morriszms commited on
Commit
53a76ab
·
verified ·
1 Parent(s): b5a6926

Upload folder using huggingface_hub

Browse files
.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
+ KoSOLAR-10.9B-v0.5-Q2_K.gguf filter=lfs diff=lfs merge=lfs -text
37
+ KoSOLAR-10.9B-v0.5-Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text
38
+ KoSOLAR-10.9B-v0.5-Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text
39
+ KoSOLAR-10.9B-v0.5-Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text
40
+ KoSOLAR-10.9B-v0.5-Q4_0.gguf filter=lfs diff=lfs merge=lfs -text
41
+ KoSOLAR-10.9B-v0.5-Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text
42
+ KoSOLAR-10.9B-v0.5-Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text
43
+ KoSOLAR-10.9B-v0.5-Q5_0.gguf filter=lfs diff=lfs merge=lfs -text
44
+ KoSOLAR-10.9B-v0.5-Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text
45
+ KoSOLAR-10.9B-v0.5-Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text
46
+ KoSOLAR-10.9B-v0.5-Q6_K.gguf filter=lfs diff=lfs merge=lfs -text
47
+ KoSOLAR-10.9B-v0.5-Q8_0.gguf filter=lfs diff=lfs merge=lfs -text
KoSOLAR-10.9B-v0.5-Q2_K.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7a6404b7be55923da34d28c194be7863e58d2530bfd21f9370eccb4a16b7c883
3
+ size 4078893312
KoSOLAR-10.9B-v0.5-Q3_K_L.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:33715f9ca2b6a0e84cef872a13de65fe151d8d1edd088e992126d1daeeba0f41
3
+ size 5733067008
KoSOLAR-10.9B-v0.5-Q3_K_M.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ec8198b30ab2bf1c46977312f4b511fd3fd386a87a6547263ca9057c6e71b223
3
+ size 5277985024
KoSOLAR-10.9B-v0.5-Q3_K_S.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cc200bfaf804454799492e07442135580e0feb0dd3484e41d856aa5da411dcc2
3
+ size 4746881280
KoSOLAR-10.9B-v0.5-Q4_0.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1b821a42945bde02b7afabe914eb875762580809003df21707c56a6ca340dde3
3
+ size 6163405056
KoSOLAR-10.9B-v0.5-Q4_K_M.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:056456ba71f9f6702c31baac2ef085b2ec3a3ee08636f20ad8fdaf41dbcb064c
3
+ size 6552688896
KoSOLAR-10.9B-v0.5-Q4_K_S.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fdc5ec0199462a34313318228a56326d747c3f231aceafff1bb89c4dd1efb2eb
3
+ size 6209542400
KoSOLAR-10.9B-v0.5-Q5_0.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4b8298a1c916dfac4468e08b203dcb6886edd24903ef676975652befb5d870ba
3
+ size 7496603904
KoSOLAR-10.9B-v0.5-Q5_K_M.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ddb006209fc5b056175a1ccb1233ebebad457ddd97ce5aaeb7d8e02b7cfe84f9
3
+ size 7697144064
KoSOLAR-10.9B-v0.5-Q5_K_S.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7143f153618f379a0019864859949515e016ba50f2e875c7846dc675a7221661
3
+ size 7496603904
KoSOLAR-10.9B-v0.5-Q6_K.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c27819d624c9e45de0d49f3a0eaa49bd24af1afc9727fe7e2b27d3d306494e2f
3
+ size 8913127680
KoSOLAR-10.9B-v0.5-Q8_0.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8cb47159a2d2638e601ae29c0da8f087b7f6df7992e1055d26a25f58cfbd207c
3
+ size 11543816448
README.md ADDED
@@ -0,0 +1,82 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ language:
3
+ - ko
4
+ base_model: rrw-x2/KoSOLAR-10.9B-v0.5
5
+ tags:
6
+ - mergekit
7
+ - merge
8
+ - LDCC/LDCC-SOLAR-10.7B
9
+ - hyeogi/SOLAR-10.7B-dpo-v1
10
+ - TensorBlock
11
+ - GGUF
12
+ license: apache-2.0
13
+ ---
14
+
15
+ <div style="width: auto; margin-left: auto; margin-right: auto">
16
+ <img src="https://i.imgur.com/jC7kdl8.jpeg" alt="TensorBlock" style="width: 100%; min-width: 400px; display: block; margin: auto;">
17
+ </div>
18
+ <div style="display: flex; justify-content: space-between; width: 100%;">
19
+ <div style="display: flex; flex-direction: column; align-items: flex-start;">
20
+ <p style="margin-top: 0.5em; margin-bottom: 0em;">
21
+ 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>
22
+ </p>
23
+ </div>
24
+ </div>
25
+
26
+ ## rrw-x2/KoSOLAR-10.9B-v0.5 - GGUF
27
+
28
+ This repo contains GGUF format model files for [rrw-x2/KoSOLAR-10.9B-v0.5](https://huggingface.co/rrw-x2/KoSOLAR-10.9B-v0.5).
29
+
30
+ 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).
31
+
32
+ <div style="text-align: left; margin: 20px 0;">
33
+ <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;">
34
+ Run them on the TensorBlock client using your local machine ↗
35
+ </a>
36
+ </div>
37
+
38
+ ## Prompt template
39
+
40
+ ```
41
+
42
+ ```
43
+
44
+ ## Model file specification
45
+
46
+ | Filename | Quant type | File Size | Description |
47
+ | -------- | ---------- | --------- | ----------- |
48
+ | [KoSOLAR-10.9B-v0.5-Q2_K.gguf](https://huggingface.co/tensorblock/KoSOLAR-10.9B-v0.5-GGUF/blob/main/KoSOLAR-10.9B-v0.5-Q2_K.gguf) | Q2_K | 3.799 GB | smallest, significant quality loss - not recommended for most purposes |
49
+ | [KoSOLAR-10.9B-v0.5-Q3_K_S.gguf](https://huggingface.co/tensorblock/KoSOLAR-10.9B-v0.5-GGUF/blob/main/KoSOLAR-10.9B-v0.5-Q3_K_S.gguf) | Q3_K_S | 4.421 GB | very small, high quality loss |
50
+ | [KoSOLAR-10.9B-v0.5-Q3_K_M.gguf](https://huggingface.co/tensorblock/KoSOLAR-10.9B-v0.5-GGUF/blob/main/KoSOLAR-10.9B-v0.5-Q3_K_M.gguf) | Q3_K_M | 4.916 GB | very small, high quality loss |
51
+ | [KoSOLAR-10.9B-v0.5-Q3_K_L.gguf](https://huggingface.co/tensorblock/KoSOLAR-10.9B-v0.5-GGUF/blob/main/KoSOLAR-10.9B-v0.5-Q3_K_L.gguf) | Q3_K_L | 5.339 GB | small, substantial quality loss |
52
+ | [KoSOLAR-10.9B-v0.5-Q4_0.gguf](https://huggingface.co/tensorblock/KoSOLAR-10.9B-v0.5-GGUF/blob/main/KoSOLAR-10.9B-v0.5-Q4_0.gguf) | Q4_0 | 5.740 GB | legacy; small, very high quality loss - prefer using Q3_K_M |
53
+ | [KoSOLAR-10.9B-v0.5-Q4_K_S.gguf](https://huggingface.co/tensorblock/KoSOLAR-10.9B-v0.5-GGUF/blob/main/KoSOLAR-10.9B-v0.5-Q4_K_S.gguf) | Q4_K_S | 5.783 GB | small, greater quality loss |
54
+ | [KoSOLAR-10.9B-v0.5-Q4_K_M.gguf](https://huggingface.co/tensorblock/KoSOLAR-10.9B-v0.5-GGUF/blob/main/KoSOLAR-10.9B-v0.5-Q4_K_M.gguf) | Q4_K_M | 6.103 GB | medium, balanced quality - recommended |
55
+ | [KoSOLAR-10.9B-v0.5-Q5_0.gguf](https://huggingface.co/tensorblock/KoSOLAR-10.9B-v0.5-GGUF/blob/main/KoSOLAR-10.9B-v0.5-Q5_0.gguf) | Q5_0 | 6.982 GB | legacy; medium, balanced quality - prefer using Q4_K_M |
56
+ | [KoSOLAR-10.9B-v0.5-Q5_K_S.gguf](https://huggingface.co/tensorblock/KoSOLAR-10.9B-v0.5-GGUF/blob/main/KoSOLAR-10.9B-v0.5-Q5_K_S.gguf) | Q5_K_S | 6.982 GB | large, low quality loss - recommended |
57
+ | [KoSOLAR-10.9B-v0.5-Q5_K_M.gguf](https://huggingface.co/tensorblock/KoSOLAR-10.9B-v0.5-GGUF/blob/main/KoSOLAR-10.9B-v0.5-Q5_K_M.gguf) | Q5_K_M | 7.169 GB | large, very low quality loss - recommended |
58
+ | [KoSOLAR-10.9B-v0.5-Q6_K.gguf](https://huggingface.co/tensorblock/KoSOLAR-10.9B-v0.5-GGUF/blob/main/KoSOLAR-10.9B-v0.5-Q6_K.gguf) | Q6_K | 8.301 GB | very large, extremely low quality loss |
59
+ | [KoSOLAR-10.9B-v0.5-Q8_0.gguf](https://huggingface.co/tensorblock/KoSOLAR-10.9B-v0.5-GGUF/blob/main/KoSOLAR-10.9B-v0.5-Q8_0.gguf) | Q8_0 | 10.751 GB | very large, extremely low quality loss - not recommended |
60
+
61
+
62
+ ## Downloading instruction
63
+
64
+ ### Command line
65
+
66
+ Firstly, install Huggingface Client
67
+
68
+ ```shell
69
+ pip install -U "huggingface_hub[cli]"
70
+ ```
71
+
72
+ Then, downoad the individual model file the a local directory
73
+
74
+ ```shell
75
+ huggingface-cli download tensorblock/KoSOLAR-10.9B-v0.5-GGUF --include "KoSOLAR-10.9B-v0.5-Q2_K.gguf" --local-dir MY_LOCAL_DIR
76
+ ```
77
+
78
+ If you wanna download multiple model files with a pattern (e.g., `*Q4_K*gguf`), you can try:
79
+
80
+ ```shell
81
+ huggingface-cli download tensorblock/KoSOLAR-10.9B-v0.5-GGUF --local-dir MY_LOCAL_DIR --local-dir-use-symlinks False --include='*Q4_K*gguf'
82
+ ```