Hugging Face's logo

tensorblock
/
original-KoRAE-13b-3ep-GGUF

Transformers
GGUF
Korean
TensorBlock
GGUF
Inference Endpoints
conversational
Model card Files Community
morriszms commited on
Commit
3458f99
•
1 Parent(s): c76e81b

Upload folder using huggingface_hub

Browse files
Files changed (14) hide show
  1. .gitattributes +12 -0
  2. README.md +81 -0
  3. original-KoRAE-13b-3ep-Q2_K.gguf +3 -0
  4. original-KoRAE-13b-3ep-Q3_K_L.gguf +3 -0
  5. original-KoRAE-13b-3ep-Q3_K_M.gguf +3 -0
  6. original-KoRAE-13b-3ep-Q3_K_S.gguf +3 -0
  7. original-KoRAE-13b-3ep-Q4_0.gguf +3 -0
  8. original-KoRAE-13b-3ep-Q4_K_M.gguf +3 -0
  9. original-KoRAE-13b-3ep-Q4_K_S.gguf +3 -0
  10. original-KoRAE-13b-3ep-Q5_0.gguf +3 -0
  11. original-KoRAE-13b-3ep-Q5_K_M.gguf +3 -0
  12. original-KoRAE-13b-3ep-Q5_K_S.gguf +3 -0
  13. original-KoRAE-13b-3ep-Q6_K.gguf +3 -0
  14. original-KoRAE-13b-3ep-Q8_0.gguf +3 -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
+ original-KoRAE-13b-3ep-Q2_K.gguf filter=lfs diff=lfs merge=lfs -text
37
+ original-KoRAE-13b-3ep-Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text
38
+ original-KoRAE-13b-3ep-Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text
39
+ original-KoRAE-13b-3ep-Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text
40
+ original-KoRAE-13b-3ep-Q4_0.gguf filter=lfs diff=lfs merge=lfs -text
41
+ original-KoRAE-13b-3ep-Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text
42
+ original-KoRAE-13b-3ep-Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text
43
+ original-KoRAE-13b-3ep-Q5_0.gguf filter=lfs diff=lfs merge=lfs -text
44
+ original-KoRAE-13b-3ep-Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text
45
+ original-KoRAE-13b-3ep-Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text
46
+ original-KoRAE-13b-3ep-Q6_K.gguf filter=lfs diff=lfs merge=lfs -text
47
+ original-KoRAE-13b-3ep-Q8_0.gguf filter=lfs diff=lfs merge=lfs -text
README.md ADDED
@@ -0,0 +1,81 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ license: cc-by-nc-sa-4.0
3
+ datasets:
4
+ - Cartinoe5930/KoRAE_original
5
+ language:
6
+ - ko
7
+ library_name: transformers
8
+ tags:
9
+ - TensorBlock
10
+ - GGUF
11
+ base_model: Cartinoe5930/original-KoRAE-13b-3ep
12
+ ---
13
+
14
+ <div style="width: auto; margin-left: auto; margin-right: auto">
15
+ <img src="https://i.imgur.com/jC7kdl8.jpeg" alt="TensorBlock" style="width: 100%; min-width: 400px; display: block; margin: auto;">
16
+ </div>
17
+ <div style="display: flex; justify-content: space-between; width: 100%;">
18
+ <div style="display: flex; flex-direction: column; align-items: flex-start;">
19
+ <p style="margin-top: 0.5em; margin-bottom: 0em;">
20
+ 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>
21
+ </p>
22
+ </div>
23
+ </div>
24
+
25
+ ## Cartinoe5930/original-KoRAE-13b-3ep - GGUF
26
+
27
+ This repo contains GGUF format model files for [Cartinoe5930/original-KoRAE-13b-3ep](https://huggingface.co/Cartinoe5930/original-KoRAE-13b-3ep).
28
+
29
+ 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).
30
+
31
+ ## Prompt template
32
+
33
+ ```
34
+ ### System:
35
+ {system_prompt}</s>
36
+
37
+ ### User:
38
+ {prompt}</s>
39
+
40
+ ### Assistant:
41
+ ```
42
+
43
+ ## Model file specification
44
+
45
+ | Filename | Quant type | File Size | Description |
46
+ | -------- | ---------- | --------- | ----------- |
47
+ | [original-KoRAE-13b-3ep-Q2_K.gguf](https://huggingface.co/tensorblock/original-KoRAE-13b-3ep-GGUF/tree/main/original-KoRAE-13b-3ep-Q2_K.gguf) | Q2_K | 4.600 GB | smallest, significant quality loss - not recommended for most purposes |
48
+ | [original-KoRAE-13b-3ep-Q3_K_S.gguf](https://huggingface.co/tensorblock/original-KoRAE-13b-3ep-GGUF/tree/main/original-KoRAE-13b-3ep-Q3_K_S.gguf) | Q3_K_S | 5.356 GB | very small, high quality loss |
49
+ | [original-KoRAE-13b-3ep-Q3_K_M.gguf](https://huggingface.co/tensorblock/original-KoRAE-13b-3ep-GGUF/tree/main/original-KoRAE-13b-3ep-Q3_K_M.gguf) | Q3_K_M | 5.988 GB | very small, high quality loss |
50
+ | [original-KoRAE-13b-3ep-Q3_K_L.gguf](https://huggingface.co/tensorblock/original-KoRAE-13b-3ep-GGUF/tree/main/original-KoRAE-13b-3ep-Q3_K_L.gguf) | Q3_K_L | 6.539 GB | small, substantial quality loss |
51
+ | [original-KoRAE-13b-3ep-Q4_0.gguf](https://huggingface.co/tensorblock/original-KoRAE-13b-3ep-GGUF/tree/main/original-KoRAE-13b-3ep-Q4_0.gguf) | Q4_0 | 6.955 GB | legacy; small, very high quality loss - prefer using Q3_K_M |
52
+ | [original-KoRAE-13b-3ep-Q4_K_S.gguf](https://huggingface.co/tensorblock/original-KoRAE-13b-3ep-GGUF/tree/main/original-KoRAE-13b-3ep-Q4_K_S.gguf) | Q4_K_S | 7.008 GB | small, greater quality loss |
53
+ | [original-KoRAE-13b-3ep-Q4_K_M.gguf](https://huggingface.co/tensorblock/original-KoRAE-13b-3ep-GGUF/tree/main/original-KoRAE-13b-3ep-Q4_K_M.gguf) | Q4_K_M | 7.421 GB | medium, balanced quality - recommended |
54
+ | [original-KoRAE-13b-3ep-Q5_0.gguf](https://huggingface.co/tensorblock/original-KoRAE-13b-3ep-GGUF/tree/main/original-KoRAE-13b-3ep-Q5_0.gguf) | Q5_0 | 8.459 GB | legacy; medium, balanced quality - prefer using Q4_K_M |
55
+ | [original-KoRAE-13b-3ep-Q5_K_S.gguf](https://huggingface.co/tensorblock/original-KoRAE-13b-3ep-GGUF/tree/main/original-KoRAE-13b-3ep-Q5_K_S.gguf) | Q5_K_S | 8.459 GB | large, low quality loss - recommended |
56
+ | [original-KoRAE-13b-3ep-Q5_K_M.gguf](https://huggingface.co/tensorblock/original-KoRAE-13b-3ep-GGUF/tree/main/original-KoRAE-13b-3ep-Q5_K_M.gguf) | Q5_K_M | 8.699 GB | large, very low quality loss - recommended |
57
+ | [original-KoRAE-13b-3ep-Q6_K.gguf](https://huggingface.co/tensorblock/original-KoRAE-13b-3ep-GGUF/tree/main/original-KoRAE-13b-3ep-Q6_K.gguf) | Q6_K | 10.058 GB | very large, extremely low quality loss |
58
+ | [original-KoRAE-13b-3ep-Q8_0.gguf](https://huggingface.co/tensorblock/original-KoRAE-13b-3ep-GGUF/tree/main/original-KoRAE-13b-3ep-Q8_0.gguf) | Q8_0 | 13.027 GB | very large, extremely low quality loss - not recommended |
59
+
60
+
61
+ ## Downloading instruction
62
+
63
+ ### Command line
64
+
65
+ Firstly, install Huggingface Client
66
+
67
+ ```shell
68
+ pip install -U "huggingface_hub[cli]"
69
+ ```
70
+
71
+ Then, downoad the individual model file the a local directory
72
+
73
+ ```shell
74
+ huggingface-cli download tensorblock/original-KoRAE-13b-3ep-GGUF --include "original-KoRAE-13b-3ep-Q2_K.gguf" --local-dir MY_LOCAL_DIR
75
+ ```
76
+
77
+ If you wanna download multiple model files with a pattern (e.g., `*Q4_K*gguf`), you can try:
78
+
79
+ ```shell
80
+ huggingface-cli download tensorblock/original-KoRAE-13b-3ep-GGUF --local-dir MY_LOCAL_DIR --local-dir-use-symlinks False --include='*Q4_K*gguf'
81
+ ```
original-KoRAE-13b-3ep-Q2_K.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b49741af4c4825c8995d4229a8e4c76612e4eebfd604dd7b0c644e2b62babfc5
3
+ size 4938918592
original-KoRAE-13b-3ep-Q3_K_L.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:26d8518bd36023908bfc430811925a7bf9e946bde1a52dd9d3e029ab503fafd4
3
+ size 7021662912
original-KoRAE-13b-3ep-Q3_K_M.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c67a41fdb232db2083620c5f89b0c89510471888007e6ef0d59fa7750d7573ce
3
+ size 6429872832
original-KoRAE-13b-3ep-Q3_K_S.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7518492ac8a4936dfdd64ecff6960fb08b11186f4d35c01c48f3436ce9c2365c
3
+ size 5751083712
original-KoRAE-13b-3ep-Q4_0.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5380657a666b8a6586d52acabbc7dcd1290bb4000277880119c0a98ba2c1896d
3
+ size 7467686592
original-KoRAE-13b-3ep-Q4_K_M.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f9621111051918d96137efa334e9acaa3f23d21799ecd8f7a9e1e9354fd2c250
3
+ size 7967808192
original-KoRAE-13b-3ep-Q4_K_S.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4e89d80499679661b6eb083b4d8067d18fa2f3d76176f0d86d507883b25bd32d
3
+ size 7525030592
original-KoRAE-13b-3ep-Q5_0.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bf4c105052584f45be04660cab3aa8ec707fc8a8df6ad9ecc6059d776dc443ba
3
+ size 9083312832
original-KoRAE-13b-3ep-Q5_K_M.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5ef6c6983fab872da8ea1bf83fc44e48a1431dc2039de69f18e3462ecf872337
3
+ size 9340951232
original-KoRAE-13b-3ep-Q5_K_S.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:349fcb73661b4c27db4fd5b7e35c036b740c2ecdb02d077f54cb768c55f3a266
3
+ size 9083312832
original-KoRAE-13b-3ep-Q6_K.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ce51195700244ffd46424e6b5e372b962a90248840453327441f6f44b491e38e
3
+ size 10799915712
original-KoRAE-13b-3ep-Q8_0.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:58aad1f990e0b70945a49b9965e35c3bcbc335f13f523949b8fd4580a3172ffd
3
+ size 13987648192