Upload folder using huggingface_hub
Browse files- .gitattributes +12 -0
- Qwen2.5-Coder-32B-Q2_K.gguf +3 -0
- Qwen2.5-Coder-32B-Q3_K_L.gguf +3 -0
- Qwen2.5-Coder-32B-Q3_K_M.gguf +3 -0
- Qwen2.5-Coder-32B-Q3_K_S.gguf +3 -0
- Qwen2.5-Coder-32B-Q4_0.gguf +3 -0
- Qwen2.5-Coder-32B-Q4_K_M.gguf +3 -0
- Qwen2.5-Coder-32B-Q4_K_S.gguf +3 -0
- Qwen2.5-Coder-32B-Q5_0.gguf +3 -0
- Qwen2.5-Coder-32B-Q5_K_M.gguf +3 -0
- Qwen2.5-Coder-32B-Q5_K_S.gguf +3 -0
- Qwen2.5-Coder-32B-Q6_K.gguf +3 -0
- Qwen2.5-Coder-32B-Q8_0.gguf +3 -0
- README.md +89 -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 |
+
Qwen2.5-Coder-32B-Q2_K.gguf filter=lfs diff=lfs merge=lfs -text
|
37 |
+
Qwen2.5-Coder-32B-Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text
|
38 |
+
Qwen2.5-Coder-32B-Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text
|
39 |
+
Qwen2.5-Coder-32B-Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text
|
40 |
+
Qwen2.5-Coder-32B-Q4_0.gguf filter=lfs diff=lfs merge=lfs -text
|
41 |
+
Qwen2.5-Coder-32B-Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text
|
42 |
+
Qwen2.5-Coder-32B-Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text
|
43 |
+
Qwen2.5-Coder-32B-Q5_0.gguf filter=lfs diff=lfs merge=lfs -text
|
44 |
+
Qwen2.5-Coder-32B-Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text
|
45 |
+
Qwen2.5-Coder-32B-Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text
|
46 |
+
Qwen2.5-Coder-32B-Q6_K.gguf filter=lfs diff=lfs merge=lfs -text
|
47 |
+
Qwen2.5-Coder-32B-Q8_0.gguf filter=lfs diff=lfs merge=lfs -text
|
Qwen2.5-Coder-32B-Q2_K.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:f2bb4b025e852a6c26ceb499b16068817440b0f187713ee79e181420dc7b1fc9
|
3 |
+
size 12313098784
|
Qwen2.5-Coder-32B-Q3_K_L.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:2d3cd781210f60b7f65bfbb2221abb0a2ad24121ae0fc30549620b226a0286cb
|
3 |
+
size 17247078944
|
Qwen2.5-Coder-32B-Q3_K_M.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:f4ef1046b90bf89bac34d279da7f4b063dc9b4a89cd649974f8feafc3d8c2cf4
|
3 |
+
size 15935048224
|
Qwen2.5-Coder-32B-Q3_K_S.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:120890d9d7dbe0ec42de1a1225a89121dbbff6ef4836947c0968f532d87acda5
|
3 |
+
size 14392330784
|
Qwen2.5-Coder-32B-Q4_0.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:697625c318e84d4bd8d23a60669c355454497516efc3b3897d4055d20c6448da
|
3 |
+
size 18640230944
|
Qwen2.5-Coder-32B-Q4_K_M.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:7d4f6df247da3ed59d4eb2b2544a9308b2880e5e5271e3cc7ce60e8d13d697bb
|
3 |
+
size 19851336224
|
Qwen2.5-Coder-32B-Q4_K_S.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:749ebedea0dc61efabb100d5064e6dbab5092fcd9f5c419f4acf450ec7f34115
|
3 |
+
size 18784410144
|
Qwen2.5-Coder-32B-Q5_0.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:a542637f5fed3bee6dd092d62a4da1d946c65baf17c9e0722386f31a0602d75c
|
3 |
+
size 22638254624
|
Qwen2.5-Coder-32B-Q5_K_M.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:e5cb8a3495c83e26d6fd0ed209ecd3d60b3af7cec26ba60360db264722da6bc7
|
3 |
+
size 23262157344
|
Qwen2.5-Coder-32B-Q5_K_S.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:80e75da1ceb297ba76af75f776cebb0fb98a87aad1f14c1100e2bdd00e399370
|
3 |
+
size 22638254624
|
Qwen2.5-Coder-32B-Q6_K.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:623f50d539383452796a508d6d82d603fbec4ce05c3b5f3104ea8896fde6464e
|
3 |
+
size 26886154784
|
Qwen2.5-Coder-32B-Q8_0.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:5f17652e6fa0844c405a5e8a5c673768c6cb8668e8ff86faa8ce31695105b586
|
3 |
+
size 34820885024
|
README.md
ADDED
@@ -0,0 +1,89 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
license: apache-2.0
|
3 |
+
license_link: https://huggingface.co/Qwen/Qwen2.5-Coder-32B/blob/main/LICENSE
|
4 |
+
language:
|
5 |
+
- en
|
6 |
+
base_model: Qwen/Qwen2.5-Coder-32B
|
7 |
+
pipeline_tag: text-generation
|
8 |
+
library_name: transformers
|
9 |
+
tags:
|
10 |
+
- code
|
11 |
+
- qwen
|
12 |
+
- qwen-coder
|
13 |
+
- codeqwen
|
14 |
+
- TensorBlock
|
15 |
+
- GGUF
|
16 |
+
---
|
17 |
+
|
18 |
+
<div style="width: auto; margin-left: auto; margin-right: auto">
|
19 |
+
<img src="https://i.imgur.com/jC7kdl8.jpeg" alt="TensorBlock" style="width: 100%; min-width: 400px; display: block; margin: auto;">
|
20 |
+
</div>
|
21 |
+
<div style="display: flex; justify-content: space-between; width: 100%;">
|
22 |
+
<div style="display: flex; flex-direction: column; align-items: flex-start;">
|
23 |
+
<p style="margin-top: 0.5em; margin-bottom: 0em;">
|
24 |
+
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>
|
25 |
+
</p>
|
26 |
+
</div>
|
27 |
+
</div>
|
28 |
+
|
29 |
+
## Qwen/Qwen2.5-Coder-32B - GGUF
|
30 |
+
|
31 |
+
This repo contains GGUF format model files for [Qwen/Qwen2.5-Coder-32B](https://huggingface.co/Qwen/Qwen2.5-Coder-32B).
|
32 |
+
|
33 |
+
The files were quantized using machines provided by [TensorBlock](https://tensorblock.co/), and they are compatible with llama.cpp as of [commit b4011](https://github.com/ggerganov/llama.cpp/commit/a6744e43e80f4be6398fc7733a01642c846dce1d).
|
34 |
+
|
35 |
+
<div style="text-align: left; margin: 20px 0;">
|
36 |
+
<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;">
|
37 |
+
Run them on the TensorBlock client using your local machine ↗
|
38 |
+
</a>
|
39 |
+
</div>
|
40 |
+
|
41 |
+
## Prompt template
|
42 |
+
|
43 |
+
```
|
44 |
+
<|im_start|>system
|
45 |
+
{system_prompt}<|im_end|>
|
46 |
+
<|im_start|>user
|
47 |
+
{prompt}<|im_end|>
|
48 |
+
<|im_start|>assistant
|
49 |
+
```
|
50 |
+
|
51 |
+
## Model file specification
|
52 |
+
|
53 |
+
| Filename | Quant type | File Size | Description |
|
54 |
+
| -------- | ---------- | --------- | ----------- |
|
55 |
+
| [Qwen2.5-Coder-32B-Q2_K.gguf](https://huggingface.co/tensorblock/Qwen2.5-Coder-32B-GGUF/blob/main/Qwen2.5-Coder-32B-Q2_K.gguf) | Q2_K | 12.313 GB | smallest, significant quality loss - not recommended for most purposes |
|
56 |
+
| [Qwen2.5-Coder-32B-Q3_K_S.gguf](https://huggingface.co/tensorblock/Qwen2.5-Coder-32B-GGUF/blob/main/Qwen2.5-Coder-32B-Q3_K_S.gguf) | Q3_K_S | 14.392 GB | very small, high quality loss |
|
57 |
+
| [Qwen2.5-Coder-32B-Q3_K_M.gguf](https://huggingface.co/tensorblock/Qwen2.5-Coder-32B-GGUF/blob/main/Qwen2.5-Coder-32B-Q3_K_M.gguf) | Q3_K_M | 15.935 GB | very small, high quality loss |
|
58 |
+
| [Qwen2.5-Coder-32B-Q3_K_L.gguf](https://huggingface.co/tensorblock/Qwen2.5-Coder-32B-GGUF/blob/main/Qwen2.5-Coder-32B-Q3_K_L.gguf) | Q3_K_L | 17.247 GB | small, substantial quality loss |
|
59 |
+
| [Qwen2.5-Coder-32B-Q4_0.gguf](https://huggingface.co/tensorblock/Qwen2.5-Coder-32B-GGUF/blob/main/Qwen2.5-Coder-32B-Q4_0.gguf) | Q4_0 | 18.640 GB | legacy; small, very high quality loss - prefer using Q3_K_M |
|
60 |
+
| [Qwen2.5-Coder-32B-Q4_K_S.gguf](https://huggingface.co/tensorblock/Qwen2.5-Coder-32B-GGUF/blob/main/Qwen2.5-Coder-32B-Q4_K_S.gguf) | Q4_K_S | 18.784 GB | small, greater quality loss |
|
61 |
+
| [Qwen2.5-Coder-32B-Q4_K_M.gguf](https://huggingface.co/tensorblock/Qwen2.5-Coder-32B-GGUF/blob/main/Qwen2.5-Coder-32B-Q4_K_M.gguf) | Q4_K_M | 19.851 GB | medium, balanced quality - recommended |
|
62 |
+
| [Qwen2.5-Coder-32B-Q5_0.gguf](https://huggingface.co/tensorblock/Qwen2.5-Coder-32B-GGUF/blob/main/Qwen2.5-Coder-32B-Q5_0.gguf) | Q5_0 | 22.638 GB | legacy; medium, balanced quality - prefer using Q4_K_M |
|
63 |
+
| [Qwen2.5-Coder-32B-Q5_K_S.gguf](https://huggingface.co/tensorblock/Qwen2.5-Coder-32B-GGUF/blob/main/Qwen2.5-Coder-32B-Q5_K_S.gguf) | Q5_K_S | 22.638 GB | large, low quality loss - recommended |
|
64 |
+
| [Qwen2.5-Coder-32B-Q5_K_M.gguf](https://huggingface.co/tensorblock/Qwen2.5-Coder-32B-GGUF/blob/main/Qwen2.5-Coder-32B-Q5_K_M.gguf) | Q5_K_M | 23.262 GB | large, very low quality loss - recommended |
|
65 |
+
| [Qwen2.5-Coder-32B-Q6_K.gguf](https://huggingface.co/tensorblock/Qwen2.5-Coder-32B-GGUF/blob/main/Qwen2.5-Coder-32B-Q6_K.gguf) | Q6_K | 26.886 GB | very large, extremely low quality loss |
|
66 |
+
| [Qwen2.5-Coder-32B-Q8_0.gguf](https://huggingface.co/tensorblock/Qwen2.5-Coder-32B-GGUF/blob/main/Qwen2.5-Coder-32B-Q8_0.gguf) | Q8_0 | 34.821 GB | very large, extremely low quality loss - not recommended |
|
67 |
+
|
68 |
+
|
69 |
+
## Downloading instruction
|
70 |
+
|
71 |
+
### Command line
|
72 |
+
|
73 |
+
Firstly, install Huggingface Client
|
74 |
+
|
75 |
+
```shell
|
76 |
+
pip install -U "huggingface_hub[cli]"
|
77 |
+
```
|
78 |
+
|
79 |
+
Then, downoad the individual model file the a local directory
|
80 |
+
|
81 |
+
```shell
|
82 |
+
huggingface-cli download tensorblock/Qwen2.5-Coder-32B-GGUF --include "Qwen2.5-Coder-32B-Q2_K.gguf" --local-dir MY_LOCAL_DIR
|
83 |
+
```
|
84 |
+
|
85 |
+
If you wanna download multiple model files with a pattern (e.g., `*Q4_K*gguf`), you can try:
|
86 |
+
|
87 |
+
```shell
|
88 |
+
huggingface-cli download tensorblock/Qwen2.5-Coder-32B-GGUF --local-dir MY_LOCAL_DIR --local-dir-use-symlinks False --include='*Q4_K*gguf'
|
89 |
+
```
|