Upload folder using huggingface_hub
Browse files- .gitattributes +12 -0
- KONI-Llama3-8B-20240630-Q2_K.gguf +3 -0
- KONI-Llama3-8B-20240630-Q3_K_L.gguf +3 -0
- KONI-Llama3-8B-20240630-Q3_K_M.gguf +3 -0
- KONI-Llama3-8B-20240630-Q3_K_S.gguf +3 -0
- KONI-Llama3-8B-20240630-Q4_0.gguf +3 -0
- KONI-Llama3-8B-20240630-Q4_K_M.gguf +3 -0
- KONI-Llama3-8B-20240630-Q4_K_S.gguf +3 -0
- KONI-Llama3-8B-20240630-Q5_0.gguf +3 -0
- KONI-Llama3-8B-20240630-Q5_K_M.gguf +3 -0
- KONI-Llama3-8B-20240630-Q5_K_S.gguf +3 -0
- KONI-Llama3-8B-20240630-Q6_K.gguf +3 -0
- KONI-Llama3-8B-20240630-Q8_0.gguf +3 -0
- README.md +85 -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 |
+
KONI-Llama3-8B-20240630-Q2_K.gguf filter=lfs diff=lfs merge=lfs -text
|
37 |
+
KONI-Llama3-8B-20240630-Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text
|
38 |
+
KONI-Llama3-8B-20240630-Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text
|
39 |
+
KONI-Llama3-8B-20240630-Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text
|
40 |
+
KONI-Llama3-8B-20240630-Q4_0.gguf filter=lfs diff=lfs merge=lfs -text
|
41 |
+
KONI-Llama3-8B-20240630-Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text
|
42 |
+
KONI-Llama3-8B-20240630-Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text
|
43 |
+
KONI-Llama3-8B-20240630-Q5_0.gguf filter=lfs diff=lfs merge=lfs -text
|
44 |
+
KONI-Llama3-8B-20240630-Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text
|
45 |
+
KONI-Llama3-8B-20240630-Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text
|
46 |
+
KONI-Llama3-8B-20240630-Q6_K.gguf filter=lfs diff=lfs merge=lfs -text
|
47 |
+
KONI-Llama3-8B-20240630-Q8_0.gguf filter=lfs diff=lfs merge=lfs -text
|
KONI-Llama3-8B-20240630-Q2_K.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:c2cd8d082320501aa1569568d4d6bde3f545f211a15d4e7888be8d16ecfbca05
|
3 |
+
size 3179131136
|
KONI-Llama3-8B-20240630-Q3_K_L.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:4fed14a2fc70947a948c6a7e00f6a323f2b0db7c8c26d134d26ff8d4b176cbf7
|
3 |
+
size 4321956096
|
KONI-Llama3-8B-20240630-Q3_K_M.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:3025e991cf6a907eb6f66e16fa0d6cfdf13685a585b34760ef7d5eb4a62c53c8
|
3 |
+
size 4018917632
|
KONI-Llama3-8B-20240630-Q3_K_S.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:5d6c0be7a63709c1dc08be6fd9c0627e159b56af5646313fd259e7ab3bc2364e
|
3 |
+
size 3664498944
|
KONI-Llama3-8B-20240630-Q4_0.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:ae5915f04a80f7e6d09b2224bb9bba9cf829c28528cbde01490b3ffcf4242afc
|
3 |
+
size 4661211392
|
KONI-Llama3-8B-20240630-Q4_K_M.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:cda54c0add872cd94314b8a532df189aaff34937b656a8e8aa06b752bdac514a
|
3 |
+
size 4920733952
|
KONI-Llama3-8B-20240630-Q4_K_S.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:2c1aa27e28dcb05404c39fb45986c335a4e95586901b2863f958f8df2825ed6f
|
3 |
+
size 4692668672
|
KONI-Llama3-8B-20240630-Q5_0.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:c02c05d0b4985bcc17c3a2145c317fd155b8e49dc683d9d18ba541f0b0340ef0
|
3 |
+
size 5599293696
|
KONI-Llama3-8B-20240630-Q5_K_M.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:0e2fff1355578ee09fea33c6048fe342fb481d78ffcb7182059701f59e615a14
|
3 |
+
size 5732987136
|
KONI-Llama3-8B-20240630-Q5_K_S.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:eebb0a743c28fa6af78207f74592767d9d66f0243d4f767eea3b1fa4b59725c2
|
3 |
+
size 5599293696
|
KONI-Llama3-8B-20240630-Q6_K.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:08be244e9e9f7c517ada2b4696cbd645b9e138f2948161a1a37b7c98e6a37f5d
|
3 |
+
size 6596006144
|
KONI-Llama3-8B-20240630-Q8_0.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:57d798ea6af4830a33b970fb3a32c511bb55e6c58a8bf423faf35701b1c0c2b0
|
3 |
+
size 8540770560
|
README.md
ADDED
@@ -0,0 +1,85 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
language:
|
3 |
+
- en
|
4 |
+
- ko
|
5 |
+
tags:
|
6 |
+
- KISTI
|
7 |
+
- KONI
|
8 |
+
- llama
|
9 |
+
- llama3
|
10 |
+
- llama3-8b
|
11 |
+
- TensorBlock
|
12 |
+
- GGUF
|
13 |
+
pipeline_tag: text-generation
|
14 |
+
license: llama3
|
15 |
+
base_model: KISTI-KONI/KONI-Llama3-8B-20240630
|
16 |
+
---
|
17 |
+
|
18 |
+
<div style="width: auto; margin-left: auto; margin-right: auto">
|
19 |
+
<img src="https://i.imgur.com/jC7kdl8.jpeg" alt="TensorBlock" style="width: 100%; min-width: 400px; display: block; margin: auto;">
|
20 |
+
</div>
|
21 |
+
<div style="display: flex; justify-content: space-between; width: 100%;">
|
22 |
+
<div style="display: flex; flex-direction: column; align-items: flex-start;">
|
23 |
+
<p style="margin-top: 0.5em; margin-bottom: 0em;">
|
24 |
+
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>
|
25 |
+
</p>
|
26 |
+
</div>
|
27 |
+
</div>
|
28 |
+
|
29 |
+
## KISTI-KONI/KONI-Llama3-8B-20240630 - GGUF
|
30 |
+
|
31 |
+
This repo contains GGUF format model files for [KISTI-KONI/KONI-Llama3-8B-20240630](https://huggingface.co/KISTI-KONI/KONI-Llama3-8B-20240630).
|
32 |
+
|
33 |
+
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).
|
34 |
+
|
35 |
+
<div style="text-align: left; margin: 20px 0;">
|
36 |
+
<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;">
|
37 |
+
Run them on the TensorBlock client using your local machine ↗
|
38 |
+
</a>
|
39 |
+
</div>
|
40 |
+
|
41 |
+
## Prompt template
|
42 |
+
|
43 |
+
```
|
44 |
+
|
45 |
+
```
|
46 |
+
|
47 |
+
## Model file specification
|
48 |
+
|
49 |
+
| Filename | Quant type | File Size | Description |
|
50 |
+
| -------- | ---------- | --------- | ----------- |
|
51 |
+
| [KONI-Llama3-8B-20240630-Q2_K.gguf](https://huggingface.co/tensorblock/KONI-Llama3-8B-20240630-GGUF/blob/main/KONI-Llama3-8B-20240630-Q2_K.gguf) | Q2_K | 3.179 GB | smallest, significant quality loss - not recommended for most purposes |
|
52 |
+
| [KONI-Llama3-8B-20240630-Q3_K_S.gguf](https://huggingface.co/tensorblock/KONI-Llama3-8B-20240630-GGUF/blob/main/KONI-Llama3-8B-20240630-Q3_K_S.gguf) | Q3_K_S | 3.664 GB | very small, high quality loss |
|
53 |
+
| [KONI-Llama3-8B-20240630-Q3_K_M.gguf](https://huggingface.co/tensorblock/KONI-Llama3-8B-20240630-GGUF/blob/main/KONI-Llama3-8B-20240630-Q3_K_M.gguf) | Q3_K_M | 4.019 GB | very small, high quality loss |
|
54 |
+
| [KONI-Llama3-8B-20240630-Q3_K_L.gguf](https://huggingface.co/tensorblock/KONI-Llama3-8B-20240630-GGUF/blob/main/KONI-Llama3-8B-20240630-Q3_K_L.gguf) | Q3_K_L | 4.322 GB | small, substantial quality loss |
|
55 |
+
| [KONI-Llama3-8B-20240630-Q4_0.gguf](https://huggingface.co/tensorblock/KONI-Llama3-8B-20240630-GGUF/blob/main/KONI-Llama3-8B-20240630-Q4_0.gguf) | Q4_0 | 4.661 GB | legacy; small, very high quality loss - prefer using Q3_K_M |
|
56 |
+
| [KONI-Llama3-8B-20240630-Q4_K_S.gguf](https://huggingface.co/tensorblock/KONI-Llama3-8B-20240630-GGUF/blob/main/KONI-Llama3-8B-20240630-Q4_K_S.gguf) | Q4_K_S | 4.693 GB | small, greater quality loss |
|
57 |
+
| [KONI-Llama3-8B-20240630-Q4_K_M.gguf](https://huggingface.co/tensorblock/KONI-Llama3-8B-20240630-GGUF/blob/main/KONI-Llama3-8B-20240630-Q4_K_M.gguf) | Q4_K_M | 4.921 GB | medium, balanced quality - recommended |
|
58 |
+
| [KONI-Llama3-8B-20240630-Q5_0.gguf](https://huggingface.co/tensorblock/KONI-Llama3-8B-20240630-GGUF/blob/main/KONI-Llama3-8B-20240630-Q5_0.gguf) | Q5_0 | 5.599 GB | legacy; medium, balanced quality - prefer using Q4_K_M |
|
59 |
+
| [KONI-Llama3-8B-20240630-Q5_K_S.gguf](https://huggingface.co/tensorblock/KONI-Llama3-8B-20240630-GGUF/blob/main/KONI-Llama3-8B-20240630-Q5_K_S.gguf) | Q5_K_S | 5.599 GB | large, low quality loss - recommended |
|
60 |
+
| [KONI-Llama3-8B-20240630-Q5_K_M.gguf](https://huggingface.co/tensorblock/KONI-Llama3-8B-20240630-GGUF/blob/main/KONI-Llama3-8B-20240630-Q5_K_M.gguf) | Q5_K_M | 5.733 GB | large, very low quality loss - recommended |
|
61 |
+
| [KONI-Llama3-8B-20240630-Q6_K.gguf](https://huggingface.co/tensorblock/KONI-Llama3-8B-20240630-GGUF/blob/main/KONI-Llama3-8B-20240630-Q6_K.gguf) | Q6_K | 6.596 GB | very large, extremely low quality loss |
|
62 |
+
| [KONI-Llama3-8B-20240630-Q8_0.gguf](https://huggingface.co/tensorblock/KONI-Llama3-8B-20240630-GGUF/blob/main/KONI-Llama3-8B-20240630-Q8_0.gguf) | Q8_0 | 8.541 GB | very large, extremely low quality loss - not recommended |
|
63 |
+
|
64 |
+
|
65 |
+
## Downloading instruction
|
66 |
+
|
67 |
+
### Command line
|
68 |
+
|
69 |
+
Firstly, install Huggingface Client
|
70 |
+
|
71 |
+
```shell
|
72 |
+
pip install -U "huggingface_hub[cli]"
|
73 |
+
```
|
74 |
+
|
75 |
+
Then, downoad the individual model file the a local directory
|
76 |
+
|
77 |
+
```shell
|
78 |
+
huggingface-cli download tensorblock/KONI-Llama3-8B-20240630-GGUF --include "KONI-Llama3-8B-20240630-Q2_K.gguf" --local-dir MY_LOCAL_DIR
|
79 |
+
```
|
80 |
+
|
81 |
+
If you wanna download multiple model files with a pattern (e.g., `*Q4_K*gguf`), you can try:
|
82 |
+
|
83 |
+
```shell
|
84 |
+
huggingface-cli download tensorblock/KONI-Llama3-8B-20240630-GGUF --local-dir MY_LOCAL_DIR --local-dir-use-symlinks False --include='*Q4_K*gguf'
|
85 |
+
```
|