Hugging Face's logo

tensorblock
/
malaysian-mistral-7b-32k-instructions-v4-GGUF

GGUF
Malay
TensorBlock
GGUF
Inference Endpoints
conversational
Model card Files Community
morriszms commited on
Commit
9375457
·
verified ·
1 Parent(s): a30c805

Upload folder using huggingface_hub

Browse files
Files changed (14) hide show
  1. .gitattributes +12 -0
  2. README.md +77 -0
  3. malaysian-mistral-7b-32k-instructions-v4-Q2_K.gguf +3 -0
  4. malaysian-mistral-7b-32k-instructions-v4-Q3_K_L.gguf +3 -0
  5. malaysian-mistral-7b-32k-instructions-v4-Q3_K_M.gguf +3 -0
  6. malaysian-mistral-7b-32k-instructions-v4-Q3_K_S.gguf +3 -0
  7. malaysian-mistral-7b-32k-instructions-v4-Q4_0.gguf +3 -0
  8. malaysian-mistral-7b-32k-instructions-v4-Q4_K_M.gguf +3 -0
  9. malaysian-mistral-7b-32k-instructions-v4-Q4_K_S.gguf +3 -0
  10. malaysian-mistral-7b-32k-instructions-v4-Q5_0.gguf +3 -0
  11. malaysian-mistral-7b-32k-instructions-v4-Q5_K_M.gguf +3 -0
  12. malaysian-mistral-7b-32k-instructions-v4-Q5_K_S.gguf +3 -0
  13. malaysian-mistral-7b-32k-instructions-v4-Q6_K.gguf +3 -0
  14. malaysian-mistral-7b-32k-instructions-v4-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
+ malaysian-mistral-7b-32k-instructions-v4-Q2_K.gguf filter=lfs diff=lfs merge=lfs -text
37
+ malaysian-mistral-7b-32k-instructions-v4-Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text
38
+ malaysian-mistral-7b-32k-instructions-v4-Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text
39
+ malaysian-mistral-7b-32k-instructions-v4-Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text
40
+ malaysian-mistral-7b-32k-instructions-v4-Q4_0.gguf filter=lfs diff=lfs merge=lfs -text
41
+ malaysian-mistral-7b-32k-instructions-v4-Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text
42
+ malaysian-mistral-7b-32k-instructions-v4-Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text
43
+ malaysian-mistral-7b-32k-instructions-v4-Q5_0.gguf filter=lfs diff=lfs merge=lfs -text
44
+ malaysian-mistral-7b-32k-instructions-v4-Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text
45
+ malaysian-mistral-7b-32k-instructions-v4-Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text
46
+ malaysian-mistral-7b-32k-instructions-v4-Q6_K.gguf filter=lfs diff=lfs merge=lfs -text
47
+ malaysian-mistral-7b-32k-instructions-v4-Q8_0.gguf filter=lfs diff=lfs merge=lfs -text
README.md ADDED
@@ -0,0 +1,77 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ language:
3
+ - ms
4
+ base_model: mesolitica/malaysian-mistral-7b-32k-instructions-v4
5
+ tags:
6
+ - TensorBlock
7
+ - GGUF
8
+ ---
9
+
10
+ <div style="width: auto; margin-left: auto; margin-right: auto">
11
+ <img src="https://i.imgur.com/jC7kdl8.jpeg" alt="TensorBlock" style="width: 100%; min-width: 400px; display: block; margin: auto;">
12
+ </div>
13
+ <div style="display: flex; justify-content: space-between; width: 100%;">
14
+ <div style="display: flex; flex-direction: column; align-items: flex-start;">
15
+ <p style="margin-top: 0.5em; margin-bottom: 0em;">
16
+ 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>
17
+ </p>
18
+ </div>
19
+ </div>
20
+
21
+ ## mesolitica/malaysian-mistral-7b-32k-instructions-v4 - GGUF
22
+
23
+ This repo contains GGUF format model files for [mesolitica/malaysian-mistral-7b-32k-instructions-v4](https://huggingface.co/mesolitica/malaysian-mistral-7b-32k-instructions-v4).
24
+
25
+ The files were quantized using machines provided by [TensorBlock](https://tensorblock.co/), and they are compatible with llama.cpp as of [commit b4242](https://github.com/ggerganov/llama.cpp/commit/a6744e43e80f4be6398fc7733a01642c846dce1d).
26
+
27
+ <div style="text-align: left; margin: 20px 0;">
28
+ <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;">
29
+ Run them on the TensorBlock client using your local machine ↗
30
+ </a>
31
+ </div>
32
+
33
+ ## Prompt template
34
+
35
+ ```
36
+ <s>[INST] {prompt} [/INST]
37
+ ```
38
+
39
+ ## Model file specification
40
+
41
+ | Filename | Quant type | File Size | Description |
42
+ | -------- | ---------- | --------- | ----------- |
43
+ | [malaysian-mistral-7b-32k-instructions-v4-Q2_K.gguf](https://huggingface.co/tensorblock/malaysian-mistral-7b-32k-instructions-v4-GGUF/blob/main/malaysian-mistral-7b-32k-instructions-v4-Q2_K.gguf) | Q2_K | 2.719 GB | smallest, significant quality loss - not recommended for most purposes |
44
+ | [malaysian-mistral-7b-32k-instructions-v4-Q3_K_S.gguf](https://huggingface.co/tensorblock/malaysian-mistral-7b-32k-instructions-v4-GGUF/blob/main/malaysian-mistral-7b-32k-instructions-v4-Q3_K_S.gguf) | Q3_K_S | 3.165 GB | very small, high quality loss |
45
+ | [malaysian-mistral-7b-32k-instructions-v4-Q3_K_M.gguf](https://huggingface.co/tensorblock/malaysian-mistral-7b-32k-instructions-v4-GGUF/blob/main/malaysian-mistral-7b-32k-instructions-v4-Q3_K_M.gguf) | Q3_K_M | 3.519 GB | very small, high quality loss |
46
+ | [malaysian-mistral-7b-32k-instructions-v4-Q3_K_L.gguf](https://huggingface.co/tensorblock/malaysian-mistral-7b-32k-instructions-v4-GGUF/blob/main/malaysian-mistral-7b-32k-instructions-v4-Q3_K_L.gguf) | Q3_K_L | 3.822 GB | small, substantial quality loss |
47
+ | [malaysian-mistral-7b-32k-instructions-v4-Q4_0.gguf](https://huggingface.co/tensorblock/malaysian-mistral-7b-32k-instructions-v4-GGUF/blob/main/malaysian-mistral-7b-32k-instructions-v4-Q4_0.gguf) | Q4_0 | 4.109 GB | legacy; small, very high quality loss - prefer using Q3_K_M |
48
+ | [malaysian-mistral-7b-32k-instructions-v4-Q4_K_S.gguf](https://huggingface.co/tensorblock/malaysian-mistral-7b-32k-instructions-v4-GGUF/blob/main/malaysian-mistral-7b-32k-instructions-v4-Q4_K_S.gguf) | Q4_K_S | 4.140 GB | small, greater quality loss |
49
+ | [malaysian-mistral-7b-32k-instructions-v4-Q4_K_M.gguf](https://huggingface.co/tensorblock/malaysian-mistral-7b-32k-instructions-v4-GGUF/blob/main/malaysian-mistral-7b-32k-instructions-v4-Q4_K_M.gguf) | Q4_K_M | 4.368 GB | medium, balanced quality - recommended |
50
+ | [malaysian-mistral-7b-32k-instructions-v4-Q5_0.gguf](https://huggingface.co/tensorblock/malaysian-mistral-7b-32k-instructions-v4-GGUF/blob/main/malaysian-mistral-7b-32k-instructions-v4-Q5_0.gguf) | Q5_0 | 4.998 GB | legacy; medium, balanced quality - prefer using Q4_K_M |
51
+ | [malaysian-mistral-7b-32k-instructions-v4-Q5_K_S.gguf](https://huggingface.co/tensorblock/malaysian-mistral-7b-32k-instructions-v4-GGUF/blob/main/malaysian-mistral-7b-32k-instructions-v4-Q5_K_S.gguf) | Q5_K_S | 4.998 GB | large, low quality loss - recommended |
52
+ | [malaysian-mistral-7b-32k-instructions-v4-Q5_K_M.gguf](https://huggingface.co/tensorblock/malaysian-mistral-7b-32k-instructions-v4-GGUF/blob/main/malaysian-mistral-7b-32k-instructions-v4-Q5_K_M.gguf) | Q5_K_M | 5.131 GB | large, very low quality loss - recommended |
53
+ | [malaysian-mistral-7b-32k-instructions-v4-Q6_K.gguf](https://huggingface.co/tensorblock/malaysian-mistral-7b-32k-instructions-v4-GGUF/blob/main/malaysian-mistral-7b-32k-instructions-v4-Q6_K.gguf) | Q6_K | 5.942 GB | very large, extremely low quality loss |
54
+ | [malaysian-mistral-7b-32k-instructions-v4-Q8_0.gguf](https://huggingface.co/tensorblock/malaysian-mistral-7b-32k-instructions-v4-GGUF/blob/main/malaysian-mistral-7b-32k-instructions-v4-Q8_0.gguf) | Q8_0 | 7.696 GB | very large, extremely low quality loss - not recommended |
55
+
56
+
57
+ ## Downloading instruction
58
+
59
+ ### Command line
60
+
61
+ Firstly, install Huggingface Client
62
+
63
+ ```shell
64
+ pip install -U "huggingface_hub[cli]"
65
+ ```
66
+
67
+ Then, downoad the individual model file the a local directory
68
+
69
+ ```shell
70
+ huggingface-cli download tensorblock/malaysian-mistral-7b-32k-instructions-v4-GGUF --include "malaysian-mistral-7b-32k-instructions-v4-Q2_K.gguf" --local-dir MY_LOCAL_DIR
71
+ ```
72
+
73
+ If you wanna download multiple model files with a pattern (e.g., `*Q4_K*gguf`), you can try:
74
+
75
+ ```shell
76
+ huggingface-cli download tensorblock/malaysian-mistral-7b-32k-instructions-v4-GGUF --local-dir MY_LOCAL_DIR --local-dir-use-symlinks False --include='*Q4_K*gguf'
77
+ ```
malaysian-mistral-7b-32k-instructions-v4-Q2_K.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:aa800566184270741d63a84c9c174a1122609d759ea770a9516944608c92d3d1
3
+ size 2719242912
malaysian-mistral-7b-32k-instructions-v4-Q3_K_L.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ad2812574ac09b64dd7acc9a57a7c599764f797d4f802d55c79ccef6c661f739
3
+ size 3822025376
malaysian-mistral-7b-32k-instructions-v4-Q3_K_M.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e7041ad99b634472ce0cf6e71809b8dc42a664d693c715151b4093f7336f924c
3
+ size 3518986912
malaysian-mistral-7b-32k-instructions-v4-Q3_K_S.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9cf402b0d818de6996737d97f4dcf6c91f93d771580083aa7fe1c5fd1909fad1
3
+ size 3164568224
malaysian-mistral-7b-32k-instructions-v4-Q4_0.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3dfce50fb9e7d7bf27281e861000d6f82e8aaa94e45a77af9a366013d9c62af6
3
+ size 4108917408
malaysian-mistral-7b-32k-instructions-v4-Q4_K_M.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d13f655177bf3d0e27c879bc5bf55d95faadfa52817c2469013a75d21fe57fd2
3
+ size 4368439968
malaysian-mistral-7b-32k-instructions-v4-Q4_K_S.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:dbb9f3680f8c56ec49e32ff1e83711be11c65ea5e1d095261ca6dd0f313e2547
3
+ size 4140374688
malaysian-mistral-7b-32k-instructions-v4-Q5_0.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a4268623bc6354b5bdde83bcb13af1595b2b1f376087bfb3acbfd0ef63db8661
3
+ size 4997716640
malaysian-mistral-7b-32k-instructions-v4-Q5_K_M.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:10fdc22805a657bd1f9ede17c76de5dd378cf3e704eb35f59a0aa5e9bf9ec829
3
+ size 5131410080
malaysian-mistral-7b-32k-instructions-v4-Q5_K_S.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:523706f5d92f337a3bfef8a364f0d722fafd03edadc90a87028df68e6abb395f
3
+ size 4997716640
malaysian-mistral-7b-32k-instructions-v4-Q6_K.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:de80bf304bbb3529dda17059c5c2c8e01ced1015c23b2686d7d60fb149d4c1db
3
+ size 5942065824
malaysian-mistral-7b-32k-instructions-v4-Q8_0.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7b9dcc37df13f9021872f041e43c860e5ce7d4415084ce7d7594b58a119972ca
3
+ size 7695858336