Hugging Face's logo

tensorblock
/
hk-SOLAR-10.7B-v2.0-GGUF

Transformers
GGUF
Korean
TensorBlock
GGUF
Inference Endpoints
conversational
Model card Files Community
morriszms commited on
Commit
27d2314
·
verified ·
1 Parent(s): 8b89dc6

Upload folder using huggingface_hub

Browse files
Files changed (14) hide show
  1. .gitattributes +12 -0
  2. README.md +83 -0
  3. hk-SOLAR-10.7B-v2.0-Q2_K.gguf +3 -0
  4. hk-SOLAR-10.7B-v2.0-Q3_K_L.gguf +3 -0
  5. hk-SOLAR-10.7B-v2.0-Q3_K_M.gguf +3 -0
  6. hk-SOLAR-10.7B-v2.0-Q3_K_S.gguf +3 -0
  7. hk-SOLAR-10.7B-v2.0-Q4_0.gguf +3 -0
  8. hk-SOLAR-10.7B-v2.0-Q4_K_M.gguf +3 -0
  9. hk-SOLAR-10.7B-v2.0-Q4_K_S.gguf +3 -0
  10. hk-SOLAR-10.7B-v2.0-Q5_0.gguf +3 -0
  11. hk-SOLAR-10.7B-v2.0-Q5_K_M.gguf +3 -0
  12. hk-SOLAR-10.7B-v2.0-Q5_K_S.gguf +3 -0
  13. hk-SOLAR-10.7B-v2.0-Q6_K.gguf +3 -0
  14. hk-SOLAR-10.7B-v2.0-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
+ hk-SOLAR-10.7B-v2.0-Q2_K.gguf filter=lfs diff=lfs merge=lfs -text
37
+ hk-SOLAR-10.7B-v2.0-Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text
38
+ hk-SOLAR-10.7B-v2.0-Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text
39
+ hk-SOLAR-10.7B-v2.0-Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text
40
+ hk-SOLAR-10.7B-v2.0-Q4_0.gguf filter=lfs diff=lfs merge=lfs -text
41
+ hk-SOLAR-10.7B-v2.0-Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text
42
+ hk-SOLAR-10.7B-v2.0-Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text
43
+ hk-SOLAR-10.7B-v2.0-Q5_0.gguf filter=lfs diff=lfs merge=lfs -text
44
+ hk-SOLAR-10.7B-v2.0-Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text
45
+ hk-SOLAR-10.7B-v2.0-Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text
46
+ hk-SOLAR-10.7B-v2.0-Q6_K.gguf filter=lfs diff=lfs merge=lfs -text
47
+ hk-SOLAR-10.7B-v2.0-Q8_0.gguf filter=lfs diff=lfs merge=lfs -text
README.md ADDED
@@ -0,0 +1,83 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ library_name: transformers
3
+ license: apache-2.0
4
+ language:
5
+ - ko
6
+ base_model: hkss/hk-SOLAR-10.7B-v2.0
7
+ tags:
8
+ - TensorBlock
9
+ - GGUF
10
+ ---
11
+
12
+ <div style="width: auto; margin-left: auto; margin-right: auto">
13
+ <img src="https://i.imgur.com/jC7kdl8.jpeg" alt="TensorBlock" style="width: 100%; min-width: 400px; display: block; margin: auto;">
14
+ </div>
15
+ <div style="display: flex; justify-content: space-between; width: 100%;">
16
+ <div style="display: flex; flex-direction: column; align-items: flex-start;">
17
+ <p style="margin-top: 0.5em; margin-bottom: 0em;">
18
+ 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>
19
+ </p>
20
+ </div>
21
+ </div>
22
+
23
+ ## hkss/hk-SOLAR-10.7B-v2.0 - GGUF
24
+
25
+ This repo contains GGUF format model files for [hkss/hk-SOLAR-10.7B-v2.0](https://huggingface.co/hkss/hk-SOLAR-10.7B-v2.0).
26
+
27
+ 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).
28
+
29
+ <div style="text-align: left; margin: 20px 0;">
30
+ <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;">
31
+ Run them on the TensorBlock client using your local machine ↗
32
+ </a>
33
+ </div>
34
+
35
+ ## Prompt template
36
+
37
+ ```
38
+ <|im_start|>system
39
+ {system_prompt}<|im_end|>
40
+ <|im_start|>user
41
+ {prompt}<|im_end|>
42
+ <|im_start|>assistant
43
+ ```
44
+
45
+ ## Model file specification
46
+
47
+ | Filename | Quant type | File Size | Description |
48
+ | -------- | ---------- | --------- | ----------- |
49
+ | [hk-SOLAR-10.7B-v2.0-Q2_K.gguf](https://huggingface.co/tensorblock/hk-SOLAR-10.7B-v2.0-GGUF/blob/main/hk-SOLAR-10.7B-v2.0-Q2_K.gguf) | Q2_K | 3.768 GB | smallest, significant quality loss - not recommended for most purposes |
50
+ | [hk-SOLAR-10.7B-v2.0-Q3_K_S.gguf](https://huggingface.co/tensorblock/hk-SOLAR-10.7B-v2.0-GGUF/blob/main/hk-SOLAR-10.7B-v2.0-Q3_K_S.gguf) | Q3_K_S | 4.387 GB | very small, high quality loss |
51
+ | [hk-SOLAR-10.7B-v2.0-Q3_K_M.gguf](https://huggingface.co/tensorblock/hk-SOLAR-10.7B-v2.0-GGUF/blob/main/hk-SOLAR-10.7B-v2.0-Q3_K_M.gguf) | Q3_K_M | 4.882 GB | very small, high quality loss |
52
+ | [hk-SOLAR-10.7B-v2.0-Q3_K_L.gguf](https://huggingface.co/tensorblock/hk-SOLAR-10.7B-v2.0-GGUF/blob/main/hk-SOLAR-10.7B-v2.0-Q3_K_L.gguf) | Q3_K_L | 5.306 GB | small, substantial quality loss |
53
+ | [hk-SOLAR-10.7B-v2.0-Q4_0.gguf](https://huggingface.co/tensorblock/hk-SOLAR-10.7B-v2.0-GGUF/blob/main/hk-SOLAR-10.7B-v2.0-Q4_0.gguf) | Q4_0 | 5.703 GB | legacy; small, very high quality loss - prefer using Q3_K_M |
54
+ | [hk-SOLAR-10.7B-v2.0-Q4_K_S.gguf](https://huggingface.co/tensorblock/hk-SOLAR-10.7B-v2.0-GGUF/blob/main/hk-SOLAR-10.7B-v2.0-Q4_K_S.gguf) | Q4_K_S | 5.746 GB | small, greater quality loss |
55
+ | [hk-SOLAR-10.7B-v2.0-Q4_K_M.gguf](https://huggingface.co/tensorblock/hk-SOLAR-10.7B-v2.0-GGUF/blob/main/hk-SOLAR-10.7B-v2.0-Q4_K_M.gguf) | Q4_K_M | 6.065 GB | medium, balanced quality - recommended |
56
+ | [hk-SOLAR-10.7B-v2.0-Q5_0.gguf](https://huggingface.co/tensorblock/hk-SOLAR-10.7B-v2.0-GGUF/blob/main/hk-SOLAR-10.7B-v2.0-Q5_0.gguf) | Q5_0 | 6.941 GB | legacy; medium, balanced quality - prefer using Q4_K_M |
57
+ | [hk-SOLAR-10.7B-v2.0-Q5_K_S.gguf](https://huggingface.co/tensorblock/hk-SOLAR-10.7B-v2.0-GGUF/blob/main/hk-SOLAR-10.7B-v2.0-Q5_K_S.gguf) | Q5_K_S | 6.941 GB | large, low quality loss - recommended |
58
+ | [hk-SOLAR-10.7B-v2.0-Q5_K_M.gguf](https://huggingface.co/tensorblock/hk-SOLAR-10.7B-v2.0-GGUF/blob/main/hk-SOLAR-10.7B-v2.0-Q5_K_M.gguf) | Q5_K_M | 7.128 GB | large, very low quality loss - recommended |
59
+ | [hk-SOLAR-10.7B-v2.0-Q6_K.gguf](https://huggingface.co/tensorblock/hk-SOLAR-10.7B-v2.0-GGUF/blob/main/hk-SOLAR-10.7B-v2.0-Q6_K.gguf) | Q6_K | 8.257 GB | very large, extremely low quality loss |
60
+ | [hk-SOLAR-10.7B-v2.0-Q8_0.gguf](https://huggingface.co/tensorblock/hk-SOLAR-10.7B-v2.0-GGUF/blob/main/hk-SOLAR-10.7B-v2.0-Q8_0.gguf) | Q8_0 | 10.694 GB | very large, extremely low quality loss - not recommended |
61
+
62
+
63
+ ## Downloading instruction
64
+
65
+ ### Command line
66
+
67
+ Firstly, install Huggingface Client
68
+
69
+ ```shell
70
+ pip install -U "huggingface_hub[cli]"
71
+ ```
72
+
73
+ Then, downoad the individual model file the a local directory
74
+
75
+ ```shell
76
+ huggingface-cli download tensorblock/hk-SOLAR-10.7B-v2.0-GGUF --include "hk-SOLAR-10.7B-v2.0-Q2_K.gguf" --local-dir MY_LOCAL_DIR
77
+ ```
78
+
79
+ If you wanna download multiple model files with a pattern (e.g., `*Q4_K*gguf`), you can try:
80
+
81
+ ```shell
82
+ huggingface-cli download tensorblock/hk-SOLAR-10.7B-v2.0-GGUF --local-dir MY_LOCAL_DIR --local-dir-use-symlinks False --include='*Q4_K*gguf'
83
+ ```
hk-SOLAR-10.7B-v2.0-Q2_K.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e55c8f19897c6319c58d6fac52b209adee092aa0a5a7ba3cf89a17562c6084a6
3
+ size 4045598816
hk-SOLAR-10.7B-v2.0-Q3_K_L.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7e31fcb9dbf1bac1f523043c2b7c4261a509d23b313a4bfc2b21085d391b011f
3
+ size 5696843872
hk-SOLAR-10.7B-v2.0-Q3_K_M.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:834c70bf762af483a97cf79cf1d7ced00efc53fdc093cbf0d5ae70c3aa94956e
3
+ size 5241761888
hk-SOLAR-10.7B-v2.0-Q3_K_S.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ff6f6ed12938e6c357e5cd4fa594a67096bd09799aa4774aec183be8fc92331c
3
+ size 4710658144
hk-SOLAR-10.7B-v2.0-Q4_0.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d9f48a86bbe3bfc2536061cedf94fc53345edcda71bf032bf1e06ae66f835050
3
+ size 6123352160
hk-SOLAR-10.7B-v2.0-Q4_K_M.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:372287039f00b35e7002f48bd5c23524e0f8744f65986a9e81f5a5561ec1f631
3
+ size 6512636000
hk-SOLAR-10.7B-v2.0-Q4_K_S.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:94ee95029959fa4fa85cc187d42482d1a3ce166a16b77516bcedd8fd172b7c01
3
+ size 6169489504
hk-SOLAR-10.7B-v2.0-Q5_0.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a00d0b880692b0933abe829a2eda48e1f591524fc458f2ea8a96b3643c6ad168
3
+ size 7452946528
hk-SOLAR-10.7B-v2.0-Q5_K_M.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1439bceafce33e1927e2cb396615c0a1a74884dd91e06c6236411adeec77b6c5
3
+ size 7653486688
hk-SOLAR-10.7B-v2.0-Q5_K_S.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f172963b9ccc4884e1579262966f2a0dd9a9c73cfe6a1063b8465726276172d1
3
+ size 7452946528
hk-SOLAR-10.7B-v2.0-Q6_K.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8e9ebfa4da9cd6c39755fa0e28076ee2d870d430ff6388553b5fbc5ad31e9343
3
+ size 8865640544
hk-SOLAR-10.7B-v2.0-Q8_0.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:225c40b00add96af1647190c29d99e947c6d423456749248abadbf2a6d5a443f
3
+ size 11482361952