to-Text
Transformers
GGUF
English
text-generation-inference
uncensored
image-captioning
vlm
visual-understanding
caption
imatrix
conversational
Model card Files
xet
Community
mradermacher commited on
Commit
91008af
·
verified ·
1 Parent(s): 8f73cb2

auto-patch README.md

Browse files
Files changed (1) hide show
  1. README.md +85 -0
README.md CHANGED
@@ -1,3 +1,22 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
  <!-- ### quantize_version: 2 -->
2
  <!-- ### output_tensor_quantised: 1 -->
3
  <!-- ### convert_type: hf -->
@@ -7,3 +26,69 @@
7
  <!-- ### quants_skip: -->
8
  <!-- ### skip_mmproj: -->
9
  weighted/imatrix quants of https://huggingface.co/prithivMLmods/Qwen2.5-VL-3B-Abliterated-Caption-it
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ base_model: prithivMLmods/Qwen2.5-VL-3B-Abliterated-Caption-it
3
+ language:
4
+ - en
5
+ library_name: transformers
6
+ mradermacher:
7
+ readme_rev: 1
8
+ quantized_by: mradermacher
9
+ tags:
10
+ - text-generation-inference
11
+ - uncensored
12
+ - image-captioning
13
+ - vlm
14
+ - visual-understanding
15
+ - caption
16
+ - image-to-text
17
+ ---
18
+ ## About
19
+
20
  <!-- ### quantize_version: 2 -->
21
  <!-- ### output_tensor_quantised: 1 -->
22
  <!-- ### convert_type: hf -->
 
26
  <!-- ### quants_skip: -->
27
  <!-- ### skip_mmproj: -->
28
  weighted/imatrix quants of https://huggingface.co/prithivMLmods/Qwen2.5-VL-3B-Abliterated-Caption-it
29
+
30
+ <!-- provided-files -->
31
+
32
+ ***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#Qwen2.5-VL-3B-Abliterated-Caption-it-i1-GGUF).***
33
+
34
+ static quants are available at https://huggingface.co/mradermacher/Qwen2.5-VL-3B-Abliterated-Caption-it-GGUF
35
+
36
+ **This is a vision model - mmproj files (if any) will be in the [static repository](https://huggingface.co/mradermacher/Qwen2.5-VL-3B-Abliterated-Caption-it-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/Qwen2.5-VL-3B-Abliterated-Caption-it-i1-GGUF/resolve/main/Qwen2.5-VL-3B-Abliterated-Caption-it.imatrix.gguf) | imatrix | 0.1 | imatrix file (for creating your own qwuants) |
50
+ | [GGUF](https://huggingface.co/mradermacher/Qwen2.5-VL-3B-Abliterated-Caption-it-i1-GGUF/resolve/main/Qwen2.5-VL-3B-Abliterated-Caption-it.i1-IQ1_S.gguf) | i1-IQ1_S | 0.9 | for the desperate |
51
+ | [GGUF](https://huggingface.co/mradermacher/Qwen2.5-VL-3B-Abliterated-Caption-it-i1-GGUF/resolve/main/Qwen2.5-VL-3B-Abliterated-Caption-it.i1-IQ1_M.gguf) | i1-IQ1_M | 1.0 | mostly desperate |
52
+ | [GGUF](https://huggingface.co/mradermacher/Qwen2.5-VL-3B-Abliterated-Caption-it-i1-GGUF/resolve/main/Qwen2.5-VL-3B-Abliterated-Caption-it.i1-IQ2_XXS.gguf) | i1-IQ2_XXS | 1.0 | |
53
+ | [GGUF](https://huggingface.co/mradermacher/Qwen2.5-VL-3B-Abliterated-Caption-it-i1-GGUF/resolve/main/Qwen2.5-VL-3B-Abliterated-Caption-it.i1-IQ2_XS.gguf) | i1-IQ2_XS | 1.1 | |
54
+ | [GGUF](https://huggingface.co/mradermacher/Qwen2.5-VL-3B-Abliterated-Caption-it-i1-GGUF/resolve/main/Qwen2.5-VL-3B-Abliterated-Caption-it.i1-IQ2_S.gguf) | i1-IQ2_S | 1.2 | |
55
+ | [GGUF](https://huggingface.co/mradermacher/Qwen2.5-VL-3B-Abliterated-Caption-it-i1-GGUF/resolve/main/Qwen2.5-VL-3B-Abliterated-Caption-it.i1-IQ2_M.gguf) | i1-IQ2_M | 1.2 | |
56
+ | [GGUF](https://huggingface.co/mradermacher/Qwen2.5-VL-3B-Abliterated-Caption-it-i1-GGUF/resolve/main/Qwen2.5-VL-3B-Abliterated-Caption-it.i1-Q2_K_S.gguf) | i1-Q2_K_S | 1.3 | very low quality |
57
+ | [GGUF](https://huggingface.co/mradermacher/Qwen2.5-VL-3B-Abliterated-Caption-it-i1-GGUF/resolve/main/Qwen2.5-VL-3B-Abliterated-Caption-it.i1-Q2_K.gguf) | i1-Q2_K | 1.4 | IQ3_XXS probably better |
58
+ | [GGUF](https://huggingface.co/mradermacher/Qwen2.5-VL-3B-Abliterated-Caption-it-i1-GGUF/resolve/main/Qwen2.5-VL-3B-Abliterated-Caption-it.i1-IQ3_XXS.gguf) | i1-IQ3_XXS | 1.4 | lower quality |
59
+ | [GGUF](https://huggingface.co/mradermacher/Qwen2.5-VL-3B-Abliterated-Caption-it-i1-GGUF/resolve/main/Qwen2.5-VL-3B-Abliterated-Caption-it.i1-IQ3_XS.gguf) | i1-IQ3_XS | 1.5 | |
60
+ | [GGUF](https://huggingface.co/mradermacher/Qwen2.5-VL-3B-Abliterated-Caption-it-i1-GGUF/resolve/main/Qwen2.5-VL-3B-Abliterated-Caption-it.i1-Q3_K_S.gguf) | i1-Q3_K_S | 1.6 | IQ3_XS probably better |
61
+ | [GGUF](https://huggingface.co/mradermacher/Qwen2.5-VL-3B-Abliterated-Caption-it-i1-GGUF/resolve/main/Qwen2.5-VL-3B-Abliterated-Caption-it.i1-IQ3_S.gguf) | i1-IQ3_S | 1.6 | beats Q3_K* |
62
+ | [GGUF](https://huggingface.co/mradermacher/Qwen2.5-VL-3B-Abliterated-Caption-it-i1-GGUF/resolve/main/Qwen2.5-VL-3B-Abliterated-Caption-it.i1-IQ3_M.gguf) | i1-IQ3_M | 1.6 | |
63
+ | [GGUF](https://huggingface.co/mradermacher/Qwen2.5-VL-3B-Abliterated-Caption-it-i1-GGUF/resolve/main/Qwen2.5-VL-3B-Abliterated-Caption-it.i1-Q3_K_M.gguf) | i1-Q3_K_M | 1.7 | IQ3_S probably better |
64
+ | [GGUF](https://huggingface.co/mradermacher/Qwen2.5-VL-3B-Abliterated-Caption-it-i1-GGUF/resolve/main/Qwen2.5-VL-3B-Abliterated-Caption-it.i1-Q3_K_L.gguf) | i1-Q3_K_L | 1.8 | IQ3_M probably better |
65
+ | [GGUF](https://huggingface.co/mradermacher/Qwen2.5-VL-3B-Abliterated-Caption-it-i1-GGUF/resolve/main/Qwen2.5-VL-3B-Abliterated-Caption-it.i1-IQ4_XS.gguf) | i1-IQ4_XS | 1.8 | |
66
+ | [GGUF](https://huggingface.co/mradermacher/Qwen2.5-VL-3B-Abliterated-Caption-it-i1-GGUF/resolve/main/Qwen2.5-VL-3B-Abliterated-Caption-it.i1-IQ4_NL.gguf) | i1-IQ4_NL | 1.9 | prefer IQ4_XS |
67
+ | [GGUF](https://huggingface.co/mradermacher/Qwen2.5-VL-3B-Abliterated-Caption-it-i1-GGUF/resolve/main/Qwen2.5-VL-3B-Abliterated-Caption-it.i1-Q4_0.gguf) | i1-Q4_0 | 1.9 | fast, low quality |
68
+ | [GGUF](https://huggingface.co/mradermacher/Qwen2.5-VL-3B-Abliterated-Caption-it-i1-GGUF/resolve/main/Qwen2.5-VL-3B-Abliterated-Caption-it.i1-Q4_K_S.gguf) | i1-Q4_K_S | 1.9 | optimal size/speed/quality |
69
+ | [GGUF](https://huggingface.co/mradermacher/Qwen2.5-VL-3B-Abliterated-Caption-it-i1-GGUF/resolve/main/Qwen2.5-VL-3B-Abliterated-Caption-it.i1-Q4_K_M.gguf) | i1-Q4_K_M | 2.0 | fast, recommended |
70
+ | [GGUF](https://huggingface.co/mradermacher/Qwen2.5-VL-3B-Abliterated-Caption-it-i1-GGUF/resolve/main/Qwen2.5-VL-3B-Abliterated-Caption-it.i1-Q4_1.gguf) | i1-Q4_1 | 2.1 | |
71
+ | [GGUF](https://huggingface.co/mradermacher/Qwen2.5-VL-3B-Abliterated-Caption-it-i1-GGUF/resolve/main/Qwen2.5-VL-3B-Abliterated-Caption-it.i1-Q5_K_S.gguf) | i1-Q5_K_S | 2.3 | |
72
+ | [GGUF](https://huggingface.co/mradermacher/Qwen2.5-VL-3B-Abliterated-Caption-it-i1-GGUF/resolve/main/Qwen2.5-VL-3B-Abliterated-Caption-it.i1-Q5_K_M.gguf) | i1-Q5_K_M | 2.3 | |
73
+ | [GGUF](https://huggingface.co/mradermacher/Qwen2.5-VL-3B-Abliterated-Caption-it-i1-GGUF/resolve/main/Qwen2.5-VL-3B-Abliterated-Caption-it.i1-Q6_K.gguf) | i1-Q6_K | 2.6 | 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 -->