Upload folder using huggingface_hub
Browse files- .gitattributes +12 -0
- Qwen2-7B-Q2_K.gguf +3 -0
- Qwen2-7B-Q3_K_L.gguf +3 -0
- Qwen2-7B-Q3_K_M.gguf +3 -0
- Qwen2-7B-Q3_K_S.gguf +3 -0
- Qwen2-7B-Q4_0.gguf +3 -0
- Qwen2-7B-Q4_K_M.gguf +3 -0
- Qwen2-7B-Q4_K_S.gguf +3 -0
- Qwen2-7B-Q5_0.gguf +3 -0
- Qwen2-7B-Q5_K_M.gguf +3 -0
- Qwen2-7B-Q5_K_S.gguf +3 -0
- Qwen2-7B-Q6_K.gguf +3 -0
- Qwen2-7B-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-Q2_K.gguf filter=lfs diff=lfs merge=lfs -text
|
37 |
+
Qwen2-7B-Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text
|
38 |
+
Qwen2-7B-Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text
|
39 |
+
Qwen2-7B-Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text
|
40 |
+
Qwen2-7B-Q4_0.gguf filter=lfs diff=lfs merge=lfs -text
|
41 |
+
Qwen2-7B-Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text
|
42 |
+
Qwen2-7B-Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text
|
43 |
+
Qwen2-7B-Q5_0.gguf filter=lfs diff=lfs merge=lfs -text
|
44 |
+
Qwen2-7B-Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text
|
45 |
+
Qwen2-7B-Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text
|
46 |
+
Qwen2-7B-Q6_K.gguf filter=lfs diff=lfs merge=lfs -text
|
47 |
+
Qwen2-7B-Q8_0.gguf filter=lfs diff=lfs merge=lfs -text
|
Qwen2-7B-Q2_K.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:99a5981c6de2d187a9188eab0c1d516b6b9b3613215791626044b07522231e52
|
3 |
+
size 3015937856
|
Qwen2-7B-Q3_K_L.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:5ffa85015e89a8f5490dee69f6cc78e60cd0bd08b36c752171ade1484c18433a
|
3 |
+
size 4088457024
|
Qwen2-7B-Q3_K_M.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:4cc60016a94e854a748868741901ccbd2b338ded4aa89626f98809c98c0393d8
|
3 |
+
size 3808388928
|
Qwen2-7B-Q3_K_S.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:9ee0da2991c837373d56d6a7abbdc8765e3338ebf7f30d3f8960bd388ff3daba
|
3 |
+
size 3492366144
|
Qwen2-7B-Q4_0.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:b48bab4842b14c58027d9816a392840c0932865c0c46b78222dbbdde82240ec9
|
3 |
+
size 4431388480
|
Qwen2-7B-Q4_K_M.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:5f7cf3a665cc6ef6339d0fe63e5298f5e9af8d17df07b696e26ccaf81466f915
|
3 |
+
size 4683071296
|
Qwen2-7B-Q4_K_S.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:5d438666b69735a898bc514b4be9b1134f2d6454ef721e2d22fd33706f34ef8e
|
3 |
+
size 4457766720
|
Qwen2-7B-Q5_0.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:41a00062c5b74eba612c3264bb5ec0205cea27673321b6eb0e3a7f621952cc1d
|
3 |
+
size 5315174208
|
Qwen2-7B-Q5_K_M.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:6a8da5c15721e7ac29c1b9a8775ac8bba2ef0d0f62b64ef44ee13c44852bde09
|
3 |
+
size 5444828992
|
Qwen2-7B-Q5_K_S.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:631886e8f69d2f3145b641b5da686ee7dfb4d26390a2fdcdd95667377a3d0f2a
|
3 |
+
size 5315174208
|
Qwen2-7B-Q6_K.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:0c76beb42010fe5a8e9ac442eb63c934b87d1e527accc0812138a070776eff74
|
3 |
+
size 6254196544
|
Qwen2-7B-Q8_0.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:31407d662e8863cf4c0c890a241ddc5117d40cd057b48a80146f3ed05014f38f
|
3 |
+
size 8098522944
|
README.md
ADDED
@@ -0,0 +1,78 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
language:
|
3 |
+
- en
|
4 |
+
pipeline_tag: text-generation
|
5 |
+
tags:
|
6 |
+
- pretrained
|
7 |
+
- TensorBlock
|
8 |
+
- GGUF
|
9 |
+
license: apache-2.0
|
10 |
+
base_model: Qwen/Qwen2-7B
|
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 - GGUF
|
25 |
+
|
26 |
+
This repo contains GGUF format model files for [Qwen/Qwen2-7B](https://huggingface.co/Qwen/Qwen2-7B).
|
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-Q2_K.gguf](https://huggingface.co/tensorblock/Qwen2-7B-GGUF/tree/main/Qwen2-7B-Q2_K.gguf) | Q2_K | 2.809 GB | smallest, significant quality loss - not recommended for most purposes |
|
45 |
+
| [Qwen2-7B-Q3_K_S.gguf](https://huggingface.co/tensorblock/Qwen2-7B-GGUF/tree/main/Qwen2-7B-Q3_K_S.gguf) | Q3_K_S | 3.253 GB | very small, high quality loss |
|
46 |
+
| [Qwen2-7B-Q3_K_M.gguf](https://huggingface.co/tensorblock/Qwen2-7B-GGUF/tree/main/Qwen2-7B-Q3_K_M.gguf) | Q3_K_M | 3.547 GB | very small, high quality loss |
|
47 |
+
| [Qwen2-7B-Q3_K_L.gguf](https://huggingface.co/tensorblock/Qwen2-7B-GGUF/tree/main/Qwen2-7B-Q3_K_L.gguf) | Q3_K_L | 3.808 GB | small, substantial quality loss |
|
48 |
+
| [Qwen2-7B-Q4_0.gguf](https://huggingface.co/tensorblock/Qwen2-7B-GGUF/tree/main/Qwen2-7B-Q4_0.gguf) | Q4_0 | 4.127 GB | legacy; small, very high quality loss - prefer using Q3_K_M |
|
49 |
+
| [Qwen2-7B-Q4_K_S.gguf](https://huggingface.co/tensorblock/Qwen2-7B-GGUF/tree/main/Qwen2-7B-Q4_K_S.gguf) | Q4_K_S | 4.152 GB | small, greater quality loss |
|
50 |
+
| [Qwen2-7B-Q4_K_M.gguf](https://huggingface.co/tensorblock/Qwen2-7B-GGUF/tree/main/Qwen2-7B-Q4_K_M.gguf) | Q4_K_M | 4.361 GB | medium, balanced quality - recommended |
|
51 |
+
| [Qwen2-7B-Q5_0.gguf](https://huggingface.co/tensorblock/Qwen2-7B-GGUF/tree/main/Qwen2-7B-Q5_0.gguf) | Q5_0 | 4.950 GB | legacy; medium, balanced quality - prefer using Q4_K_M |
|
52 |
+
| [Qwen2-7B-Q5_K_S.gguf](https://huggingface.co/tensorblock/Qwen2-7B-GGUF/tree/main/Qwen2-7B-Q5_K_S.gguf) | Q5_K_S | 4.950 GB | large, low quality loss - recommended |
|
53 |
+
| [Qwen2-7B-Q5_K_M.gguf](https://huggingface.co/tensorblock/Qwen2-7B-GGUF/tree/main/Qwen2-7B-Q5_K_M.gguf) | Q5_K_M | 5.071 GB | large, very low quality loss - recommended |
|
54 |
+
| [Qwen2-7B-Q6_K.gguf](https://huggingface.co/tensorblock/Qwen2-7B-GGUF/tree/main/Qwen2-7B-Q6_K.gguf) | Q6_K | 5.825 GB | very large, extremely low quality loss |
|
55 |
+
| [Qwen2-7B-Q8_0.gguf](https://huggingface.co/tensorblock/Qwen2-7B-GGUF/tree/main/Qwen2-7B-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-GGUF --include "Qwen2-7B-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-GGUF --local-dir MY_LOCAL_DIR --local-dir-use-symlinks False --include='*Q4_K*gguf'
|
78 |
+
```
|