Hugging Face's logo

tensorblock
/
AISquare-Instruct-yi-ko-6b-v0.9.30-GGUF

Text Generation
GGUF
English
TensorBlock
GGUF
Inference Endpoints
Model card Files Community
morriszms commited on
Commit
630b1af
•
1 Parent(s): 24bcb15

Upload folder using huggingface_hub

Browse files
Files changed (14) hide show
  1. .gitattributes +12 -0
  2. AISquare-Instruct-yi-ko-6b-v0.9.30-Q2_K.gguf +3 -0
  3. AISquare-Instruct-yi-ko-6b-v0.9.30-Q3_K_L.gguf +3 -0
  4. AISquare-Instruct-yi-ko-6b-v0.9.30-Q3_K_M.gguf +3 -0
  5. AISquare-Instruct-yi-ko-6b-v0.9.30-Q3_K_S.gguf +3 -0
  6. AISquare-Instruct-yi-ko-6b-v0.9.30-Q4_0.gguf +3 -0
  7. AISquare-Instruct-yi-ko-6b-v0.9.30-Q4_K_M.gguf +3 -0
  8. AISquare-Instruct-yi-ko-6b-v0.9.30-Q4_K_S.gguf +3 -0
  9. AISquare-Instruct-yi-ko-6b-v0.9.30-Q5_0.gguf +3 -0
  10. AISquare-Instruct-yi-ko-6b-v0.9.30-Q5_K_M.gguf +3 -0
  11. AISquare-Instruct-yi-ko-6b-v0.9.30-Q5_K_S.gguf +3 -0
  12. AISquare-Instruct-yi-ko-6b-v0.9.30-Q6_K.gguf +3 -0
  13. AISquare-Instruct-yi-ko-6b-v0.9.30-Q8_0.gguf +3 -0
  14. README.md +73 -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
+ AISquare-Instruct-yi-ko-6b-v0.9.30-Q2_K.gguf filter=lfs diff=lfs merge=lfs -text
37
+ AISquare-Instruct-yi-ko-6b-v0.9.30-Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text
38
+ AISquare-Instruct-yi-ko-6b-v0.9.30-Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text
39
+ AISquare-Instruct-yi-ko-6b-v0.9.30-Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text
40
+ AISquare-Instruct-yi-ko-6b-v0.9.30-Q4_0.gguf filter=lfs diff=lfs merge=lfs -text
41
+ AISquare-Instruct-yi-ko-6b-v0.9.30-Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text
42
+ AISquare-Instruct-yi-ko-6b-v0.9.30-Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text
43
+ AISquare-Instruct-yi-ko-6b-v0.9.30-Q5_0.gguf filter=lfs diff=lfs merge=lfs -text
44
+ AISquare-Instruct-yi-ko-6b-v0.9.30-Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text
45
+ AISquare-Instruct-yi-ko-6b-v0.9.30-Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text
46
+ AISquare-Instruct-yi-ko-6b-v0.9.30-Q6_K.gguf filter=lfs diff=lfs merge=lfs -text
47
+ AISquare-Instruct-yi-ko-6b-v0.9.30-Q8_0.gguf filter=lfs diff=lfs merge=lfs -text
AISquare-Instruct-yi-ko-6b-v0.9.30-Q2_K.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5160e6eaf8e4a94b1dd9e370f942cf4765bdbba256e3727beda518a4f4bddc33
3
+ size 2405459968
AISquare-Instruct-yi-ko-6b-v0.9.30-Q3_K_L.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c3cc916d680d21027d88c0d69541ec8fbdbf14d738510d16abbcc29abcc36e33
3
+ size 3311302656
AISquare-Instruct-yi-ko-6b-v0.9.30-Q3_K_M.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b72ca4b696fcad444431cd874ae96619bc58085d7b840cc3247fe71305b4f09a
3
+ size 3067246592
AISquare-Instruct-yi-ko-6b-v0.9.30-Q3_K_S.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:aa643c5b7cd0d9dedbc9abd74ad797d17f7f9b2ad476d899b83c1fde9f57570b
3
+ size 2783606784
AISquare-Instruct-yi-ko-6b-v0.9.30-Q4_0.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:888e7151d44ab45e04253c117cd8dad2f0c4e4122b4ed0e4243c1010aaba5cbe
3
+ size 3561605120
AISquare-Instruct-yi-ko-6b-v0.9.30-Q4_K_M.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7fb6788418810a3e28bb8784b79d9819627e25b56d987a60ded7ddf5e2753355
3
+ size 3756247040
AISquare-Instruct-yi-ko-6b-v0.9.30-Q4_K_S.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b31cccf1a9940304ce7a6d5e61ca287b4340c82597e14c30fbe6028ce449e2df
3
+ size 3585198080
AISquare-Instruct-yi-ko-6b-v0.9.30-Q5_0.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b3dc757cd1b110dfda948ce10fea15989c1a32c29509047a525f8f883eea8a1d
3
+ size 4293838848
AISquare-Instruct-yi-ko-6b-v0.9.30-Q5_K_M.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bd38a75095363e9974516aa8118e6d04d2769b0d5f8a765acb0c3cfc09ff9466
3
+ size 4394108928
AISquare-Instruct-yi-ko-6b-v0.9.30-Q5_K_S.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e96f662d0c9a396080b5865107f72cd1ae6f3e3228d401295f8ef1dc68bad1fa
3
+ size 4293838848
AISquare-Instruct-yi-ko-6b-v0.9.30-Q6_K.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:eca062e77d7de18d4d0c25fac19f75f1b7e38e5fb5d3db599b03f35a98259dd7
3
+ size 5071837184
AISquare-Instruct-yi-ko-6b-v0.9.30-Q8_0.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:09f5c28867c30a853c1c4a5d5e3e9aa8d3665fad298daa52090746228f9fe02c
3
+ size 6568376320
README.md ADDED
@@ -0,0 +1,73 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ language:
3
+ - en
4
+ pipeline_tag: text-generation
5
+ license: cc-by-nc-4.0
6
+ tags:
7
+ - TensorBlock
8
+ - GGUF
9
+ base_model: zomd/AISquare-Instruct-yi-ko-6b-v0.9.30
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
+ ## zomd/AISquare-Instruct-yi-ko-6b-v0.9.30 - GGUF
24
+
25
+ This repo contains GGUF format model files for [zomd/AISquare-Instruct-yi-ko-6b-v0.9.30](https://huggingface.co/zomd/AISquare-Instruct-yi-ko-6b-v0.9.30).
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
+ ## Prompt template
30
+
31
+ ```
32
+
33
+ ```
34
+
35
+ ## Model file specification
36
+
37
+ | Filename | Quant type | File Size | Description |
38
+ | -------- | ---------- | --------- | ----------- |
39
+ | [AISquare-Instruct-yi-ko-6b-v0.9.30-Q2_K.gguf](https://huggingface.co/tensorblock/AISquare-Instruct-yi-ko-6b-v0.9.30-GGUF/tree/main/AISquare-Instruct-yi-ko-6b-v0.9.30-Q2_K.gguf) | Q2_K | 2.240 GB | smallest, significant quality loss - not recommended for most purposes |
40
+ | [AISquare-Instruct-yi-ko-6b-v0.9.30-Q3_K_S.gguf](https://huggingface.co/tensorblock/AISquare-Instruct-yi-ko-6b-v0.9.30-GGUF/tree/main/AISquare-Instruct-yi-ko-6b-v0.9.30-Q3_K_S.gguf) | Q3_K_S | 2.592 GB | very small, high quality loss |
41
+ | [AISquare-Instruct-yi-ko-6b-v0.9.30-Q3_K_M.gguf](https://huggingface.co/tensorblock/AISquare-Instruct-yi-ko-6b-v0.9.30-GGUF/tree/main/AISquare-Instruct-yi-ko-6b-v0.9.30-Q3_K_M.gguf) | Q3_K_M | 2.857 GB | very small, high quality loss |
42
+ | [AISquare-Instruct-yi-ko-6b-v0.9.30-Q3_K_L.gguf](https://huggingface.co/tensorblock/AISquare-Instruct-yi-ko-6b-v0.9.30-GGUF/tree/main/AISquare-Instruct-yi-ko-6b-v0.9.30-Q3_K_L.gguf) | Q3_K_L | 3.084 GB | small, substantial quality loss |
43
+ | [AISquare-Instruct-yi-ko-6b-v0.9.30-Q4_0.gguf](https://huggingface.co/tensorblock/AISquare-Instruct-yi-ko-6b-v0.9.30-GGUF/tree/main/AISquare-Instruct-yi-ko-6b-v0.9.30-Q4_0.gguf) | Q4_0 | 3.317 GB | legacy; small, very high quality loss - prefer using Q3_K_M |
44
+ | [AISquare-Instruct-yi-ko-6b-v0.9.30-Q4_K_S.gguf](https://huggingface.co/tensorblock/AISquare-Instruct-yi-ko-6b-v0.9.30-GGUF/tree/main/AISquare-Instruct-yi-ko-6b-v0.9.30-Q4_K_S.gguf) | Q4_K_S | 3.339 GB | small, greater quality loss |
45
+ | [AISquare-Instruct-yi-ko-6b-v0.9.30-Q4_K_M.gguf](https://huggingface.co/tensorblock/AISquare-Instruct-yi-ko-6b-v0.9.30-GGUF/tree/main/AISquare-Instruct-yi-ko-6b-v0.9.30-Q4_K_M.gguf) | Q4_K_M | 3.498 GB | medium, balanced quality - recommended |
46
+ | [AISquare-Instruct-yi-ko-6b-v0.9.30-Q5_0.gguf](https://huggingface.co/tensorblock/AISquare-Instruct-yi-ko-6b-v0.9.30-GGUF/tree/main/AISquare-Instruct-yi-ko-6b-v0.9.30-Q5_0.gguf) | Q5_0 | 3.999 GB | legacy; medium, balanced quality - prefer using Q4_K_M |
47
+ | [AISquare-Instruct-yi-ko-6b-v0.9.30-Q5_K_S.gguf](https://huggingface.co/tensorblock/AISquare-Instruct-yi-ko-6b-v0.9.30-GGUF/tree/main/AISquare-Instruct-yi-ko-6b-v0.9.30-Q5_K_S.gguf) | Q5_K_S | 3.999 GB | large, low quality loss - recommended |
48
+ | [AISquare-Instruct-yi-ko-6b-v0.9.30-Q5_K_M.gguf](https://huggingface.co/tensorblock/AISquare-Instruct-yi-ko-6b-v0.9.30-GGUF/tree/main/AISquare-Instruct-yi-ko-6b-v0.9.30-Q5_K_M.gguf) | Q5_K_M | 4.092 GB | large, very low quality loss - recommended |
49
+ | [AISquare-Instruct-yi-ko-6b-v0.9.30-Q6_K.gguf](https://huggingface.co/tensorblock/AISquare-Instruct-yi-ko-6b-v0.9.30-GGUF/tree/main/AISquare-Instruct-yi-ko-6b-v0.9.30-Q6_K.gguf) | Q6_K | 4.724 GB | very large, extremely low quality loss |
50
+ | [AISquare-Instruct-yi-ko-6b-v0.9.30-Q8_0.gguf](https://huggingface.co/tensorblock/AISquare-Instruct-yi-ko-6b-v0.9.30-GGUF/tree/main/AISquare-Instruct-yi-ko-6b-v0.9.30-Q8_0.gguf) | Q8_0 | 6.117 GB | very large, extremely low quality loss - not recommended |
51
+
52
+
53
+ ## Downloading instruction
54
+
55
+ ### Command line
56
+
57
+ Firstly, install Huggingface Client
58
+
59
+ ```shell
60
+ pip install -U "huggingface_hub[cli]"
61
+ ```
62
+
63
+ Then, downoad the individual model file the a local directory
64
+
65
+ ```shell
66
+ huggingface-cli download tensorblock/AISquare-Instruct-yi-ko-6b-v0.9.30-GGUF --include "AISquare-Instruct-yi-ko-6b-v0.9.30-Q2_K.gguf" --local-dir MY_LOCAL_DIR
67
+ ```
68
+
69
+ If you wanna download multiple model files with a pattern (e.g., `*Q4_K*gguf`), you can try:
70
+
71
+ ```shell
72
+ huggingface-cli download tensorblock/AISquare-Instruct-yi-ko-6b-v0.9.30-GGUF --local-dir MY_LOCAL_DIR --local-dir-use-symlinks False --include='*Q4_K*gguf'
73
+ ```