Upload folder using huggingface_hub
Browse files- .gitattributes +12 -0
- Qwen1.5-0.5B-Q2_K.gguf +3 -0
- Qwen1.5-0.5B-Q3_K_L.gguf +3 -0
- Qwen1.5-0.5B-Q3_K_M.gguf +3 -0
- Qwen1.5-0.5B-Q3_K_S.gguf +3 -0
- Qwen1.5-0.5B-Q4_0.gguf +3 -0
- Qwen1.5-0.5B-Q4_K_M.gguf +3 -0
- Qwen1.5-0.5B-Q4_K_S.gguf +3 -0
- Qwen1.5-0.5B-Q5_0.gguf +3 -0
- Qwen1.5-0.5B-Q5_K_M.gguf +3 -0
- Qwen1.5-0.5B-Q5_K_S.gguf +3 -0
- Qwen1.5-0.5B-Q6_K.gguf +3 -0
- Qwen1.5-0.5B-Q8_0.gguf +3 -0
- README.md +80 -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 |
+
Qwen1.5-0.5B-Q2_K.gguf filter=lfs diff=lfs merge=lfs -text
|
37 |
+
Qwen1.5-0.5B-Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text
|
38 |
+
Qwen1.5-0.5B-Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text
|
39 |
+
Qwen1.5-0.5B-Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text
|
40 |
+
Qwen1.5-0.5B-Q4_0.gguf filter=lfs diff=lfs merge=lfs -text
|
41 |
+
Qwen1.5-0.5B-Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text
|
42 |
+
Qwen1.5-0.5B-Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text
|
43 |
+
Qwen1.5-0.5B-Q5_0.gguf filter=lfs diff=lfs merge=lfs -text
|
44 |
+
Qwen1.5-0.5B-Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text
|
45 |
+
Qwen1.5-0.5B-Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text
|
46 |
+
Qwen1.5-0.5B-Q6_K.gguf filter=lfs diff=lfs merge=lfs -text
|
47 |
+
Qwen1.5-0.5B-Q8_0.gguf filter=lfs diff=lfs merge=lfs -text
|
Qwen1.5-0.5B-Q2_K.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:61853bccf6d47883dc90ca0b3a8ecb524d3325b4a0fb8b9fe41260244e22a3a0
|
3 |
+
size 298413472
|
Qwen1.5-0.5B-Q3_K_L.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:2d03276b7bdb5b36413fd886504ac62df83e278136b3e86050af875a8e6d9bd3
|
3 |
+
size 364202400
|
Qwen1.5-0.5B-Q3_K_M.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:5f65b36dd3a19a15078aeead5449e91d44fa186be093bc96da2a53e9e4c17b8a
|
3 |
+
size 349882784
|
Qwen1.5-0.5B-Q3_K_S.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:2c93a25dfb4274795043c0fcc336fe75e9679ab3c6a310fb47e5d532100f41e0
|
3 |
+
size 333384096
|
Qwen1.5-0.5B-Q4_0.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:79260279f6d4ccc1791ae8aad401b56fb00197d1ed8314ec95307799ae0d4916
|
3 |
+
size 394991008
|
Qwen1.5-0.5B-Q4_K_M.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:93d83feaf48400a58b8cc5903baa8f081335de366e808314975d5489f2bd43b8
|
3 |
+
size 407156128
|
Qwen1.5-0.5B-Q4_K_S.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:6a31c27de889a446b2c2d0a936a870177f60014595e4b0ee1f5c38495402b757
|
3 |
+
size 396596640
|
Qwen1.5-0.5B-Q5_0.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:5e3b240b7800f5f0f0674a9a9da15931048d9d626f208b60fadbe14dafbb3e6b
|
3 |
+
size 452973984
|
Qwen1.5-0.5B-Q5_K_M.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:b93470c317f204a29a0970d475c4c49b2824e2ddec80697d9c6a9b24e40bc4ad
|
3 |
+
size 459240864
|
Qwen1.5-0.5B-Q5_K_S.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:7a2f07ebac643d601614310ef5ad379dcb7a8eca18a18c630f2c3b0e661ea82a
|
3 |
+
size 452973984
|
Qwen1.5-0.5B-Q6_K.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:ab98345a460afe83d0202bdaa3fe7ca97d3b4c8694ed334ece4b74bd6c86e07f
|
3 |
+
size 514580896
|
Qwen1.5-0.5B-Q8_0.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:32fd11da4b8b413018bc28e39ed69e7d0320905597f5a3b2dd1c3ff300ecffa8
|
3 |
+
size 664603040
|
README.md
ADDED
@@ -0,0 +1,80 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
license: other
|
3 |
+
license_name: tongyi-qianwen-research
|
4 |
+
license_link: https://huggingface.co/Qwen/Qwen1.5-0.5B/blob/main/LICENSE
|
5 |
+
language:
|
6 |
+
- en
|
7 |
+
pipeline_tag: text-generation
|
8 |
+
tags:
|
9 |
+
- pretrained
|
10 |
+
- TensorBlock
|
11 |
+
- GGUF
|
12 |
+
base_model: Qwen/Qwen1.5-0.5B
|
13 |
+
---
|
14 |
+
|
15 |
+
<div style="width: auto; margin-left: auto; margin-right: auto">
|
16 |
+
<img src="https://i.imgur.com/jC7kdl8.jpeg" alt="TensorBlock" style="width: 100%; min-width: 400px; display: block; margin: auto;">
|
17 |
+
</div>
|
18 |
+
<div style="display: flex; justify-content: space-between; width: 100%;">
|
19 |
+
<div style="display: flex; flex-direction: column; align-items: flex-start;">
|
20 |
+
<p style="margin-top: 0.5em; margin-bottom: 0em;">
|
21 |
+
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>
|
22 |
+
</p>
|
23 |
+
</div>
|
24 |
+
</div>
|
25 |
+
|
26 |
+
## Qwen/Qwen1.5-0.5B - GGUF
|
27 |
+
|
28 |
+
This repo contains GGUF format model files for [Qwen/Qwen1.5-0.5B](https://huggingface.co/Qwen/Qwen1.5-0.5B).
|
29 |
+
|
30 |
+
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).
|
31 |
+
|
32 |
+
## Prompt template
|
33 |
+
|
34 |
+
```
|
35 |
+
<|im_start|>system
|
36 |
+
{system_prompt}<|im_end|>
|
37 |
+
<|im_start|>user
|
38 |
+
{prompt}<|im_end|>
|
39 |
+
<|im_start|>assistant
|
40 |
+
```
|
41 |
+
|
42 |
+
## Model file specification
|
43 |
+
|
44 |
+
| Filename | Quant type | File Size | Description |
|
45 |
+
| -------- | ---------- | --------- | ----------- |
|
46 |
+
| [Qwen1.5-0.5B-Q2_K.gguf](https://huggingface.co/tensorblock/Qwen1.5-0.5B-GGUF/tree/main/Qwen1.5-0.5B-Q2_K.gguf) | Q2_K | 0.278 GB | smallest, significant quality loss - not recommended for most purposes |
|
47 |
+
| [Qwen1.5-0.5B-Q3_K_S.gguf](https://huggingface.co/tensorblock/Qwen1.5-0.5B-GGUF/tree/main/Qwen1.5-0.5B-Q3_K_S.gguf) | Q3_K_S | 0.310 GB | very small, high quality loss |
|
48 |
+
| [Qwen1.5-0.5B-Q3_K_M.gguf](https://huggingface.co/tensorblock/Qwen1.5-0.5B-GGUF/tree/main/Qwen1.5-0.5B-Q3_K_M.gguf) | Q3_K_M | 0.326 GB | very small, high quality loss |
|
49 |
+
| [Qwen1.5-0.5B-Q3_K_L.gguf](https://huggingface.co/tensorblock/Qwen1.5-0.5B-GGUF/tree/main/Qwen1.5-0.5B-Q3_K_L.gguf) | Q3_K_L | 0.339 GB | small, substantial quality loss |
|
50 |
+
| [Qwen1.5-0.5B-Q4_0.gguf](https://huggingface.co/tensorblock/Qwen1.5-0.5B-GGUF/tree/main/Qwen1.5-0.5B-Q4_0.gguf) | Q4_0 | 0.368 GB | legacy; small, very high quality loss - prefer using Q3_K_M |
|
51 |
+
| [Qwen1.5-0.5B-Q4_K_S.gguf](https://huggingface.co/tensorblock/Qwen1.5-0.5B-GGUF/tree/main/Qwen1.5-0.5B-Q4_K_S.gguf) | Q4_K_S | 0.369 GB | small, greater quality loss |
|
52 |
+
| [Qwen1.5-0.5B-Q4_K_M.gguf](https://huggingface.co/tensorblock/Qwen1.5-0.5B-GGUF/tree/main/Qwen1.5-0.5B-Q4_K_M.gguf) | Q4_K_M | 0.379 GB | medium, balanced quality - recommended |
|
53 |
+
| [Qwen1.5-0.5B-Q5_0.gguf](https://huggingface.co/tensorblock/Qwen1.5-0.5B-GGUF/tree/main/Qwen1.5-0.5B-Q5_0.gguf) | Q5_0 | 0.422 GB | legacy; medium, balanced quality - prefer using Q4_K_M |
|
54 |
+
| [Qwen1.5-0.5B-Q5_K_S.gguf](https://huggingface.co/tensorblock/Qwen1.5-0.5B-GGUF/tree/main/Qwen1.5-0.5B-Q5_K_S.gguf) | Q5_K_S | 0.422 GB | large, low quality loss - recommended |
|
55 |
+
| [Qwen1.5-0.5B-Q5_K_M.gguf](https://huggingface.co/tensorblock/Qwen1.5-0.5B-GGUF/tree/main/Qwen1.5-0.5B-Q5_K_M.gguf) | Q5_K_M | 0.428 GB | large, very low quality loss - recommended |
|
56 |
+
| [Qwen1.5-0.5B-Q6_K.gguf](https://huggingface.co/tensorblock/Qwen1.5-0.5B-GGUF/tree/main/Qwen1.5-0.5B-Q6_K.gguf) | Q6_K | 0.479 GB | very large, extremely low quality loss |
|
57 |
+
| [Qwen1.5-0.5B-Q8_0.gguf](https://huggingface.co/tensorblock/Qwen1.5-0.5B-GGUF/tree/main/Qwen1.5-0.5B-Q8_0.gguf) | Q8_0 | 0.619 GB | very large, extremely low quality loss - not recommended |
|
58 |
+
|
59 |
+
|
60 |
+
## Downloading instruction
|
61 |
+
|
62 |
+
### Command line
|
63 |
+
|
64 |
+
Firstly, install Huggingface Client
|
65 |
+
|
66 |
+
```shell
|
67 |
+
pip install -U "huggingface_hub[cli]"
|
68 |
+
```
|
69 |
+
|
70 |
+
Then, downoad the individual model file the a local directory
|
71 |
+
|
72 |
+
```shell
|
73 |
+
huggingface-cli download tensorblock/Qwen1.5-0.5B-GGUF --include "Qwen1.5-0.5B-Q2_K.gguf" --local-dir MY_LOCAL_DIR
|
74 |
+
```
|
75 |
+
|
76 |
+
If you wanna download multiple model files with a pattern (e.g., `*Q4_K*gguf`), you can try:
|
77 |
+
|
78 |
+
```shell
|
79 |
+
huggingface-cli download tensorblock/Qwen1.5-0.5B-GGUF --local-dir MY_LOCAL_DIR --local-dir-use-symlinks False --include='*Q4_K*gguf'
|
80 |
+
```
|