Upload folder using huggingface_hub
Browse files- .gitattributes +12 -0
- DeepSeek-R1-Distill-Qwen-32B-Q2_K.gguf +3 -0
- DeepSeek-R1-Distill-Qwen-32B-Q3_K_L.gguf +3 -0
- DeepSeek-R1-Distill-Qwen-32B-Q3_K_M.gguf +3 -0
- DeepSeek-R1-Distill-Qwen-32B-Q3_K_S.gguf +3 -0
- DeepSeek-R1-Distill-Qwen-32B-Q4_0.gguf +3 -0
- DeepSeek-R1-Distill-Qwen-32B-Q4_K_M.gguf +3 -0
- DeepSeek-R1-Distill-Qwen-32B-Q4_K_S.gguf +3 -0
- DeepSeek-R1-Distill-Qwen-32B-Q5_0.gguf +3 -0
- DeepSeek-R1-Distill-Qwen-32B-Q5_K_M.gguf +3 -0
- DeepSeek-R1-Distill-Qwen-32B-Q5_K_S.gguf +3 -0
- DeepSeek-R1-Distill-Qwen-32B-Q6_K.gguf +3 -0
- DeepSeek-R1-Distill-Qwen-32B-Q8_0.gguf +3 -0
- README.md +75 -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 |
+
DeepSeek-R1-Distill-Qwen-32B-Q2_K.gguf filter=lfs diff=lfs merge=lfs -text
|
37 |
+
DeepSeek-R1-Distill-Qwen-32B-Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text
|
38 |
+
DeepSeek-R1-Distill-Qwen-32B-Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text
|
39 |
+
DeepSeek-R1-Distill-Qwen-32B-Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text
|
40 |
+
DeepSeek-R1-Distill-Qwen-32B-Q4_0.gguf filter=lfs diff=lfs merge=lfs -text
|
41 |
+
DeepSeek-R1-Distill-Qwen-32B-Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text
|
42 |
+
DeepSeek-R1-Distill-Qwen-32B-Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text
|
43 |
+
DeepSeek-R1-Distill-Qwen-32B-Q5_0.gguf filter=lfs diff=lfs merge=lfs -text
|
44 |
+
DeepSeek-R1-Distill-Qwen-32B-Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text
|
45 |
+
DeepSeek-R1-Distill-Qwen-32B-Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text
|
46 |
+
DeepSeek-R1-Distill-Qwen-32B-Q6_K.gguf filter=lfs diff=lfs merge=lfs -text
|
47 |
+
DeepSeek-R1-Distill-Qwen-32B-Q8_0.gguf filter=lfs diff=lfs merge=lfs -text
|
DeepSeek-R1-Distill-Qwen-32B-Q2_K.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:092c13007938e38520c7645a54ae956f066fd3f71ec64c672edf7c3ce38d8667
|
3 |
+
size 12313098144
|
DeepSeek-R1-Distill-Qwen-32B-Q3_K_L.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:7b9635bbf9c90241d1629136eb3322be69aa30d8462192ca26c7ebd294ef15b2
|
3 |
+
size 17247078304
|
DeepSeek-R1-Distill-Qwen-32B-Q3_K_M.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:8dbb8d113984061de9b820f2a9b9fbf17023ea46d17766db38d2f1030eab7b59
|
3 |
+
size 15935047584
|
DeepSeek-R1-Distill-Qwen-32B-Q3_K_S.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:c0fa87c75674c4a43180e458f1c129911860192ef7f9bd24a314af90ef009bbe
|
3 |
+
size 14392330144
|
DeepSeek-R1-Distill-Qwen-32B-Q4_0.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:a2ada50128b0f188241b7b4296dc34d0a0feb8ea1dba06382e381a76a448414a
|
3 |
+
size 18640230304
|
DeepSeek-R1-Distill-Qwen-32B-Q4_K_M.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:d40138b137925a4c0ad798d4e04e02a718a53a179fe1f7cb5f273dbdffe5f783
|
3 |
+
size 19851335584
|
DeepSeek-R1-Distill-Qwen-32B-Q4_K_S.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:0b22f0e29798ea1b0d628031e59944e4f9da9b3c7914c6037d0e15cc65b2d975
|
3 |
+
size 18784409504
|
DeepSeek-R1-Distill-Qwen-32B-Q5_0.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:03247c3f6925e0feeae9177a1183d55eca4636e7937cba177c86875d64864119
|
3 |
+
size 22638253984
|
DeepSeek-R1-Distill-Qwen-32B-Q5_K_M.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:324f155eea30976dfe7253e02f752a57390b49d0b956bdd61fac2f202543dad0
|
3 |
+
size 23262156704
|
DeepSeek-R1-Distill-Qwen-32B-Q5_K_S.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:6c16c58c738cc0ebeb63abf4b40b7fd6481c6e3964a9215c67487d6940c06e4b
|
3 |
+
size 22638253984
|
DeepSeek-R1-Distill-Qwen-32B-Q6_K.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:05bfd58cc49069ecc3e4a01a9be0c889651d7bcf9de3d1ba6cd7796c7eb7617f
|
3 |
+
size 26886154144
|
DeepSeek-R1-Distill-Qwen-32B-Q8_0.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:4f049246c8659097011864464ebf2a63293dd84f244980a934e7d8b9f13554bc
|
3 |
+
size 34820884384
|
README.md
ADDED
@@ -0,0 +1,75 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
base_model: deepseek-ai/DeepSeek-R1-Distill-Qwen-32B
|
3 |
+
tags:
|
4 |
+
- TensorBlock
|
5 |
+
- GGUF
|
6 |
+
---
|
7 |
+
|
8 |
+
<div style="width: auto; margin-left: auto; margin-right: auto">
|
9 |
+
<img src="https://i.imgur.com/jC7kdl8.jpeg" alt="TensorBlock" style="width: 100%; min-width: 400px; display: block; margin: auto;">
|
10 |
+
</div>
|
11 |
+
<div style="display: flex; justify-content: space-between; width: 100%;">
|
12 |
+
<div style="display: flex; flex-direction: column; align-items: flex-start;">
|
13 |
+
<p style="margin-top: 0.5em; margin-bottom: 0em;">
|
14 |
+
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>
|
15 |
+
</p>
|
16 |
+
</div>
|
17 |
+
</div>
|
18 |
+
|
19 |
+
## deepseek-ai/DeepSeek-R1-Distill-Qwen-32B - GGUF
|
20 |
+
|
21 |
+
This repo contains GGUF format model files for [deepseek-ai/DeepSeek-R1-Distill-Qwen-32B](https://huggingface.co/deepseek-ai/DeepSeek-R1-Distill-Qwen-32B).
|
22 |
+
|
23 |
+
The files were quantized using machines provided by [TensorBlock](https://tensorblock.co/), and they are compatible with llama.cpp as of [commit ec7f3ac](https://github.com/ggerganov/llama.cpp/commit/ec7f3ac9ab33e46b136eb5ab6a76c4d81f57c7f1).
|
24 |
+
|
25 |
+
<div style="text-align: left; margin: 20px 0;">
|
26 |
+
<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;">
|
27 |
+
Run them on the TensorBlock client using your local machine ↗
|
28 |
+
</a>
|
29 |
+
</div>
|
30 |
+
|
31 |
+
## Prompt template
|
32 |
+
|
33 |
+
```
|
34 |
+
<|begin▁of▁sentence|>{system_prompt}<|User|>{prompt}<|Assistant|>
|
35 |
+
```
|
36 |
+
|
37 |
+
## Model file specification
|
38 |
+
|
39 |
+
| Filename | Quant type | File Size | Description |
|
40 |
+
| -------- | ---------- | --------- | ----------- |
|
41 |
+
| [DeepSeek-R1-Distill-Qwen-32B-Q2_K.gguf](https://huggingface.co/tensorblock/DeepSeek-R1-Distill-Qwen-32B-GGUF/blob/main/DeepSeek-R1-Distill-Qwen-32B-Q2_K.gguf) | Q2_K | 12.313 GB | smallest, significant quality loss - not recommended for most purposes |
|
42 |
+
| [DeepSeek-R1-Distill-Qwen-32B-Q3_K_S.gguf](https://huggingface.co/tensorblock/DeepSeek-R1-Distill-Qwen-32B-GGUF/blob/main/DeepSeek-R1-Distill-Qwen-32B-Q3_K_S.gguf) | Q3_K_S | 14.392 GB | very small, high quality loss |
|
43 |
+
| [DeepSeek-R1-Distill-Qwen-32B-Q3_K_M.gguf](https://huggingface.co/tensorblock/DeepSeek-R1-Distill-Qwen-32B-GGUF/blob/main/DeepSeek-R1-Distill-Qwen-32B-Q3_K_M.gguf) | Q3_K_M | 15.935 GB | very small, high quality loss |
|
44 |
+
| [DeepSeek-R1-Distill-Qwen-32B-Q3_K_L.gguf](https://huggingface.co/tensorblock/DeepSeek-R1-Distill-Qwen-32B-GGUF/blob/main/DeepSeek-R1-Distill-Qwen-32B-Q3_K_L.gguf) | Q3_K_L | 17.247 GB | small, substantial quality loss |
|
45 |
+
| [DeepSeek-R1-Distill-Qwen-32B-Q4_0.gguf](https://huggingface.co/tensorblock/DeepSeek-R1-Distill-Qwen-32B-GGUF/blob/main/DeepSeek-R1-Distill-Qwen-32B-Q4_0.gguf) | Q4_0 | 18.640 GB | legacy; small, very high quality loss - prefer using Q3_K_M |
|
46 |
+
| [DeepSeek-R1-Distill-Qwen-32B-Q4_K_S.gguf](https://huggingface.co/tensorblock/DeepSeek-R1-Distill-Qwen-32B-GGUF/blob/main/DeepSeek-R1-Distill-Qwen-32B-Q4_K_S.gguf) | Q4_K_S | 18.784 GB | small, greater quality loss |
|
47 |
+
| [DeepSeek-R1-Distill-Qwen-32B-Q4_K_M.gguf](https://huggingface.co/tensorblock/DeepSeek-R1-Distill-Qwen-32B-GGUF/blob/main/DeepSeek-R1-Distill-Qwen-32B-Q4_K_M.gguf) | Q4_K_M | 19.851 GB | medium, balanced quality - recommended |
|
48 |
+
| [DeepSeek-R1-Distill-Qwen-32B-Q5_0.gguf](https://huggingface.co/tensorblock/DeepSeek-R1-Distill-Qwen-32B-GGUF/blob/main/DeepSeek-R1-Distill-Qwen-32B-Q5_0.gguf) | Q5_0 | 22.638 GB | legacy; medium, balanced quality - prefer using Q4_K_M |
|
49 |
+
| [DeepSeek-R1-Distill-Qwen-32B-Q5_K_S.gguf](https://huggingface.co/tensorblock/DeepSeek-R1-Distill-Qwen-32B-GGUF/blob/main/DeepSeek-R1-Distill-Qwen-32B-Q5_K_S.gguf) | Q5_K_S | 22.638 GB | large, low quality loss - recommended |
|
50 |
+
| [DeepSeek-R1-Distill-Qwen-32B-Q5_K_M.gguf](https://huggingface.co/tensorblock/DeepSeek-R1-Distill-Qwen-32B-GGUF/blob/main/DeepSeek-R1-Distill-Qwen-32B-Q5_K_M.gguf) | Q5_K_M | 23.262 GB | large, very low quality loss - recommended |
|
51 |
+
| [DeepSeek-R1-Distill-Qwen-32B-Q6_K.gguf](https://huggingface.co/tensorblock/DeepSeek-R1-Distill-Qwen-32B-GGUF/blob/main/DeepSeek-R1-Distill-Qwen-32B-Q6_K.gguf) | Q6_K | 26.886 GB | very large, extremely low quality loss |
|
52 |
+
| [DeepSeek-R1-Distill-Qwen-32B-Q8_0.gguf](https://huggingface.co/tensorblock/DeepSeek-R1-Distill-Qwen-32B-GGUF/blob/main/DeepSeek-R1-Distill-Qwen-32B-Q8_0.gguf) | Q8_0 | 34.821 GB | very large, extremely low quality loss - not recommended |
|
53 |
+
|
54 |
+
|
55 |
+
## Downloading instruction
|
56 |
+
|
57 |
+
### Command line
|
58 |
+
|
59 |
+
Firstly, install Huggingface Client
|
60 |
+
|
61 |
+
```shell
|
62 |
+
pip install -U "huggingface_hub[cli]"
|
63 |
+
```
|
64 |
+
|
65 |
+
Then, downoad the individual model file the a local directory
|
66 |
+
|
67 |
+
```shell
|
68 |
+
huggingface-cli download tensorblock/DeepSeek-R1-Distill-Qwen-32B-GGUF --include "DeepSeek-R1-Distill-Qwen-32B-Q2_K.gguf" --local-dir MY_LOCAL_DIR
|
69 |
+
```
|
70 |
+
|
71 |
+
If you wanna download multiple model files with a pattern (e.g., `*Q4_K*gguf`), you can try:
|
72 |
+
|
73 |
+
```shell
|
74 |
+
huggingface-cli download tensorblock/DeepSeek-R1-Distill-Qwen-32B-GGUF --local-dir MY_LOCAL_DIR --local-dir-use-symlinks False --include='*Q4_K*gguf'
|
75 |
+
```
|