Upload folder using huggingface_hub
Browse files- .gitattributes +12 -0
- Qwen2.5-7B-Q2_K.gguf +3 -0
- Qwen2.5-7B-Q3_K_L.gguf +3 -0
- Qwen2.5-7B-Q3_K_M.gguf +3 -0
- Qwen2.5-7B-Q3_K_S.gguf +3 -0
- Qwen2.5-7B-Q4_0.gguf +3 -0
- Qwen2.5-7B-Q4_K_M.gguf +3 -0
- Qwen2.5-7B-Q4_K_S.gguf +3 -0
- Qwen2.5-7B-Q5_0.gguf +3 -0
- Qwen2.5-7B-Q5_K_M.gguf +3 -0
- Qwen2.5-7B-Q5_K_S.gguf +3 -0
- Qwen2.5-7B-Q6_K.gguf +3 -0
- Qwen2.5-7B-Q8_0.gguf +3 -0
- README.md +79 -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 |
+
Qwen2.5-7B-Q2_K.gguf filter=lfs diff=lfs merge=lfs -text
|
37 |
+
Qwen2.5-7B-Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text
|
38 |
+
Qwen2.5-7B-Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text
|
39 |
+
Qwen2.5-7B-Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text
|
40 |
+
Qwen2.5-7B-Q4_0.gguf filter=lfs diff=lfs merge=lfs -text
|
41 |
+
Qwen2.5-7B-Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text
|
42 |
+
Qwen2.5-7B-Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text
|
43 |
+
Qwen2.5-7B-Q5_0.gguf filter=lfs diff=lfs merge=lfs -text
|
44 |
+
Qwen2.5-7B-Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text
|
45 |
+
Qwen2.5-7B-Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text
|
46 |
+
Qwen2.5-7B-Q6_K.gguf filter=lfs diff=lfs merge=lfs -text
|
47 |
+
Qwen2.5-7B-Q8_0.gguf filter=lfs diff=lfs merge=lfs -text
|
Qwen2.5-7B-Q2_K.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:b299f1e255836a005354a515056a2165069e26d2f507135a6ec0eb47632ae2d5
|
3 |
+
size 3015940128
|
Qwen2.5-7B-Q3_K_L.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:5fcd3a6bbc4c1ee5417c6d07e328a59e10fff2fc0b6ac37d350f2457f8dc4678
|
3 |
+
size 4088459296
|
Qwen2.5-7B-Q3_K_M.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:b36d5d1e388e90cf9eea71e64b4b45fa53fdabb150752c04e1240812370eff01
|
3 |
+
size 3808391200
|
Qwen2.5-7B-Q3_K_S.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:0279be732def84bdcb9e5c688422ce8ac1831a69f910f644cc47efd104ab4f29
|
3 |
+
size 3492368416
|
Qwen2.5-7B-Q4_0.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:dc6f8f4a46138765383c2515f4a02d9c97564cb658c3d9eae0b582bb301e4b66
|
3 |
+
size 4431390752
|
Qwen2.5-7B-Q4_K_M.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:456373ad5d036841b3b68004dd49dbb411fd4ec0efb35b71b9b2bc5e03b80a45
|
3 |
+
size 4683073568
|
Qwen2.5-7B-Q4_K_S.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:cde35bfc35ce0919de160df4024bfefeeec57f33119073c4f8891eac3cb0ce46
|
3 |
+
size 4457768992
|
Qwen2.5-7B-Q5_0.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:0b1f4c40b79e83ed4523b45791ec665b50e61c9866f24ce5d7027e022a726ea0
|
3 |
+
size 5315176480
|
Qwen2.5-7B-Q5_K_M.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:25696e18675a395784cf892824a87ad9cc9d8e1d79a8f449b6591b6387a12368
|
3 |
+
size 5444831264
|
Qwen2.5-7B-Q5_K_S.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:7019e7f36249ec0bea60ceedbb20703d897b2e8ebb3ae85ee2fa8dce85bd7b9a
|
3 |
+
size 5315176480
|
Qwen2.5-7B-Q6_K.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:e56697a9fa8c8bd4435286460210e2d8bde08f85f39c1244f6e1791e1025343b
|
3 |
+
size 6254198816
|
Qwen2.5-7B-Q8_0.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:08aaddaa8e067a78a8cfd73da5f56b756489c64f255efd45f182802d5d890b65
|
3 |
+
size 8098525216
|
README.md
ADDED
@@ -0,0 +1,79 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
license: apache-2.0
|
3 |
+
license_link: https://huggingface.co/Qwen/Qwen2.5-7B/blob/main/LICENSE
|
4 |
+
language:
|
5 |
+
- en
|
6 |
+
pipeline_tag: text-generation
|
7 |
+
library_name: transformers
|
8 |
+
tags:
|
9 |
+
- TensorBlock
|
10 |
+
- GGUF
|
11 |
+
base_model: Qwen/Qwen2.5-7B
|
12 |
+
---
|
13 |
+
|
14 |
+
<div style="width: auto; margin-left: auto; margin-right: auto">
|
15 |
+
<img src="https://i.imgur.com/jC7kdl8.jpeg" alt="TensorBlock" style="width: 100%; min-width: 400px; display: block; margin: auto;">
|
16 |
+
</div>
|
17 |
+
<div style="display: flex; justify-content: space-between; width: 100%;">
|
18 |
+
<div style="display: flex; flex-direction: column; align-items: flex-start;">
|
19 |
+
<p style="margin-top: 0.5em; margin-bottom: 0em;">
|
20 |
+
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>
|
21 |
+
</p>
|
22 |
+
</div>
|
23 |
+
</div>
|
24 |
+
|
25 |
+
## Qwen/Qwen2.5-7B - GGUF
|
26 |
+
|
27 |
+
This repo contains GGUF format model files for [Qwen/Qwen2.5-7B](https://huggingface.co/Qwen/Qwen2.5-7B).
|
28 |
+
|
29 |
+
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).
|
30 |
+
|
31 |
+
## Prompt template
|
32 |
+
|
33 |
+
```
|
34 |
+
<|im_start|>system
|
35 |
+
{system_prompt}<|im_end|>
|
36 |
+
<|im_start|>user
|
37 |
+
{prompt}<|im_end|>
|
38 |
+
<|im_start|>assistant
|
39 |
+
```
|
40 |
+
|
41 |
+
## Model file specification
|
42 |
+
|
43 |
+
| Filename | Quant type | File Size | Description |
|
44 |
+
| -------- | ---------- | --------- | ----------- |
|
45 |
+
| [Qwen2.5-7B-Q2_K.gguf](https://huggingface.co/tensorblock/Qwen2.5-7B-GGUF/tree/main/Qwen2.5-7B-Q2_K.gguf) | Q2_K | 2.809 GB | smallest, significant quality loss - not recommended for most purposes |
|
46 |
+
| [Qwen2.5-7B-Q3_K_S.gguf](https://huggingface.co/tensorblock/Qwen2.5-7B-GGUF/tree/main/Qwen2.5-7B-Q3_K_S.gguf) | Q3_K_S | 3.253 GB | very small, high quality loss |
|
47 |
+
| [Qwen2.5-7B-Q3_K_M.gguf](https://huggingface.co/tensorblock/Qwen2.5-7B-GGUF/tree/main/Qwen2.5-7B-Q3_K_M.gguf) | Q3_K_M | 3.547 GB | very small, high quality loss |
|
48 |
+
| [Qwen2.5-7B-Q3_K_L.gguf](https://huggingface.co/tensorblock/Qwen2.5-7B-GGUF/tree/main/Qwen2.5-7B-Q3_K_L.gguf) | Q3_K_L | 3.808 GB | small, substantial quality loss |
|
49 |
+
| [Qwen2.5-7B-Q4_0.gguf](https://huggingface.co/tensorblock/Qwen2.5-7B-GGUF/tree/main/Qwen2.5-7B-Q4_0.gguf) | Q4_0 | 4.127 GB | legacy; small, very high quality loss - prefer using Q3_K_M |
|
50 |
+
| [Qwen2.5-7B-Q4_K_S.gguf](https://huggingface.co/tensorblock/Qwen2.5-7B-GGUF/tree/main/Qwen2.5-7B-Q4_K_S.gguf) | Q4_K_S | 4.152 GB | small, greater quality loss |
|
51 |
+
| [Qwen2.5-7B-Q4_K_M.gguf](https://huggingface.co/tensorblock/Qwen2.5-7B-GGUF/tree/main/Qwen2.5-7B-Q4_K_M.gguf) | Q4_K_M | 4.361 GB | medium, balanced quality - recommended |
|
52 |
+
| [Qwen2.5-7B-Q5_0.gguf](https://huggingface.co/tensorblock/Qwen2.5-7B-GGUF/tree/main/Qwen2.5-7B-Q5_0.gguf) | Q5_0 | 4.950 GB | legacy; medium, balanced quality - prefer using Q4_K_M |
|
53 |
+
| [Qwen2.5-7B-Q5_K_S.gguf](https://huggingface.co/tensorblock/Qwen2.5-7B-GGUF/tree/main/Qwen2.5-7B-Q5_K_S.gguf) | Q5_K_S | 4.950 GB | large, low quality loss - recommended |
|
54 |
+
| [Qwen2.5-7B-Q5_K_M.gguf](https://huggingface.co/tensorblock/Qwen2.5-7B-GGUF/tree/main/Qwen2.5-7B-Q5_K_M.gguf) | Q5_K_M | 5.071 GB | large, very low quality loss - recommended |
|
55 |
+
| [Qwen2.5-7B-Q6_K.gguf](https://huggingface.co/tensorblock/Qwen2.5-7B-GGUF/tree/main/Qwen2.5-7B-Q6_K.gguf) | Q6_K | 5.825 GB | very large, extremely low quality loss |
|
56 |
+
| [Qwen2.5-7B-Q8_0.gguf](https://huggingface.co/tensorblock/Qwen2.5-7B-GGUF/tree/main/Qwen2.5-7B-Q8_0.gguf) | Q8_0 | 7.542 GB | very large, extremely low quality loss - not recommended |
|
57 |
+
|
58 |
+
|
59 |
+
## Downloading instruction
|
60 |
+
|
61 |
+
### Command line
|
62 |
+
|
63 |
+
Firstly, install Huggingface Client
|
64 |
+
|
65 |
+
```shell
|
66 |
+
pip install -U "huggingface_hub[cli]"
|
67 |
+
```
|
68 |
+
|
69 |
+
Then, downoad the individual model file the a local directory
|
70 |
+
|
71 |
+
```shell
|
72 |
+
huggingface-cli download tensorblock/Qwen2.5-7B-GGUF --include "Qwen2.5-7B-Q2_K.gguf" --local-dir MY_LOCAL_DIR
|
73 |
+
```
|
74 |
+
|
75 |
+
If you wanna download multiple model files with a pattern (e.g., `*Q4_K*gguf`), you can try:
|
76 |
+
|
77 |
+
```shell
|
78 |
+
huggingface-cli download tensorblock/Qwen2.5-7B-GGUF --local-dir MY_LOCAL_DIR --local-dir-use-symlinks False --include='*Q4_K*gguf'
|
79 |
+
```
|