Upload folder using huggingface_hub
Browse files- .gitattributes +12 -0
- QwQ-32B-Preview-abliterated-Q2_K.gguf +3 -0
- QwQ-32B-Preview-abliterated-Q3_K_L.gguf +3 -0
- QwQ-32B-Preview-abliterated-Q3_K_M.gguf +3 -0
- QwQ-32B-Preview-abliterated-Q3_K_S.gguf +3 -0
- QwQ-32B-Preview-abliterated-Q4_0.gguf +3 -0
- QwQ-32B-Preview-abliterated-Q4_K_M.gguf +3 -0
- QwQ-32B-Preview-abliterated-Q4_K_S.gguf +3 -0
- QwQ-32B-Preview-abliterated-Q5_0.gguf +3 -0
- QwQ-32B-Preview-abliterated-Q5_K_M.gguf +3 -0
- QwQ-32B-Preview-abliterated-Q5_K_S.gguf +3 -0
- QwQ-32B-Preview-abliterated-Q6_K.gguf +3 -0
- QwQ-32B-Preview-abliterated-Q8_0.gguf +3 -0
- README.md +88 -0
.gitattributes
CHANGED
@@ -33,3 +33,15 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
|
|
33 |
*.zip filter=lfs diff=lfs merge=lfs -text
|
34 |
*.zst filter=lfs diff=lfs merge=lfs -text
|
35 |
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
33 |
*.zip filter=lfs diff=lfs merge=lfs -text
|
34 |
*.zst filter=lfs diff=lfs merge=lfs -text
|
35 |
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
36 |
+
QwQ-32B-Preview-abliterated-Q2_K.gguf filter=lfs diff=lfs merge=lfs -text
|
37 |
+
QwQ-32B-Preview-abliterated-Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text
|
38 |
+
QwQ-32B-Preview-abliterated-Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text
|
39 |
+
QwQ-32B-Preview-abliterated-Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text
|
40 |
+
QwQ-32B-Preview-abliterated-Q4_0.gguf filter=lfs diff=lfs merge=lfs -text
|
41 |
+
QwQ-32B-Preview-abliterated-Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text
|
42 |
+
QwQ-32B-Preview-abliterated-Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text
|
43 |
+
QwQ-32B-Preview-abliterated-Q5_0.gguf filter=lfs diff=lfs merge=lfs -text
|
44 |
+
QwQ-32B-Preview-abliterated-Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text
|
45 |
+
QwQ-32B-Preview-abliterated-Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text
|
46 |
+
QwQ-32B-Preview-abliterated-Q6_K.gguf filter=lfs diff=lfs merge=lfs -text
|
47 |
+
QwQ-32B-Preview-abliterated-Q8_0.gguf filter=lfs diff=lfs merge=lfs -text
|
QwQ-32B-Preview-abliterated-Q2_K.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:80b8179b15a264a262cf887ca76405e75bb3d9d283a56e5db84f5cbfaf9dec59
|
3 |
+
size 12313098944
|
QwQ-32B-Preview-abliterated-Q3_K_L.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:1606ff81811a738d36eef8a3fef3116000208ecafdd7d35e80f6173e1aa08e38
|
3 |
+
size 17247079104
|
QwQ-32B-Preview-abliterated-Q3_K_M.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:8aae2f825642b505f97552ef6bbdc1ba5e315a3bf1ebbb160bb922538db9ac80
|
3 |
+
size 15935048384
|
QwQ-32B-Preview-abliterated-Q3_K_S.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:0be2ba394f59e586a0b72956089fac7830a74ef1e2ed33a7238e423884098139
|
3 |
+
size 14392330944
|
QwQ-32B-Preview-abliterated-Q4_0.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:80a497fc788e7593be508ec0e1b357b3832fd74bc2763d603d5d43415115368f
|
3 |
+
size 18640231104
|
QwQ-32B-Preview-abliterated-Q4_K_M.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:6278acec322cac64ac9f5f98578a16e6ca88d361ebb3f54b82a3a5d1b0208a61
|
3 |
+
size 19851336384
|
QwQ-32B-Preview-abliterated-Q4_K_S.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:bfed5dcfa09cb2f3495dccfde2e5359e6dbe40fe873b1873efa4a097b88a5c8b
|
3 |
+
size 18784410304
|
QwQ-32B-Preview-abliterated-Q5_0.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:f585759ce9f847c8dbe1ded4c42bf783f8b4abc473bfb7c223b681e177b0a181
|
3 |
+
size 22638254784
|
QwQ-32B-Preview-abliterated-Q5_K_M.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:0c8c5f71efbe8787c39608c69874f63684a9aeb8636485d7f78f7d8aa9ddc6c7
|
3 |
+
size 23262157504
|
QwQ-32B-Preview-abliterated-Q5_K_S.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:2a452630f1702847a425202c19d5b935885472895de090f6c00336cf80438e08
|
3 |
+
size 22638254784
|
QwQ-32B-Preview-abliterated-Q6_K.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:80e3cc42dd173f6931d54ce34c5eb7ad51829c98ae561a90f802b24fc4a5c6a8
|
3 |
+
size 26886154944
|
QwQ-32B-Preview-abliterated-Q8_0.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:f82fb2c2772d5d8747922a208612cb5c84715195a79d5149893a732f11550b9f
|
3 |
+
size 34820885184
|
README.md
ADDED
@@ -0,0 +1,88 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
license: apache-2.0
|
3 |
+
license_link: https://huggingface.co/huihui-ai/QwQ-32B-Preview-abliterated/blob/main/LICENSE
|
4 |
+
language:
|
5 |
+
- en
|
6 |
+
pipeline_tag: text-generation
|
7 |
+
base_model: huihui-ai/QwQ-32B-Preview-abliterated
|
8 |
+
tags:
|
9 |
+
- chat
|
10 |
+
- abliterated
|
11 |
+
- uncensored
|
12 |
+
- TensorBlock
|
13 |
+
- GGUF
|
14 |
+
library_name: transformers
|
15 |
+
---
|
16 |
+
|
17 |
+
<div style="width: auto; margin-left: auto; margin-right: auto">
|
18 |
+
<img src="https://i.imgur.com/jC7kdl8.jpeg" alt="TensorBlock" style="width: 100%; min-width: 400px; display: block; margin: auto;">
|
19 |
+
</div>
|
20 |
+
<div style="display: flex; justify-content: space-between; width: 100%;">
|
21 |
+
<div style="display: flex; flex-direction: column; align-items: flex-start;">
|
22 |
+
<p style="margin-top: 0.5em; margin-bottom: 0em;">
|
23 |
+
Feedback and support: TensorBlock's <a href="https://x.com/tensorblock_aoi">Twitter/X</a>, <a href="https://t.me/TensorBlock">Telegram Group</a> and <a href="https://x.com/tensorblock_aoi">Discord server</a>
|
24 |
+
</p>
|
25 |
+
</div>
|
26 |
+
</div>
|
27 |
+
|
28 |
+
## huihui-ai/QwQ-32B-Preview-abliterated - GGUF
|
29 |
+
|
30 |
+
This repo contains GGUF format model files for [huihui-ai/QwQ-32B-Preview-abliterated](https://huggingface.co/huihui-ai/QwQ-32B-Preview-abliterated).
|
31 |
+
|
32 |
+
The files were quantized using machines provided by [TensorBlock](https://tensorblock.co/), and they are compatible with llama.cpp as of [commit b4242](https://github.com/ggerganov/llama.cpp/commit/a6744e43e80f4be6398fc7733a01642c846dce1d).
|
33 |
+
|
34 |
+
<div style="text-align: left; margin: 20px 0;">
|
35 |
+
<a href="https://tensorblock.co/waitlist/client" style="display: inline-block; padding: 10px 20px; background-color: #007bff; color: white; text-decoration: none; border-radius: 5px; font-weight: bold;">
|
36 |
+
Run them on the TensorBlock client using your local machine ↗
|
37 |
+
</a>
|
38 |
+
</div>
|
39 |
+
|
40 |
+
## Prompt template
|
41 |
+
|
42 |
+
```
|
43 |
+
<|im_start|>system
|
44 |
+
{system_prompt}<|im_end|>
|
45 |
+
<|im_start|>user
|
46 |
+
{prompt}<|im_end|>
|
47 |
+
<|im_start|>assistant
|
48 |
+
```
|
49 |
+
|
50 |
+
## Model file specification
|
51 |
+
|
52 |
+
| Filename | Quant type | File Size | Description |
|
53 |
+
| -------- | ---------- | --------- | ----------- |
|
54 |
+
| [QwQ-32B-Preview-abliterated-Q2_K.gguf](https://huggingface.co/tensorblock/QwQ-32B-Preview-abliterated-GGUF/blob/main/QwQ-32B-Preview-abliterated-Q2_K.gguf) | Q2_K | 12.313 GB | smallest, significant quality loss - not recommended for most purposes |
|
55 |
+
| [QwQ-32B-Preview-abliterated-Q3_K_S.gguf](https://huggingface.co/tensorblock/QwQ-32B-Preview-abliterated-GGUF/blob/main/QwQ-32B-Preview-abliterated-Q3_K_S.gguf) | Q3_K_S | 14.392 GB | very small, high quality loss |
|
56 |
+
| [QwQ-32B-Preview-abliterated-Q3_K_M.gguf](https://huggingface.co/tensorblock/QwQ-32B-Preview-abliterated-GGUF/blob/main/QwQ-32B-Preview-abliterated-Q3_K_M.gguf) | Q3_K_M | 15.935 GB | very small, high quality loss |
|
57 |
+
| [QwQ-32B-Preview-abliterated-Q3_K_L.gguf](https://huggingface.co/tensorblock/QwQ-32B-Preview-abliterated-GGUF/blob/main/QwQ-32B-Preview-abliterated-Q3_K_L.gguf) | Q3_K_L | 17.247 GB | small, substantial quality loss |
|
58 |
+
| [QwQ-32B-Preview-abliterated-Q4_0.gguf](https://huggingface.co/tensorblock/QwQ-32B-Preview-abliterated-GGUF/blob/main/QwQ-32B-Preview-abliterated-Q4_0.gguf) | Q4_0 | 18.640 GB | legacy; small, very high quality loss - prefer using Q3_K_M |
|
59 |
+
| [QwQ-32B-Preview-abliterated-Q4_K_S.gguf](https://huggingface.co/tensorblock/QwQ-32B-Preview-abliterated-GGUF/blob/main/QwQ-32B-Preview-abliterated-Q4_K_S.gguf) | Q4_K_S | 18.784 GB | small, greater quality loss |
|
60 |
+
| [QwQ-32B-Preview-abliterated-Q4_K_M.gguf](https://huggingface.co/tensorblock/QwQ-32B-Preview-abliterated-GGUF/blob/main/QwQ-32B-Preview-abliterated-Q4_K_M.gguf) | Q4_K_M | 19.851 GB | medium, balanced quality - recommended |
|
61 |
+
| [QwQ-32B-Preview-abliterated-Q5_0.gguf](https://huggingface.co/tensorblock/QwQ-32B-Preview-abliterated-GGUF/blob/main/QwQ-32B-Preview-abliterated-Q5_0.gguf) | Q5_0 | 22.638 GB | legacy; medium, balanced quality - prefer using Q4_K_M |
|
62 |
+
| [QwQ-32B-Preview-abliterated-Q5_K_S.gguf](https://huggingface.co/tensorblock/QwQ-32B-Preview-abliterated-GGUF/blob/main/QwQ-32B-Preview-abliterated-Q5_K_S.gguf) | Q5_K_S | 22.638 GB | large, low quality loss - recommended |
|
63 |
+
| [QwQ-32B-Preview-abliterated-Q5_K_M.gguf](https://huggingface.co/tensorblock/QwQ-32B-Preview-abliterated-GGUF/blob/main/QwQ-32B-Preview-abliterated-Q5_K_M.gguf) | Q5_K_M | 23.262 GB | large, very low quality loss - recommended |
|
64 |
+
| [QwQ-32B-Preview-abliterated-Q6_K.gguf](https://huggingface.co/tensorblock/QwQ-32B-Preview-abliterated-GGUF/blob/main/QwQ-32B-Preview-abliterated-Q6_K.gguf) | Q6_K | 26.886 GB | very large, extremely low quality loss |
|
65 |
+
| [QwQ-32B-Preview-abliterated-Q8_0.gguf](https://huggingface.co/tensorblock/QwQ-32B-Preview-abliterated-GGUF/blob/main/QwQ-32B-Preview-abliterated-Q8_0.gguf) | Q8_0 | 34.821 GB | very large, extremely low quality loss - not recommended |
|
66 |
+
|
67 |
+
|
68 |
+
## Downloading instruction
|
69 |
+
|
70 |
+
### Command line
|
71 |
+
|
72 |
+
Firstly, install Huggingface Client
|
73 |
+
|
74 |
+
```shell
|
75 |
+
pip install -U "huggingface_hub[cli]"
|
76 |
+
```
|
77 |
+
|
78 |
+
Then, downoad the individual model file the a local directory
|
79 |
+
|
80 |
+
```shell
|
81 |
+
huggingface-cli download tensorblock/QwQ-32B-Preview-abliterated-GGUF --include "QwQ-32B-Preview-abliterated-Q2_K.gguf" --local-dir MY_LOCAL_DIR
|
82 |
+
```
|
83 |
+
|
84 |
+
If you wanna download multiple model files with a pattern (e.g., `*Q4_K*gguf`), you can try:
|
85 |
+
|
86 |
+
```shell
|
87 |
+
huggingface-cli download tensorblock/QwQ-32B-Preview-abliterated-GGUF --local-dir MY_LOCAL_DIR --local-dir-use-symlinks False --include='*Q4_K*gguf'
|
88 |
+
```
|