Hugging Face's logo

tensorblock
/
kullm-mistral-S-GGUF

GGUF
Korean
TensorBlock
GGUF
conversational
Model card Files
xet
 Community
morriszms commited on
Commit
1a5c085
·
verified ·
1 Parent(s): 463acb0

Upload folder using huggingface_hub

Browse files
Files changed (14) hide show
  1. .gitattributes +12 -0
  2. README.md +78 -0
  3. kullm-mistral-S-Q2_K.gguf +3 -0
  4. kullm-mistral-S-Q3_K_L.gguf +3 -0
  5. kullm-mistral-S-Q3_K_M.gguf +3 -0
  6. kullm-mistral-S-Q3_K_S.gguf +3 -0
  7. kullm-mistral-S-Q4_0.gguf +3 -0
  8. kullm-mistral-S-Q4_K_M.gguf +3 -0
  9. kullm-mistral-S-Q4_K_S.gguf +3 -0
  10. kullm-mistral-S-Q5_0.gguf +3 -0
  11. kullm-mistral-S-Q5_K_M.gguf +3 -0
  12. kullm-mistral-S-Q5_K_S.gguf +3 -0
  13. kullm-mistral-S-Q6_K.gguf +3 -0
  14. kullm-mistral-S-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
+ kullm-mistral-S-Q2_K.gguf filter=lfs diff=lfs merge=lfs -text
37
+ kullm-mistral-S-Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text
38
+ kullm-mistral-S-Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text
39
+ kullm-mistral-S-Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text
40
+ kullm-mistral-S-Q4_0.gguf filter=lfs diff=lfs merge=lfs -text
41
+ kullm-mistral-S-Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text
42
+ kullm-mistral-S-Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text
43
+ kullm-mistral-S-Q5_0.gguf filter=lfs diff=lfs merge=lfs -text
44
+ kullm-mistral-S-Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text
45
+ kullm-mistral-S-Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text
46
+ kullm-mistral-S-Q6_K.gguf filter=lfs diff=lfs merge=lfs -text
47
+ kullm-mistral-S-Q8_0.gguf filter=lfs diff=lfs merge=lfs -text
README.md ADDED
@@ -0,0 +1,78 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ license: apache-2.0
3
+ language:
4
+ - ko
5
+ base_model: heavytail/kullm-mistral-S
6
+ tags:
7
+ - TensorBlock
8
+ - GGUF
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
+ ## heavytail/kullm-mistral-S - GGUF
23
+
24
+ This repo contains GGUF format model files for [heavytail/kullm-mistral-S](https://huggingface.co/heavytail/kullm-mistral-S).
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
+ <s>[INST] {prompt} [/INST]
38
+ ```
39
+
40
+ ## Model file specification
41
+
42
+ | Filename | Quant type | File Size | Description |
43
+ | -------- | ---------- | --------- | ----------- |
44
+ | [kullm-mistral-S-Q2_K.gguf](https://huggingface.co/tensorblock/kullm-mistral-S-GGUF/blob/main/kullm-mistral-S-Q2_K.gguf) | Q2_K | 2.532 GB | smallest, significant quality loss - not recommended for most purposes |
45
+ | [kullm-mistral-S-Q3_K_S.gguf](https://huggingface.co/tensorblock/kullm-mistral-S-GGUF/blob/main/kullm-mistral-S-Q3_K_S.gguf) | Q3_K_S | 2.947 GB | very small, high quality loss |
46
+ | [kullm-mistral-S-Q3_K_M.gguf](https://huggingface.co/tensorblock/kullm-mistral-S-GGUF/blob/main/kullm-mistral-S-Q3_K_M.gguf) | Q3_K_M | 3.277 GB | very small, high quality loss |
47
+ | [kullm-mistral-S-Q3_K_L.gguf](https://huggingface.co/tensorblock/kullm-mistral-S-GGUF/blob/main/kullm-mistral-S-Q3_K_L.gguf) | Q3_K_L | 3.560 GB | small, substantial quality loss |
48
+ | [kullm-mistral-S-Q4_0.gguf](https://huggingface.co/tensorblock/kullm-mistral-S-GGUF/blob/main/kullm-mistral-S-Q4_0.gguf) | Q4_0 | 3.827 GB | legacy; small, very high quality loss - prefer using Q3_K_M |
49
+ | [kullm-mistral-S-Q4_K_S.gguf](https://huggingface.co/tensorblock/kullm-mistral-S-GGUF/blob/main/kullm-mistral-S-Q4_K_S.gguf) | Q4_K_S | 3.856 GB | small, greater quality loss |
50
+ | [kullm-mistral-S-Q4_K_M.gguf](https://huggingface.co/tensorblock/kullm-mistral-S-GGUF/blob/main/kullm-mistral-S-Q4_K_M.gguf) | Q4_K_M | 4.068 GB | medium, balanced quality - recommended |
51
+ | [kullm-mistral-S-Q5_0.gguf](https://huggingface.co/tensorblock/kullm-mistral-S-GGUF/blob/main/kullm-mistral-S-Q5_0.gguf) | Q5_0 | 4.654 GB | legacy; medium, balanced quality - prefer using Q4_K_M |
52
+ | [kullm-mistral-S-Q5_K_S.gguf](https://huggingface.co/tensorblock/kullm-mistral-S-GGUF/blob/main/kullm-mistral-S-Q5_K_S.gguf) | Q5_K_S | 4.654 GB | large, low quality loss - recommended |
53
+ | [kullm-mistral-S-Q5_K_M.gguf](https://huggingface.co/tensorblock/kullm-mistral-S-GGUF/blob/main/kullm-mistral-S-Q5_K_M.gguf) | Q5_K_M | 4.779 GB | large, very low quality loss - recommended |
54
+ | [kullm-mistral-S-Q6_K.gguf](https://huggingface.co/tensorblock/kullm-mistral-S-GGUF/blob/main/kullm-mistral-S-Q6_K.gguf) | Q6_K | 5.534 GB | very large, extremely low quality loss |
55
+ | [kullm-mistral-S-Q8_0.gguf](https://huggingface.co/tensorblock/kullm-mistral-S-GGUF/blob/main/kullm-mistral-S-Q8_0.gguf) | Q8_0 | 7.167 GB | very large, extremely low quality loss - not recommended |
56
+
57
+
58
+ ## Downloading instruction
59
+
60
+ ### Command line
61
+
62
+ Firstly, install Huggingface Client
63
+
64
+ ```shell
65
+ pip install -U "huggingface_hub[cli]"
66
+ ```
67
+
68
+ Then, downoad the individual model file the a local directory
69
+
70
+ ```shell
71
+ huggingface-cli download tensorblock/kullm-mistral-S-GGUF --include "kullm-mistral-S-Q2_K.gguf" --local-dir MY_LOCAL_DIR
72
+ ```
73
+
74
+ If you wanna download multiple model files with a pattern (e.g., `*Q4_K*gguf`), you can try:
75
+
76
+ ```shell
77
+ huggingface-cli download tensorblock/kullm-mistral-S-GGUF --local-dir MY_LOCAL_DIR --local-dir-use-symlinks False --include='*Q4_K*gguf'
78
+ ```
kullm-mistral-S-Q2_K.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2b27bdf3349c4ff02121252343a1210707f8dc636b88ea907cfaaa829b3ad70f
3
+ size 2719242880
kullm-mistral-S-Q3_K_L.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bcec70b4b59c6600a689410c58a9a725638bd5218da71730fffd46bd0c744a5d
3
+ size 3822025344
kullm-mistral-S-Q3_K_M.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:468e132dd294106f330a0d125f7ccc8b5d97d949b192d25aea53bf6e5602aa2e
3
+ size 3518986880
kullm-mistral-S-Q3_K_S.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:94065896112c2f71d093321c5817a66f1cdc7f7fdec84680655f67d8907b2edb
3
+ size 3164568192
kullm-mistral-S-Q4_0.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2f6a2512577f0a783bb8990e071f047050f3e924e7c07c85f037dc6635071472
3
+ size 4108917376
kullm-mistral-S-Q4_K_M.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:74fe98db51e8130b491ec65dbbf96b41919367a02c079192279995864a4df6c3
3
+ size 4368439936
kullm-mistral-S-Q4_K_S.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4f0f381e0b49be41f72429d6c5e8647e391b8d2ea4da0374fb5fde75d653a729
3
+ size 4140374656
kullm-mistral-S-Q5_0.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0c8522ace261845465421970a0c490b78d9c7cc83add9ca2dd3aafc4041d3c3e
3
+ size 4997716608
kullm-mistral-S-Q5_K_M.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cccd596cab8f572d100c44e38f64f163442bcf5382703404716577120d25614b
3
+ size 5131410048
kullm-mistral-S-Q5_K_S.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6c82ec9423bc33f123ed9e138a396c2da62b378523bbdfc993e006271c87288d
3
+ size 4997716608
kullm-mistral-S-Q6_K.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f6ced8cbd87bd8073cbeb7f6716708092d23d6f47130e4e7e13523d091c8baa7
3
+ size 5942065792
kullm-mistral-S-Q8_0.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fa3c0a3080624ceca46570401ceb6c226a6bbf17212c3f5ec5c01c6781a6f565
3
+ size 7695858304