Upload folder using huggingface_hub
Browse files- .gitattributes +12 -0
- Qwen2-7B-Instruct-Q2_K.gguf +3 -0
- Qwen2-7B-Instruct-Q3_K_L.gguf +3 -0
- Qwen2-7B-Instruct-Q3_K_M.gguf +3 -0
- Qwen2-7B-Instruct-Q3_K_S.gguf +3 -0
- Qwen2-7B-Instruct-Q4_0.gguf +3 -0
- Qwen2-7B-Instruct-Q4_K_M.gguf +3 -0
- Qwen2-7B-Instruct-Q4_K_S.gguf +3 -0
- Qwen2-7B-Instruct-Q5_0.gguf +3 -0
- Qwen2-7B-Instruct-Q5_K_M.gguf +3 -0
- Qwen2-7B-Instruct-Q5_K_S.gguf +3 -0
- Qwen2-7B-Instruct-Q6_K.gguf +3 -0
- Qwen2-7B-Instruct-Q8_0.gguf +3 -0
- README.md +78 -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 |
+
Qwen2-7B-Instruct-Q2_K.gguf filter=lfs diff=lfs merge=lfs -text
|
37 |
+
Qwen2-7B-Instruct-Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text
|
38 |
+
Qwen2-7B-Instruct-Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text
|
39 |
+
Qwen2-7B-Instruct-Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text
|
40 |
+
Qwen2-7B-Instruct-Q4_0.gguf filter=lfs diff=lfs merge=lfs -text
|
41 |
+
Qwen2-7B-Instruct-Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text
|
42 |
+
Qwen2-7B-Instruct-Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text
|
43 |
+
Qwen2-7B-Instruct-Q5_0.gguf filter=lfs diff=lfs merge=lfs -text
|
44 |
+
Qwen2-7B-Instruct-Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text
|
45 |
+
Qwen2-7B-Instruct-Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text
|
46 |
+
Qwen2-7B-Instruct-Q6_K.gguf filter=lfs diff=lfs merge=lfs -text
|
47 |
+
Qwen2-7B-Instruct-Q8_0.gguf filter=lfs diff=lfs merge=lfs -text
|
Qwen2-7B-Instruct-Q2_K.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:4b12c479f7d0da6dc9dcc7353c0b33144400f6d9a247fb860631e797ea38cfb1
|
3 |
+
size 3015938144
|
Qwen2-7B-Instruct-Q3_K_L.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:03555c2fc24b7411974ee1d06e5ed41e58ae2b2871b5dc1d7fb4604a3ee5bd9e
|
3 |
+
size 4088457312
|
Qwen2-7B-Instruct-Q3_K_M.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:e9ee9f493d2b0e2a009cd1e28bb6b37f36deba9b77e660dcb0fbab588928b78c
|
3 |
+
size 3808389216
|
Qwen2-7B-Instruct-Q3_K_S.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:aa767300284f187d3c459f3d99588012c89f097d4e96783e2ca3c958326fb0d7
|
3 |
+
size 3492366432
|
Qwen2-7B-Instruct-Q4_0.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:f77a9c17211498c1af4fb55bcdb3a6efbc1f91a69280189b9e0c821fc0be909b
|
3 |
+
size 4431388768
|
Qwen2-7B-Instruct-Q4_K_M.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:8f6f820efdc73b3b86f6078706f7963412ae199ea231351bc5a1611b1c520db3
|
3 |
+
size 4683071584
|
Qwen2-7B-Instruct-Q4_K_S.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:dc574d94e48a174487ff4c7c8b3bc25c466b8295bf7cb5484ca2ce8b66ac198f
|
3 |
+
size 4457767008
|
Qwen2-7B-Instruct-Q5_0.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:21768e601ca5683ed368adf22797ddd14f3555c06456fbc8310124767857f8df
|
3 |
+
size 5315174496
|
Qwen2-7B-Instruct-Q5_K_M.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:3532e9839cc8773fc638397243e092146c8e5f755c18118c612c9c1068e37d5d
|
3 |
+
size 5444829280
|
Qwen2-7B-Instruct-Q5_K_S.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:5141daab182609235490d0f4b8e70536b692d5504ecb25c069963c3b09bfa973
|
3 |
+
size 5315174496
|
Qwen2-7B-Instruct-Q6_K.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:3dd25810dab35eda04979f32894e5e34aefeb5e5e93378a4adc15d7d515818ea
|
3 |
+
size 6254196832
|
Qwen2-7B-Instruct-Q8_0.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:13f84292290712722e1651acf94b597b461481bdefef732caa2b79cc0391d617
|
3 |
+
size 8098523232
|
README.md
ADDED
@@ -0,0 +1,78 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
license: apache-2.0
|
3 |
+
language:
|
4 |
+
- en
|
5 |
+
pipeline_tag: text-generation
|
6 |
+
tags:
|
7 |
+
- chat
|
8 |
+
- TensorBlock
|
9 |
+
- GGUF
|
10 |
+
base_model: Qwen/Qwen2-7B-Instruct
|
11 |
+
---
|
12 |
+
|
13 |
+
<div style="width: auto; margin-left: auto; margin-right: auto">
|
14 |
+
<img src="https://i.imgur.com/jC7kdl8.jpeg" alt="TensorBlock" style="width: 100%; min-width: 400px; display: block; margin: auto;">
|
15 |
+
</div>
|
16 |
+
<div style="display: flex; justify-content: space-between; width: 100%;">
|
17 |
+
<div style="display: flex; flex-direction: column; align-items: flex-start;">
|
18 |
+
<p style="margin-top: 0.5em; margin-bottom: 0em;">
|
19 |
+
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>
|
20 |
+
</p>
|
21 |
+
</div>
|
22 |
+
</div>
|
23 |
+
|
24 |
+
## Qwen/Qwen2-7B-Instruct - GGUF
|
25 |
+
|
26 |
+
This repo contains GGUF format model files for [Qwen/Qwen2-7B-Instruct](https://huggingface.co/Qwen/Qwen2-7B-Instruct).
|
27 |
+
|
28 |
+
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).
|
29 |
+
|
30 |
+
## Prompt template
|
31 |
+
|
32 |
+
```
|
33 |
+
<|im_start|>system
|
34 |
+
{system_prompt}<|im_end|>
|
35 |
+
<|im_start|>user
|
36 |
+
{prompt}<|im_end|>
|
37 |
+
<|im_start|>assistant
|
38 |
+
```
|
39 |
+
|
40 |
+
## Model file specification
|
41 |
+
|
42 |
+
| Filename | Quant type | File Size | Description |
|
43 |
+
| -------- | ---------- | --------- | ----------- |
|
44 |
+
| [Qwen2-7B-Instruct-Q2_K.gguf](https://huggingface.co/tensorblock/Qwen2-7B-Instruct-GGUF/tree/main/Qwen2-7B-Instruct-Q2_K.gguf) | Q2_K | 2.809 GB | smallest, significant quality loss - not recommended for most purposes |
|
45 |
+
| [Qwen2-7B-Instruct-Q3_K_S.gguf](https://huggingface.co/tensorblock/Qwen2-7B-Instruct-GGUF/tree/main/Qwen2-7B-Instruct-Q3_K_S.gguf) | Q3_K_S | 3.253 GB | very small, high quality loss |
|
46 |
+
| [Qwen2-7B-Instruct-Q3_K_M.gguf](https://huggingface.co/tensorblock/Qwen2-7B-Instruct-GGUF/tree/main/Qwen2-7B-Instruct-Q3_K_M.gguf) | Q3_K_M | 3.547 GB | very small, high quality loss |
|
47 |
+
| [Qwen2-7B-Instruct-Q3_K_L.gguf](https://huggingface.co/tensorblock/Qwen2-7B-Instruct-GGUF/tree/main/Qwen2-7B-Instruct-Q3_K_L.gguf) | Q3_K_L | 3.808 GB | small, substantial quality loss |
|
48 |
+
| [Qwen2-7B-Instruct-Q4_0.gguf](https://huggingface.co/tensorblock/Qwen2-7B-Instruct-GGUF/tree/main/Qwen2-7B-Instruct-Q4_0.gguf) | Q4_0 | 4.127 GB | legacy; small, very high quality loss - prefer using Q3_K_M |
|
49 |
+
| [Qwen2-7B-Instruct-Q4_K_S.gguf](https://huggingface.co/tensorblock/Qwen2-7B-Instruct-GGUF/tree/main/Qwen2-7B-Instruct-Q4_K_S.gguf) | Q4_K_S | 4.152 GB | small, greater quality loss |
|
50 |
+
| [Qwen2-7B-Instruct-Q4_K_M.gguf](https://huggingface.co/tensorblock/Qwen2-7B-Instruct-GGUF/tree/main/Qwen2-7B-Instruct-Q4_K_M.gguf) | Q4_K_M | 4.361 GB | medium, balanced quality - recommended |
|
51 |
+
| [Qwen2-7B-Instruct-Q5_0.gguf](https://huggingface.co/tensorblock/Qwen2-7B-Instruct-GGUF/tree/main/Qwen2-7B-Instruct-Q5_0.gguf) | Q5_0 | 4.950 GB | legacy; medium, balanced quality - prefer using Q4_K_M |
|
52 |
+
| [Qwen2-7B-Instruct-Q5_K_S.gguf](https://huggingface.co/tensorblock/Qwen2-7B-Instruct-GGUF/tree/main/Qwen2-7B-Instruct-Q5_K_S.gguf) | Q5_K_S | 4.950 GB | large, low quality loss - recommended |
|
53 |
+
| [Qwen2-7B-Instruct-Q5_K_M.gguf](https://huggingface.co/tensorblock/Qwen2-7B-Instruct-GGUF/tree/main/Qwen2-7B-Instruct-Q5_K_M.gguf) | Q5_K_M | 5.071 GB | large, very low quality loss - recommended |
|
54 |
+
| [Qwen2-7B-Instruct-Q6_K.gguf](https://huggingface.co/tensorblock/Qwen2-7B-Instruct-GGUF/tree/main/Qwen2-7B-Instruct-Q6_K.gguf) | Q6_K | 5.825 GB | very large, extremely low quality loss |
|
55 |
+
| [Qwen2-7B-Instruct-Q8_0.gguf](https://huggingface.co/tensorblock/Qwen2-7B-Instruct-GGUF/tree/main/Qwen2-7B-Instruct-Q8_0.gguf) | Q8_0 | 7.542 GB | very large, extremely low quality loss - not recommended |
|
56 |
+
|
57 |
+
|
58 |
+
## Downloading instruction
|
59 |
+
|
60 |
+
### Command line
|
61 |
+
|
62 |
+
Firstly, install Huggingface Client
|
63 |
+
|
64 |
+
```shell
|
65 |
+
pip install -U "huggingface_hub[cli]"
|
66 |
+
```
|
67 |
+
|
68 |
+
Then, downoad the individual model file the a local directory
|
69 |
+
|
70 |
+
```shell
|
71 |
+
huggingface-cli download tensorblock/Qwen2-7B-Instruct-GGUF --include "Qwen2-7B-Instruct-Q2_K.gguf" --local-dir MY_LOCAL_DIR
|
72 |
+
```
|
73 |
+
|
74 |
+
If you wanna download multiple model files with a pattern (e.g., `*Q4_K*gguf`), you can try:
|
75 |
+
|
76 |
+
```shell
|
77 |
+
huggingface-cli download tensorblock/Qwen2-7B-Instruct-GGUF --local-dir MY_LOCAL_DIR --local-dir-use-symlinks False --include='*Q4_K*gguf'
|
78 |
+
```
|