Upload folder using huggingface_hub
Browse files- .gitattributes +12 -0
- Qwen2-1.5B-Q2_K.gguf +3 -0
- Qwen2-1.5B-Q3_K_L.gguf +3 -0
- Qwen2-1.5B-Q3_K_M.gguf +3 -0
- Qwen2-1.5B-Q3_K_S.gguf +3 -0
- Qwen2-1.5B-Q4_0.gguf +3 -0
- Qwen2-1.5B-Q4_K_M.gguf +3 -0
- Qwen2-1.5B-Q4_K_S.gguf +3 -0
- Qwen2-1.5B-Q5_0.gguf +3 -0
- Qwen2-1.5B-Q5_K_M.gguf +3 -0
- Qwen2-1.5B-Q5_K_S.gguf +3 -0
- Qwen2-1.5B-Q6_K.gguf +3 -0
- Qwen2-1.5B-Q8_0.gguf +3 -0
- README.md +86 -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 |
+
Qwen2-1.5B-Q2_K.gguf filter=lfs diff=lfs merge=lfs -text
|
37 |
+
Qwen2-1.5B-Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text
|
38 |
+
Qwen2-1.5B-Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text
|
39 |
+
Qwen2-1.5B-Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text
|
40 |
+
Qwen2-1.5B-Q4_0.gguf filter=lfs diff=lfs merge=lfs -text
|
41 |
+
Qwen2-1.5B-Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text
|
42 |
+
Qwen2-1.5B-Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text
|
43 |
+
Qwen2-1.5B-Q5_0.gguf filter=lfs diff=lfs merge=lfs -text
|
44 |
+
Qwen2-1.5B-Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text
|
45 |
+
Qwen2-1.5B-Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text
|
46 |
+
Qwen2-1.5B-Q6_K.gguf filter=lfs diff=lfs merge=lfs -text
|
47 |
+
Qwen2-1.5B-Q8_0.gguf filter=lfs diff=lfs merge=lfs -text
|
Qwen2-1.5B-Q2_K.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:6708fea6bda87f334959f97c7bcf6fa60d327f971c763472d1503933dd0cea22
|
3 |
+
size 676302272
|
Qwen2-1.5B-Q3_K_L.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:74ee542f3bc1b7fd96e73ccd35ff9e81542c04d077bace62d745345e88692157
|
3 |
+
size 880160192
|
Qwen2-1.5B-Q3_K_M.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:32d2e9771f01b2437b779740f040d75919dc1e0c1be5f004e6bc0b6b4215ce9e
|
3 |
+
size 824176064
|
Qwen2-1.5B-Q3_K_S.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:69fe26a93f65874deeb1ed0040284696e5a9f1a5aa8ea021a1c76baae3ce1d82
|
3 |
+
size 760942016
|
Qwen2-1.5B-Q4_0.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:c135cdfbedac22c57adc4d51b2e9f0124747a1469470ada871409ae8f56060e2
|
3 |
+
size 934952384
|
Qwen2-1.5B-Q4_K_M.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:7e82c7c639357cb6606c07e70c8465e0dccc0f596adbc6e53fa25c42fa006ae8
|
3 |
+
size 986045888
|
Qwen2-1.5B-Q4_K_S.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:6450e1a31ba81d728d126f3b24532b6bd09a0700f8ff6fa3543dacbe68d348ad
|
3 |
+
size 940309952
|
Qwen2-1.5B-Q5_0.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:adb3a51440a7b22966ab68eac72e7db2c9f3004a453579008e7d38af46dfd831
|
3 |
+
size 1098726848
|
Qwen2-1.5B-Q5_K_M.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:71839ee7372410ad61881b7243ebc211dac69b01570b1591dab41edad2954f8c
|
3 |
+
size 1125047744
|
Qwen2-1.5B-Q5_K_S.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:7f882f513b6feea6eb8f93ee587253a60e000362736d6d840369b1916836b6ad
|
3 |
+
size 1098726848
|
Qwen2-1.5B-Q6_K.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:65498b0a286322b97d7a51c3f04ccbcf34e3b831fca4bc6db55c545ffb93f2f6
|
3 |
+
size 1272737216
|
Qwen2-1.5B-Q8_0.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:5b0357ec312ac0ff641d2b171942e096aa060c1e11c5ae7a068ecbbd0ce13630
|
3 |
+
size 1646570432
|
README.md
ADDED
@@ -0,0 +1,86 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
language:
|
3 |
+
- en
|
4 |
+
library_name: transformers
|
5 |
+
license: apache-2.0
|
6 |
+
tags:
|
7 |
+
- unsloth
|
8 |
+
- transformers
|
9 |
+
- qwen2
|
10 |
+
- TensorBlock
|
11 |
+
- GGUF
|
12 |
+
base_model: unsloth/Qwen2-1.5B
|
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 |
+
## unsloth/Qwen2-1.5B - GGUF
|
27 |
+
|
28 |
+
This repo contains GGUF format model files for [unsloth/Qwen2-1.5B](https://huggingface.co/unsloth/Qwen2-1.5B).
|
29 |
+
|
30 |
+
The files were quantized using machines provided by [TensorBlock](https://tensorblock.co/), and they are compatible with llama.cpp as of [commit b4242](https://github.com/ggerganov/llama.cpp/commit/a6744e43e80f4be6398fc7733a01642c846dce1d).
|
31 |
+
|
32 |
+
<div style="text-align: left; margin: 20px 0;">
|
33 |
+
<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;">
|
34 |
+
Run them on the TensorBlock client using your local machine ↗
|
35 |
+
</a>
|
36 |
+
</div>
|
37 |
+
|
38 |
+
## Prompt template
|
39 |
+
|
40 |
+
```
|
41 |
+
<|im_start|>system
|
42 |
+
{system_prompt}<|im_end|>
|
43 |
+
<|im_start|>user
|
44 |
+
{prompt}<|im_end|>
|
45 |
+
<|im_start|>assistant
|
46 |
+
```
|
47 |
+
|
48 |
+
## Model file specification
|
49 |
+
|
50 |
+
| Filename | Quant type | File Size | Description |
|
51 |
+
| -------- | ---------- | --------- | ----------- |
|
52 |
+
| [Qwen2-1.5B-Q2_K.gguf](https://huggingface.co/tensorblock/Qwen2-1.5B-GGUF/blob/main/Qwen2-1.5B-Q2_K.gguf) | Q2_K | 0.676 GB | smallest, significant quality loss - not recommended for most purposes |
|
53 |
+
| [Qwen2-1.5B-Q3_K_S.gguf](https://huggingface.co/tensorblock/Qwen2-1.5B-GGUF/blob/main/Qwen2-1.5B-Q3_K_S.gguf) | Q3_K_S | 0.761 GB | very small, high quality loss |
|
54 |
+
| [Qwen2-1.5B-Q3_K_M.gguf](https://huggingface.co/tensorblock/Qwen2-1.5B-GGUF/blob/main/Qwen2-1.5B-Q3_K_M.gguf) | Q3_K_M | 0.824 GB | very small, high quality loss |
|
55 |
+
| [Qwen2-1.5B-Q3_K_L.gguf](https://huggingface.co/tensorblock/Qwen2-1.5B-GGUF/blob/main/Qwen2-1.5B-Q3_K_L.gguf) | Q3_K_L | 0.880 GB | small, substantial quality loss |
|
56 |
+
| [Qwen2-1.5B-Q4_0.gguf](https://huggingface.co/tensorblock/Qwen2-1.5B-GGUF/blob/main/Qwen2-1.5B-Q4_0.gguf) | Q4_0 | 0.935 GB | legacy; small, very high quality loss - prefer using Q3_K_M |
|
57 |
+
| [Qwen2-1.5B-Q4_K_S.gguf](https://huggingface.co/tensorblock/Qwen2-1.5B-GGUF/blob/main/Qwen2-1.5B-Q4_K_S.gguf) | Q4_K_S | 0.940 GB | small, greater quality loss |
|
58 |
+
| [Qwen2-1.5B-Q4_K_M.gguf](https://huggingface.co/tensorblock/Qwen2-1.5B-GGUF/blob/main/Qwen2-1.5B-Q4_K_M.gguf) | Q4_K_M | 0.986 GB | medium, balanced quality - recommended |
|
59 |
+
| [Qwen2-1.5B-Q5_0.gguf](https://huggingface.co/tensorblock/Qwen2-1.5B-GGUF/blob/main/Qwen2-1.5B-Q5_0.gguf) | Q5_0 | 1.099 GB | legacy; medium, balanced quality - prefer using Q4_K_M |
|
60 |
+
| [Qwen2-1.5B-Q5_K_S.gguf](https://huggingface.co/tensorblock/Qwen2-1.5B-GGUF/blob/main/Qwen2-1.5B-Q5_K_S.gguf) | Q5_K_S | 1.099 GB | large, low quality loss - recommended |
|
61 |
+
| [Qwen2-1.5B-Q5_K_M.gguf](https://huggingface.co/tensorblock/Qwen2-1.5B-GGUF/blob/main/Qwen2-1.5B-Q5_K_M.gguf) | Q5_K_M | 1.125 GB | large, very low quality loss - recommended |
|
62 |
+
| [Qwen2-1.5B-Q6_K.gguf](https://huggingface.co/tensorblock/Qwen2-1.5B-GGUF/blob/main/Qwen2-1.5B-Q6_K.gguf) | Q6_K | 1.273 GB | very large, extremely low quality loss |
|
63 |
+
| [Qwen2-1.5B-Q8_0.gguf](https://huggingface.co/tensorblock/Qwen2-1.5B-GGUF/blob/main/Qwen2-1.5B-Q8_0.gguf) | Q8_0 | 1.647 GB | very large, extremely low quality loss - not recommended |
|
64 |
+
|
65 |
+
|
66 |
+
## Downloading instruction
|
67 |
+
|
68 |
+
### Command line
|
69 |
+
|
70 |
+
Firstly, install Huggingface Client
|
71 |
+
|
72 |
+
```shell
|
73 |
+
pip install -U "huggingface_hub[cli]"
|
74 |
+
```
|
75 |
+
|
76 |
+
Then, downoad the individual model file the a local directory
|
77 |
+
|
78 |
+
```shell
|
79 |
+
huggingface-cli download tensorblock/Qwen2-1.5B-GGUF --include "Qwen2-1.5B-Q2_K.gguf" --local-dir MY_LOCAL_DIR
|
80 |
+
```
|
81 |
+
|
82 |
+
If you wanna download multiple model files with a pattern (e.g., `*Q4_K*gguf`), you can try:
|
83 |
+
|
84 |
+
```shell
|
85 |
+
huggingface-cli download tensorblock/Qwen2-1.5B-GGUF --local-dir MY_LOCAL_DIR --local-dir-use-symlinks False --include='*Q4_K*gguf'
|
86 |
+
```
|