Hugging Face's logo

tensorblock
/
KoSOLAR-10.7B-v1.0-GGUF

Transformers
GGUF
Merge
TensorBlock
GGUF
Inference Endpoints
conversational
Model card Files Community
morriszms commited on
Commit
bfa35be
•
1 Parent(s): 0b6e557

Upload folder using huggingface_hub

Browse files
Files changed (14) hide show
  1. .gitattributes +12 -0
  2. KoSOLAR-10.7B-v1.0-Q2_K.gguf +3 -0
  3. KoSOLAR-10.7B-v1.0-Q3_K_L.gguf +3 -0
  4. KoSOLAR-10.7B-v1.0-Q3_K_M.gguf +3 -0
  5. KoSOLAR-10.7B-v1.0-Q3_K_S.gguf +3 -0
  6. KoSOLAR-10.7B-v1.0-Q4_0.gguf +3 -0
  7. KoSOLAR-10.7B-v1.0-Q4_K_M.gguf +3 -0
  8. KoSOLAR-10.7B-v1.0-Q4_K_S.gguf +3 -0
  9. KoSOLAR-10.7B-v1.0-Q5_0.gguf +3 -0
  10. KoSOLAR-10.7B-v1.0-Q5_K_M.gguf +3 -0
  11. KoSOLAR-10.7B-v1.0-Q5_K_S.gguf +3 -0
  12. KoSOLAR-10.7B-v1.0-Q6_K.gguf +3 -0
  13. KoSOLAR-10.7B-v1.0-Q8_0.gguf +3 -0
  14. README.md +84 -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
+ KoSOLAR-10.7B-v1.0-Q2_K.gguf filter=lfs diff=lfs merge=lfs -text
37
+ KoSOLAR-10.7B-v1.0-Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text
38
+ KoSOLAR-10.7B-v1.0-Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text
39
+ KoSOLAR-10.7B-v1.0-Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text
40
+ KoSOLAR-10.7B-v1.0-Q4_0.gguf filter=lfs diff=lfs merge=lfs -text
41
+ KoSOLAR-10.7B-v1.0-Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text
42
+ KoSOLAR-10.7B-v1.0-Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text
43
+ KoSOLAR-10.7B-v1.0-Q5_0.gguf filter=lfs diff=lfs merge=lfs -text
44
+ KoSOLAR-10.7B-v1.0-Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text
45
+ KoSOLAR-10.7B-v1.0-Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text
46
+ KoSOLAR-10.7B-v1.0-Q6_K.gguf filter=lfs diff=lfs merge=lfs -text
47
+ KoSOLAR-10.7B-v1.0-Q8_0.gguf filter=lfs diff=lfs merge=lfs -text
KoSOLAR-10.7B-v1.0-Q2_K.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f2e3e7b6998645b81ae7e7d084c016a892580cc9acf87fbfa1490f3a6486a969
3
+ size 4003232704
KoSOLAR-10.7B-v1.0-Q3_K_L.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cd317be0af38752edd6f0aa24a5a0f9d7827333ec945dc5217f9f912580de37e
3
+ size 5650750400
KoSOLAR-10.7B-v1.0-Q3_K_M.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c9ec9ae85bd4ec2225a368825ee7eecea16e4856804a6098c3f26619f6aadaca
3
+ size 5195668416
KoSOLAR-10.7B-v1.0-Q3_K_S.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:347f79e399c4491d1c76bd2b9cf94b926fcfba7c8935b2e5430488da36535374
3
+ size 4664564672
KoSOLAR-10.7B-v1.0-Q4_0.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e9799bbf14c470be067b526ec181a3425e5e531bee6f86d313e576ab931607fd
3
+ size 6072384448
KoSOLAR-10.7B-v1.0-Q4_K_M.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7f15f9ce549d23cc9261e091172eec084f0df5e3a99dda1717a2f7737afd6515
3
+ size 6461668288
KoSOLAR-10.7B-v1.0-Q4_K_S.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:93178261343acc5995f98e6dbe164018dc0e3069fd3e3e0f6e115ae38a08904b
3
+ size 6118521792
KoSOLAR-10.7B-v1.0-Q5_0.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2cdb95102ba6ae27fe72a135b9ccd7188ac5a6d8800953f94b63972f37e65456
3
+ size 7397391296
KoSOLAR-10.7B-v1.0-Q5_K_M.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:dd28ac1dd2b9640dc2d090662e8bacd53cc4fd5e07e1764946b99acda896e2ac
3
+ size 7597931456
KoSOLAR-10.7B-v1.0-Q5_K_S.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f05eebda7f285b7c635796757b823d01ef1dcff810bb3f1e81271170b3a0ae73
3
+ size 7397391296
KoSOLAR-10.7B-v1.0-Q6_K.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:07c25db028e27c31e03a01b3ae528c05d971405c74a188dff63babd1c9762e03
3
+ size 8805211072
KoSOLAR-10.7B-v1.0-Q8_0.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:35ba107f2f632493deede45cfc40726c9556ec26fc822185864c899a52d4b1f4
3
+ size 11404155840
README.md ADDED
@@ -0,0 +1,84 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ library_name: transformers
3
+ tags:
4
+ - merge
5
+ - TensorBlock
6
+ - GGUF
7
+ license: apache-2.0
8
+ base_model: rrw-x2/KoSOLAR-10.7B-v1.0
9
+ ---
10
+
11
+ <div style="width: auto; margin-left: auto; margin-right: auto">
12
+ <img src="https://i.imgur.com/jC7kdl8.jpeg" alt="TensorBlock" style="width: 100%; min-width: 400px; display: block; margin: auto;">
13
+ </div>
14
+ <div style="display: flex; justify-content: space-between; width: 100%;">
15
+ <div style="display: flex; flex-direction: column; align-items: flex-start;">
16
+ <p style="margin-top: 0.5em; margin-bottom: 0em;">
17
+ 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>
18
+ </p>
19
+ </div>
20
+ </div>
21
+
22
+ ## rrw-x2/KoSOLAR-10.7B-v1.0 - GGUF
23
+
24
+ This repo contains GGUF format model files for [rrw-x2/KoSOLAR-10.7B-v1.0](https://huggingface.co/rrw-x2/KoSOLAR-10.7B-v1.0).
25
+
26
+ 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).
27
+
28
+ <div style="text-align: left; margin: 20px 0;">
29
+ <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;">
30
+ Run them on the TensorBlock client using your local machine ↗
31
+ </a>
32
+ </div>
33
+
34
+ ## Prompt template
35
+
36
+ ```
37
+ ### System:
38
+ {system_prompt}
39
+
40
+ ### User:
41
+ {prompt}
42
+
43
+ ### Assistant:
44
+ ```
45
+
46
+ ## Model file specification
47
+
48
+ | Filename | Quant type | File Size | Description |
49
+ | -------- | ---------- | --------- | ----------- |
50
+ | [KoSOLAR-10.7B-v1.0-Q2_K.gguf](https://huggingface.co/tensorblock/KoSOLAR-10.7B-v1.0-GGUF/blob/main/KoSOLAR-10.7B-v1.0-Q2_K.gguf) | Q2_K | 3.728 GB | smallest, significant quality loss - not recommended for most purposes |
51
+ | [KoSOLAR-10.7B-v1.0-Q3_K_S.gguf](https://huggingface.co/tensorblock/KoSOLAR-10.7B-v1.0-GGUF/blob/main/KoSOLAR-10.7B-v1.0-Q3_K_S.gguf) | Q3_K_S | 4.344 GB | very small, high quality loss |
52
+ | [KoSOLAR-10.7B-v1.0-Q3_K_M.gguf](https://huggingface.co/tensorblock/KoSOLAR-10.7B-v1.0-GGUF/blob/main/KoSOLAR-10.7B-v1.0-Q3_K_M.gguf) | Q3_K_M | 4.839 GB | very small, high quality loss |
53
+ | [KoSOLAR-10.7B-v1.0-Q3_K_L.gguf](https://huggingface.co/tensorblock/KoSOLAR-10.7B-v1.0-GGUF/blob/main/KoSOLAR-10.7B-v1.0-Q3_K_L.gguf) | Q3_K_L | 5.263 GB | small, substantial quality loss |
54
+ | [KoSOLAR-10.7B-v1.0-Q4_0.gguf](https://huggingface.co/tensorblock/KoSOLAR-10.7B-v1.0-GGUF/blob/main/KoSOLAR-10.7B-v1.0-Q4_0.gguf) | Q4_0 | 5.655 GB | legacy; small, very high quality loss - prefer using Q3_K_M |
55
+ | [KoSOLAR-10.7B-v1.0-Q4_K_S.gguf](https://huggingface.co/tensorblock/KoSOLAR-10.7B-v1.0-GGUF/blob/main/KoSOLAR-10.7B-v1.0-Q4_K_S.gguf) | Q4_K_S | 5.698 GB | small, greater quality loss |
56
+ | [KoSOLAR-10.7B-v1.0-Q4_K_M.gguf](https://huggingface.co/tensorblock/KoSOLAR-10.7B-v1.0-GGUF/blob/main/KoSOLAR-10.7B-v1.0-Q4_K_M.gguf) | Q4_K_M | 6.018 GB | medium, balanced quality - recommended |
57
+ | [KoSOLAR-10.7B-v1.0-Q5_0.gguf](https://huggingface.co/tensorblock/KoSOLAR-10.7B-v1.0-GGUF/blob/main/KoSOLAR-10.7B-v1.0-Q5_0.gguf) | Q5_0 | 6.889 GB | legacy; medium, balanced quality - prefer using Q4_K_M |
58
+ | [KoSOLAR-10.7B-v1.0-Q5_K_S.gguf](https://huggingface.co/tensorblock/KoSOLAR-10.7B-v1.0-GGUF/blob/main/KoSOLAR-10.7B-v1.0-Q5_K_S.gguf) | Q5_K_S | 6.889 GB | large, low quality loss - recommended |
59
+ | [KoSOLAR-10.7B-v1.0-Q5_K_M.gguf](https://huggingface.co/tensorblock/KoSOLAR-10.7B-v1.0-GGUF/blob/main/KoSOLAR-10.7B-v1.0-Q5_K_M.gguf) | Q5_K_M | 7.076 GB | large, very low quality loss - recommended |
60
+ | [KoSOLAR-10.7B-v1.0-Q6_K.gguf](https://huggingface.co/tensorblock/KoSOLAR-10.7B-v1.0-GGUF/blob/main/KoSOLAR-10.7B-v1.0-Q6_K.gguf) | Q6_K | 8.200 GB | very large, extremely low quality loss |
61
+ | [KoSOLAR-10.7B-v1.0-Q8_0.gguf](https://huggingface.co/tensorblock/KoSOLAR-10.7B-v1.0-GGUF/blob/main/KoSOLAR-10.7B-v1.0-Q8_0.gguf) | Q8_0 | 10.621 GB | very large, extremely low quality loss - not recommended |
62
+
63
+
64
+ ## Downloading instruction
65
+
66
+ ### Command line
67
+
68
+ Firstly, install Huggingface Client
69
+
70
+ ```shell
71
+ pip install -U "huggingface_hub[cli]"
72
+ ```
73
+
74
+ Then, downoad the individual model file the a local directory
75
+
76
+ ```shell
77
+ huggingface-cli download tensorblock/KoSOLAR-10.7B-v1.0-GGUF --include "KoSOLAR-10.7B-v1.0-Q2_K.gguf" --local-dir MY_LOCAL_DIR
78
+ ```
79
+
80
+ If you wanna download multiple model files with a pattern (e.g., `*Q4_K*gguf`), you can try:
81
+
82
+ ```shell
83
+ huggingface-cli download tensorblock/KoSOLAR-10.7B-v1.0-GGUF --local-dir MY_LOCAL_DIR --local-dir-use-symlinks False --include='*Q4_K*gguf'
84
+ ```