Hugging Face's logo

mradermacher
/
Qwen2.5-3B-Instruct-abliterated-GGUF

Transformers
GGUF
English
chat
abliterated
uncensored
conversational
Model card Files Community
mradermacher commited on
Commit
1488106
·
verified ·
1 Parent(s): dc825b1

auto-patch README.md

Browse files
Files changed (1) hide show
  1. README.md +13 -12
README.md CHANGED
@@ -34,17 +34,18 @@ more details, including on how to concatenate multi-part files.
34
 
35
  | Link | Type | Size/GB | Notes |
36
  |:-----|:-----|--------:|:------|
37
- | [GGUF](https://huggingface.co/mradermacher/Qwen2.5-3B-Instruct-Abliterated-GGUF/resolve/main/Qwen2.5-3B-Instruct-abliterated.Q2_K.gguf) | Q2_K | 1.4 | |
38
- | [GGUF](https://huggingface.co/mradermacher/Qwen2.5-3B-Instruct-Abliterated-GGUF/resolve/main/Qwen2.5-3B-Instruct-abliterated.Q3_K_S.gguf) | Q3_K_S | 1.6 | |
39
- | [GGUF](https://huggingface.co/mradermacher/Qwen2.5-3B-Instruct-Abliterated-GGUF/resolve/main/Qwen2.5-3B-Instruct-abliterated.Q3_K_M.gguf) | Q3_K_M | 1.7 | lower quality |
40
- | [GGUF](https://huggingface.co/mradermacher/Qwen2.5-3B-Instruct-Abliterated-GGUF/resolve/main/Qwen2.5-3B-Instruct-abliterated.Q3_K_L.gguf) | Q3_K_L | 1.8 | |
41
- | [GGUF](https://huggingface.co/mradermacher/Qwen2.5-3B-Instruct-Abliterated-GGUF/resolve/main/Qwen2.5-3B-Instruct-abliterated.IQ4_XS.gguf) | IQ4_XS | 1.9 | |
42
- | [GGUF](https://huggingface.co/mradermacher/Qwen2.5-3B-Instruct-Abliterated-GGUF/resolve/main/Qwen2.5-3B-Instruct-abliterated.Q4_K_S.gguf) | Q4_K_S | 1.9 | fast, recommended |
43
- | [GGUF](https://huggingface.co/mradermacher/Qwen2.5-3B-Instruct-Abliterated-GGUF/resolve/main/Qwen2.5-3B-Instruct-abliterated.Q4_K_M.gguf) | Q4_K_M | 2.0 | fast, recommended |
44
- | [GGUF](https://huggingface.co/mradermacher/Qwen2.5-3B-Instruct-Abliterated-GGUF/resolve/main/Qwen2.5-3B-Instruct-abliterated.Q5_K_S.gguf) | Q5_K_S | 2.3 | |
45
- | [GGUF](https://huggingface.co/mradermacher/Qwen2.5-3B-Instruct-Abliterated-GGUF/resolve/main/Qwen2.5-3B-Instruct-abliterated.Q5_K_M.gguf) | Q5_K_M | 2.3 | |
46
- | [GGUF](https://huggingface.co/mradermacher/Qwen2.5-3B-Instruct-Abliterated-GGUF/resolve/main/Qwen2.5-3B-Instruct-abliterated.Q6_K.gguf) | Q6_K | 2.6 | very good quality |
47
- | [GGUF](https://huggingface.co/mradermacher/Qwen2.5-3B-Instruct-Abliterated-GGUF/resolve/main/Qwen2.5-3B-Instruct-abliterated.Q8_0.gguf) | Q8_0 | 3.4 | fast, best quality |
 
48
 
49
  Here is a handy graph by ikawrakow comparing some lower-quality quant
50
  types (lower is better):
@@ -63,6 +64,6 @@ questions you might have and/or if you want some other model quantized.
63
 
64
  I thank my company, [nethype GmbH](https://www.nethype.de/), for letting
65
  me use its servers and providing upgrades to my workstation to enable
66
- this work in my free time.
67
 
68
  <!-- end -->
 
34
 
35
  | Link | Type | Size/GB | Notes |
36
  |:-----|:-----|--------:|:------|
37
+ | [PART 1](https://huggingface.co/mradermacher/Qwen2.5-3B-Instruct-Abliterated-GGUF/resolve/main/Qwen2.5-3B-Instruct-Abliterated.Q2_K.gguf) [PART 2](https://huggingface.co/mradermacher/Qwen2.5-3B-Instruct-Abliterated-GGUF/resolve/main/Qwen2.5-3B-Instruct-abliterated.Q2_K.gguf) | Q2_K | 2.8 | |
38
+ | [PART 1](https://huggingface.co/mradermacher/Qwen2.5-3B-Instruct-Abliterated-GGUF/resolve/main/Qwen2.5-3B-Instruct-Abliterated.Q3_K_S.gguf) [PART 2](https://huggingface.co/mradermacher/Qwen2.5-3B-Instruct-Abliterated-GGUF/resolve/main/Qwen2.5-3B-Instruct-abliterated.Q3_K_S.gguf) | Q3_K_S | 3.1 | |
39
+ | [PART 1](https://huggingface.co/mradermacher/Qwen2.5-3B-Instruct-Abliterated-GGUF/resolve/main/Qwen2.5-3B-Instruct-Abliterated.Q3_K_M.gguf) [PART 2](https://huggingface.co/mradermacher/Qwen2.5-3B-Instruct-Abliterated-GGUF/resolve/main/Qwen2.5-3B-Instruct-abliterated.Q3_K_M.gguf) | Q3_K_M | 3.4 | lower quality |
40
+ | [PART 1](https://huggingface.co/mradermacher/Qwen2.5-3B-Instruct-Abliterated-GGUF/resolve/main/Qwen2.5-3B-Instruct-Abliterated.Q3_K_L.gguf) [PART 2](https://huggingface.co/mradermacher/Qwen2.5-3B-Instruct-Abliterated-GGUF/resolve/main/Qwen2.5-3B-Instruct-abliterated.Q3_K_L.gguf) | Q3_K_L | 3.6 | |
41
+ | [PART 1](https://huggingface.co/mradermacher/Qwen2.5-3B-Instruct-Abliterated-GGUF/resolve/main/Qwen2.5-3B-Instruct-Abliterated.IQ4_XS.gguf) [PART 2](https://huggingface.co/mradermacher/Qwen2.5-3B-Instruct-Abliterated-GGUF/resolve/main/Qwen2.5-3B-Instruct-abliterated.IQ4_XS.gguf) | IQ4_XS | 3.8 | |
42
+ | [PART 1](https://huggingface.co/mradermacher/Qwen2.5-3B-Instruct-Abliterated-GGUF/resolve/main/Qwen2.5-3B-Instruct-Abliterated.Q4_K_S.gguf) [PART 2](https://huggingface.co/mradermacher/Qwen2.5-3B-Instruct-Abliterated-GGUF/resolve/main/Qwen2.5-3B-Instruct-abliterated.Q4_K_S.gguf) | Q4_K_S | 3.9 | fast, recommended |
43
+ | [PART 1](https://huggingface.co/mradermacher/Qwen2.5-3B-Instruct-Abliterated-GGUF/resolve/main/Qwen2.5-3B-Instruct-Abliterated.Q4_K_M.gguf) [PART 2](https://huggingface.co/mradermacher/Qwen2.5-3B-Instruct-Abliterated-GGUF/resolve/main/Qwen2.5-3B-Instruct-abliterated.Q4_K_M.gguf) | Q4_K_M | 4.1 | fast, recommended |
44
+ | [PART 1](https://huggingface.co/mradermacher/Qwen2.5-3B-Instruct-Abliterated-GGUF/resolve/main/Qwen2.5-3B-Instruct-Abliterated.Q5_K_S.gguf) [PART 2](https://huggingface.co/mradermacher/Qwen2.5-3B-Instruct-Abliterated-GGUF/resolve/main/Qwen2.5-3B-Instruct-abliterated.Q5_K_S.gguf) | Q5_K_S | 4.7 | |
45
+ | [PART 1](https://huggingface.co/mradermacher/Qwen2.5-3B-Instruct-Abliterated-GGUF/resolve/main/Qwen2.5-3B-Instruct-Abliterated.Q5_K_M.gguf) [PART 2](https://huggingface.co/mradermacher/Qwen2.5-3B-Instruct-Abliterated-GGUF/resolve/main/Qwen2.5-3B-Instruct-abliterated.Q5_K_M.gguf) | Q5_K_M | 4.8 | |
46
+ | [PART 1](https://huggingface.co/mradermacher/Qwen2.5-3B-Instruct-Abliterated-GGUF/resolve/main/Qwen2.5-3B-Instruct-Abliterated.Q6_K.gguf) [PART 2](https://huggingface.co/mradermacher/Qwen2.5-3B-Instruct-Abliterated-GGUF/resolve/main/Qwen2.5-3B-Instruct-abliterated.Q6_K.gguf) | Q6_K | 5.4 | very good quality |
47
+ | [GGUF](https://huggingface.co/mradermacher/Qwen2.5-3B-Instruct-Abliterated-GGUF/resolve/main/Qwen2.5-3B-Instruct-Abliterated.f16.gguf) | f16 | 6.9 | 16 bpw, overkill |
48
+ | [PART 1](https://huggingface.co/mradermacher/Qwen2.5-3B-Instruct-Abliterated-GGUF/resolve/main/Qwen2.5-3B-Instruct-Abliterated.Q8_0.gguf) [PART 2](https://huggingface.co/mradermacher/Qwen2.5-3B-Instruct-Abliterated-GGUF/resolve/main/Qwen2.5-3B-Instruct-abliterated.Q8_0.gguf) | Q8_0 | 7.0 | fast, best quality |
49
 
50
  Here is a handy graph by ikawrakow comparing some lower-quality quant
51
  types (lower is better):
 
64
 
65
  I thank my company, [nethype GmbH](https://www.nethype.de/), for letting
66
  me use its servers and providing upgrades to my workstation to enable
67
+ 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.
68
 
69
  <!-- end -->