Upload folder using huggingface_hub
Browse files- .gitattributes +12 -0
- EXAONE-3.5-7.8B-Instruct-Q2_K.gguf +3 -0
- EXAONE-3.5-7.8B-Instruct-Q3_K_L.gguf +3 -0
- EXAONE-3.5-7.8B-Instruct-Q3_K_M.gguf +3 -0
- EXAONE-3.5-7.8B-Instruct-Q3_K_S.gguf +3 -0
- EXAONE-3.5-7.8B-Instruct-Q4_0.gguf +3 -0
- EXAONE-3.5-7.8B-Instruct-Q4_K_M.gguf +3 -0
- EXAONE-3.5-7.8B-Instruct-Q4_K_S.gguf +3 -0
- EXAONE-3.5-7.8B-Instruct-Q5_0.gguf +3 -0
- EXAONE-3.5-7.8B-Instruct-Q5_K_M.gguf +3 -0
- EXAONE-3.5-7.8B-Instruct-Q5_K_S.gguf +3 -0
- EXAONE-3.5-7.8B-Instruct-Q6_K.gguf +3 -0
- EXAONE-3.5-7.8B-Instruct-Q8_0.gguf +3 -0
- README.md +88 -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 |
+
EXAONE-3.5-7.8B-Instruct-Q2_K.gguf filter=lfs diff=lfs merge=lfs -text
|
37 |
+
EXAONE-3.5-7.8B-Instruct-Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text
|
38 |
+
EXAONE-3.5-7.8B-Instruct-Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text
|
39 |
+
EXAONE-3.5-7.8B-Instruct-Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text
|
40 |
+
EXAONE-3.5-7.8B-Instruct-Q4_0.gguf filter=lfs diff=lfs merge=lfs -text
|
41 |
+
EXAONE-3.5-7.8B-Instruct-Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text
|
42 |
+
EXAONE-3.5-7.8B-Instruct-Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text
|
43 |
+
EXAONE-3.5-7.8B-Instruct-Q5_0.gguf filter=lfs diff=lfs merge=lfs -text
|
44 |
+
EXAONE-3.5-7.8B-Instruct-Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text
|
45 |
+
EXAONE-3.5-7.8B-Instruct-Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text
|
46 |
+
EXAONE-3.5-7.8B-Instruct-Q6_K.gguf filter=lfs diff=lfs merge=lfs -text
|
47 |
+
EXAONE-3.5-7.8B-Instruct-Q8_0.gguf filter=lfs diff=lfs merge=lfs -text
|
EXAONE-3.5-7.8B-Instruct-Q2_K.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:7ddf9822b6bfcc004a8fd726ac22b188e0f9bd08e4e64d4a977db71719aa0e62
|
3 |
+
size 3053868992
|
EXAONE-3.5-7.8B-Instruct-Q3_K_L.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:ce333f57d2db1acc52808a8e95d31b55016e42fb5faeb36af918b66a4bc28ef2
|
3 |
+
size 4185937856
|
EXAONE-3.5-7.8B-Instruct-Q3_K_M.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:a615ebb6336b3dddbdeba987ea4c924eb755cdabb7d877a8ad9f4bbe5862112c
|
3 |
+
size 3882899392
|
EXAONE-3.5-7.8B-Instruct-Q3_K_S.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:4e8098290842f8a2caf14fa48afcf4da27a64fb6eb7c5af7b8e6b610f004eb86
|
3 |
+
size 3528480704
|
EXAONE-3.5-7.8B-Instruct-Q4_0.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:7254ac26e58c336e41eff58bbb1be21b12f14dc41e50967a812854be37080722
|
3 |
+
size 4511127488
|
EXAONE-3.5-7.8B-Instruct-Q4_K_M.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:1ea80a36a25939b38642e20156b994061224b09088c339a3122c757243cffc91
|
3 |
+
size 4770650048
|
EXAONE-3.5-7.8B-Instruct-Q4_K_S.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:ad4033a04816e044380be5ecb2e52a87dc3edfdfb2013fe46a724d23cdcd79db
|
3 |
+
size 4542584768
|
EXAONE-3.5-7.8B-Instruct-Q5_0.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:b3c6db86ca85b05ccb682d328858d6987dc7d65290603fd14170311629868752
|
3 |
+
size 5435971520
|
EXAONE-3.5-7.8B-Instruct-Q5_K_M.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:b700ff4f350658c995784f0f25b745125211480eacb8cacc38d246bbebb142b2
|
3 |
+
size 5569664960
|
EXAONE-3.5-7.8B-Instruct-Q5_K_S.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:51e035e1694f6e2282ae2600fc9827d99c5e2d98060bbb2c5cafd24874605fd7
|
3 |
+
size 5435971520
|
EXAONE-3.5-7.8B-Instruct-Q6_K.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:86e4b5eeb654739ab007a6bfabf914edfb332de37512a2c311d7986b31f28d6f
|
3 |
+
size 6418618304
|
EXAONE-3.5-7.8B-Instruct-Q8_0.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:89b751053fe98849ad1c84031e7461cc29019c4ea4fc023de1b7d7e095f0d51a
|
3 |
+
size 8312084416
|
README.md
ADDED
@@ -0,0 +1,88 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
license: other
|
3 |
+
license_name: exaone
|
4 |
+
license_link: LICENSE
|
5 |
+
language:
|
6 |
+
- en
|
7 |
+
- ko
|
8 |
+
tags:
|
9 |
+
- lg-ai
|
10 |
+
- exaone
|
11 |
+
- exaone-3.5
|
12 |
+
- TensorBlock
|
13 |
+
- GGUF
|
14 |
+
pipeline_tag: text-generation
|
15 |
+
library_name: transformers
|
16 |
+
base_model: LGAI-EXAONE/EXAONE-3.5-7.8B-Instruct
|
17 |
+
---
|
18 |
+
|
19 |
+
<div style="width: auto; margin-left: auto; margin-right: auto">
|
20 |
+
<img src="https://i.imgur.com/jC7kdl8.jpeg" alt="TensorBlock" style="width: 100%; min-width: 400px; display: block; margin: auto;">
|
21 |
+
</div>
|
22 |
+
<div style="display: flex; justify-content: space-between; width: 100%;">
|
23 |
+
<div style="display: flex; flex-direction: column; align-items: flex-start;">
|
24 |
+
<p style="margin-top: 0.5em; margin-bottom: 0em;">
|
25 |
+
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>
|
26 |
+
</p>
|
27 |
+
</div>
|
28 |
+
</div>
|
29 |
+
|
30 |
+
## LGAI-EXAONE/EXAONE-3.5-7.8B-Instruct - GGUF
|
31 |
+
|
32 |
+
This repo contains GGUF format model files for [LGAI-EXAONE/EXAONE-3.5-7.8B-Instruct](https://huggingface.co/LGAI-EXAONE/EXAONE-3.5-7.8B-Instruct).
|
33 |
+
|
34 |
+
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).
|
35 |
+
|
36 |
+
<div style="text-align: left; margin: 20px 0;">
|
37 |
+
<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;">
|
38 |
+
Run them on the TensorBlock client using your local machine ↗
|
39 |
+
</a>
|
40 |
+
</div>
|
41 |
+
|
42 |
+
## Prompt template
|
43 |
+
|
44 |
+
```
|
45 |
+
[|system|]{system_prompt}[|endofturn|]
|
46 |
+
[|user|]{prompt}
|
47 |
+
[|assistant|]
|
48 |
+
```
|
49 |
+
|
50 |
+
## Model file specification
|
51 |
+
|
52 |
+
| Filename | Quant type | File Size | Description |
|
53 |
+
| -------- | ---------- | --------- | ----------- |
|
54 |
+
| [EXAONE-3.5-7.8B-Instruct-Q2_K.gguf](https://huggingface.co/tensorblock/EXAONE-3.5-7.8B-Instruct-GGUF/blob/main/EXAONE-3.5-7.8B-Instruct-Q2_K.gguf) | Q2_K | 3.054 GB | smallest, significant quality loss - not recommended for most purposes |
|
55 |
+
| [EXAONE-3.5-7.8B-Instruct-Q3_K_S.gguf](https://huggingface.co/tensorblock/EXAONE-3.5-7.8B-Instruct-GGUF/blob/main/EXAONE-3.5-7.8B-Instruct-Q3_K_S.gguf) | Q3_K_S | 3.528 GB | very small, high quality loss |
|
56 |
+
| [EXAONE-3.5-7.8B-Instruct-Q3_K_M.gguf](https://huggingface.co/tensorblock/EXAONE-3.5-7.8B-Instruct-GGUF/blob/main/EXAONE-3.5-7.8B-Instruct-Q3_K_M.gguf) | Q3_K_M | 3.883 GB | very small, high quality loss |
|
57 |
+
| [EXAONE-3.5-7.8B-Instruct-Q3_K_L.gguf](https://huggingface.co/tensorblock/EXAONE-3.5-7.8B-Instruct-GGUF/blob/main/EXAONE-3.5-7.8B-Instruct-Q3_K_L.gguf) | Q3_K_L | 4.186 GB | small, substantial quality loss |
|
58 |
+
| [EXAONE-3.5-7.8B-Instruct-Q4_0.gguf](https://huggingface.co/tensorblock/EXAONE-3.5-7.8B-Instruct-GGUF/blob/main/EXAONE-3.5-7.8B-Instruct-Q4_0.gguf) | Q4_0 | 4.511 GB | legacy; small, very high quality loss - prefer using Q3_K_M |
|
59 |
+
| [EXAONE-3.5-7.8B-Instruct-Q4_K_S.gguf](https://huggingface.co/tensorblock/EXAONE-3.5-7.8B-Instruct-GGUF/blob/main/EXAONE-3.5-7.8B-Instruct-Q4_K_S.gguf) | Q4_K_S | 4.543 GB | small, greater quality loss |
|
60 |
+
| [EXAONE-3.5-7.8B-Instruct-Q4_K_M.gguf](https://huggingface.co/tensorblock/EXAONE-3.5-7.8B-Instruct-GGUF/blob/main/EXAONE-3.5-7.8B-Instruct-Q4_K_M.gguf) | Q4_K_M | 4.771 GB | medium, balanced quality - recommended |
|
61 |
+
| [EXAONE-3.5-7.8B-Instruct-Q5_0.gguf](https://huggingface.co/tensorblock/EXAONE-3.5-7.8B-Instruct-GGUF/blob/main/EXAONE-3.5-7.8B-Instruct-Q5_0.gguf) | Q5_0 | 5.436 GB | legacy; medium, balanced quality - prefer using Q4_K_M |
|
62 |
+
| [EXAONE-3.5-7.8B-Instruct-Q5_K_S.gguf](https://huggingface.co/tensorblock/EXAONE-3.5-7.8B-Instruct-GGUF/blob/main/EXAONE-3.5-7.8B-Instruct-Q5_K_S.gguf) | Q5_K_S | 5.436 GB | large, low quality loss - recommended |
|
63 |
+
| [EXAONE-3.5-7.8B-Instruct-Q5_K_M.gguf](https://huggingface.co/tensorblock/EXAONE-3.5-7.8B-Instruct-GGUF/blob/main/EXAONE-3.5-7.8B-Instruct-Q5_K_M.gguf) | Q5_K_M | 5.570 GB | large, very low quality loss - recommended |
|
64 |
+
| [EXAONE-3.5-7.8B-Instruct-Q6_K.gguf](https://huggingface.co/tensorblock/EXAONE-3.5-7.8B-Instruct-GGUF/blob/main/EXAONE-3.5-7.8B-Instruct-Q6_K.gguf) | Q6_K | 6.419 GB | very large, extremely low quality loss |
|
65 |
+
| [EXAONE-3.5-7.8B-Instruct-Q8_0.gguf](https://huggingface.co/tensorblock/EXAONE-3.5-7.8B-Instruct-GGUF/blob/main/EXAONE-3.5-7.8B-Instruct-Q8_0.gguf) | Q8_0 | 8.312 GB | very large, extremely low quality loss - not recommended |
|
66 |
+
|
67 |
+
|
68 |
+
## Downloading instruction
|
69 |
+
|
70 |
+
### Command line
|
71 |
+
|
72 |
+
Firstly, install Huggingface Client
|
73 |
+
|
74 |
+
```shell
|
75 |
+
pip install -U "huggingface_hub[cli]"
|
76 |
+
```
|
77 |
+
|
78 |
+
Then, downoad the individual model file the a local directory
|
79 |
+
|
80 |
+
```shell
|
81 |
+
huggingface-cli download tensorblock/EXAONE-3.5-7.8B-Instruct-GGUF --include "EXAONE-3.5-7.8B-Instruct-Q2_K.gguf" --local-dir MY_LOCAL_DIR
|
82 |
+
```
|
83 |
+
|
84 |
+
If you wanna download multiple model files with a pattern (e.g., `*Q4_K*gguf`), you can try:
|
85 |
+
|
86 |
+
```shell
|
87 |
+
huggingface-cli download tensorblock/EXAONE-3.5-7.8B-Instruct-GGUF --local-dir MY_LOCAL_DIR --local-dir-use-symlinks False --include='*Q4_K*gguf'
|
88 |
+
```
|