Hugging Face's logo

tensorblock
/
KONI-Llama3.1-8B-Instruct-20241024-GGUF

Text Generation
GGUF
Korean
TensorBlock
GGUF
conversational
Model card Files
xet
 Community
morriszms commited on
Commit
1b27006
·
verified ·
1 Parent(s): 27f8a66

Upload folder using huggingface_hub

Browse files
Files changed (14) hide show
  1. .gitattributes +12 -0
  2. KONI-Llama3.1-8B-Instruct-20241024-Q2_K.gguf +3 -0
  3. KONI-Llama3.1-8B-Instruct-20241024-Q3_K_L.gguf +3 -0
  4. KONI-Llama3.1-8B-Instruct-20241024-Q3_K_M.gguf +3 -0
  5. KONI-Llama3.1-8B-Instruct-20241024-Q3_K_S.gguf +3 -0
  6. KONI-Llama3.1-8B-Instruct-20241024-Q4_0.gguf +3 -0
  7. KONI-Llama3.1-8B-Instruct-20241024-Q4_K_M.gguf +3 -0
  8. KONI-Llama3.1-8B-Instruct-20241024-Q4_K_S.gguf +3 -0
  9. KONI-Llama3.1-8B-Instruct-20241024-Q5_0.gguf +3 -0
  10. KONI-Llama3.1-8B-Instruct-20241024-Q5_K_M.gguf +3 -0
  11. KONI-Llama3.1-8B-Instruct-20241024-Q5_K_S.gguf +3 -0
  12. KONI-Llama3.1-8B-Instruct-20241024-Q6_K.gguf +3 -0
  13. KONI-Llama3.1-8B-Instruct-20241024-Q8_0.gguf +3 -0
  14. README.md +86 -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
+ KONI-Llama3.1-8B-Instruct-20241024-Q2_K.gguf filter=lfs diff=lfs merge=lfs -text
37
+ KONI-Llama3.1-8B-Instruct-20241024-Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text
38
+ KONI-Llama3.1-8B-Instruct-20241024-Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text
39
+ KONI-Llama3.1-8B-Instruct-20241024-Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text
40
+ KONI-Llama3.1-8B-Instruct-20241024-Q4_0.gguf filter=lfs diff=lfs merge=lfs -text
41
+ KONI-Llama3.1-8B-Instruct-20241024-Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text
42
+ KONI-Llama3.1-8B-Instruct-20241024-Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text
43
+ KONI-Llama3.1-8B-Instruct-20241024-Q5_0.gguf filter=lfs diff=lfs merge=lfs -text
44
+ KONI-Llama3.1-8B-Instruct-20241024-Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text
45
+ KONI-Llama3.1-8B-Instruct-20241024-Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text
46
+ KONI-Llama3.1-8B-Instruct-20241024-Q6_K.gguf filter=lfs diff=lfs merge=lfs -text
47
+ KONI-Llama3.1-8B-Instruct-20241024-Q8_0.gguf filter=lfs diff=lfs merge=lfs -text
KONI-Llama3.1-8B-Instruct-20241024-Q2_K.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:eb7b51d4f8e58f02b72cab7d81580845c96a8b936120df812843e46b73be01aa
3
+ size 3179136704
KONI-Llama3.1-8B-Instruct-20241024-Q3_K_L.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2f3c3e756e60c93ab31c04e1d91773083690d1a2a82cd9e02f3f455ee59a48ae
3
+ size 4321961664
KONI-Llama3.1-8B-Instruct-20241024-Q3_K_M.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:faa61e7f9c326bfcf424a9128de2cdf98272c87d10ded95b90e5a8bc5a793aa3
3
+ size 4018923200
KONI-Llama3.1-8B-Instruct-20241024-Q3_K_S.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d2e6d362290c49defc872cc07b51bd869335fc3ea15647d7cf4a0a500a5f3a54
3
+ size 3664504512
KONI-Llama3.1-8B-Instruct-20241024-Q4_0.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:41a982c22c78728c194e4af6f14059a0662e336dfca5a269f3b223e019362d22
3
+ size 4661216960
KONI-Llama3.1-8B-Instruct-20241024-Q4_K_M.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:374edfb9f22c3345da9a65f26728304ce3aeb3051fe6cb46a28ca0e0336fb095
3
+ size 4920739520
KONI-Llama3.1-8B-Instruct-20241024-Q4_K_S.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a68426954ce89aa86a926ba80d59ddeaee5c88f7a75cf3d896e9d0253dc03368
3
+ size 4692674240
KONI-Llama3.1-8B-Instruct-20241024-Q5_0.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1edde2e36d3a18e353da5bd2473286bd28a4f9ca08c568b2046a080d37a068a6
3
+ size 5599299264
KONI-Llama3.1-8B-Instruct-20241024-Q5_K_M.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:519d692ee294a3098c0465a1d726a68d4de390349dc3484bc3f5f6b1e614178b
3
+ size 5732992704
KONI-Llama3.1-8B-Instruct-20241024-Q5_K_S.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:143052e3a4281e1061ea6a7bb703ea9226aaaeb645ad821905015191601bf4c8
3
+ size 5599299264
KONI-Llama3.1-8B-Instruct-20241024-Q6_K.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2d86ff038fb41aa36318bf943535645e660e5c077218262ea1bcea409e3448c9
3
+ size 6596011712
KONI-Llama3.1-8B-Instruct-20241024-Q8_0.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ad864f5a8a3287b5dfadfca2ffca5a44bd64e020bafc009364d108ccac6b4097
3
+ size 8540776128
README.md ADDED
@@ -0,0 +1,86 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ language: ko
3
+ pipeline_tag: text-generation
4
+ license: llama3.1
5
+ tags:
6
+ - TensorBlock
7
+ - GGUF
8
+ base_model: KISTI-KONI/KONI-Llama3.1-8B-Instruct-20241024
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
+ ## KISTI-KONI/KONI-Llama3.1-8B-Instruct-20241024 - GGUF
23
+
24
+ This repo contains GGUF format model files for [KISTI-KONI/KONI-Llama3.1-8B-Instruct-20241024](https://huggingface.co/KISTI-KONI/KONI-Llama3.1-8B-Instruct-20241024).
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
+ <|begin_of_text|><|start_header_id|>system<|end_header_id|>
38
+
39
+ You are KONI, an AI assistant trained based on LlaMA3.1 and created by KISTI to be helpful and honest. Your knowledge spans a wide range of topics, allowing you to engage in substantive conversations and provide analysis on complex subjects. Below is an instruction that describes a task. Write a response that appropriately completes the request. If you don't know the answer, just say that you don't know.
40
+ Cutting Knowledge Date: July 2024
41
+ Today Date: 27 Aug 2024
42
+
43
+ {system_prompt}<|eot_id|><|start_header_id|>user<|end_header_id|>
44
+
45
+ {prompt}<|eot_id|><|start_header_id|>KONI<|end_header_id|>
46
+ ```
47
+
48
+ ## Model file specification
49
+
50
+ | Filename | Quant type | File Size | Description |
51
+ | -------- | ---------- | --------- | ----------- |
52
+ | [KONI-Llama3.1-8B-Instruct-20241024-Q2_K.gguf](https://huggingface.co/tensorblock/KONI-Llama3.1-8B-Instruct-20241024-GGUF/blob/main/KONI-Llama3.1-8B-Instruct-20241024-Q2_K.gguf) | Q2_K | 3.179 GB | smallest, significant quality loss - not recommended for most purposes |
53
+ | [KONI-Llama3.1-8B-Instruct-20241024-Q3_K_S.gguf](https://huggingface.co/tensorblock/KONI-Llama3.1-8B-Instruct-20241024-GGUF/blob/main/KONI-Llama3.1-8B-Instruct-20241024-Q3_K_S.gguf) | Q3_K_S | 3.665 GB | very small, high quality loss |
54
+ | [KONI-Llama3.1-8B-Instruct-20241024-Q3_K_M.gguf](https://huggingface.co/tensorblock/KONI-Llama3.1-8B-Instruct-20241024-GGUF/blob/main/KONI-Llama3.1-8B-Instruct-20241024-Q3_K_M.gguf) | Q3_K_M | 4.019 GB | very small, high quality loss |
55
+ | [KONI-Llama3.1-8B-Instruct-20241024-Q3_K_L.gguf](https://huggingface.co/tensorblock/KONI-Llama3.1-8B-Instruct-20241024-GGUF/blob/main/KONI-Llama3.1-8B-Instruct-20241024-Q3_K_L.gguf) | Q3_K_L | 4.322 GB | small, substantial quality loss |
56
+ | [KONI-Llama3.1-8B-Instruct-20241024-Q4_0.gguf](https://huggingface.co/tensorblock/KONI-Llama3.1-8B-Instruct-20241024-GGUF/blob/main/KONI-Llama3.1-8B-Instruct-20241024-Q4_0.gguf) | Q4_0 | 4.661 GB | legacy; small, very high quality loss - prefer using Q3_K_M |
57
+ | [KONI-Llama3.1-8B-Instruct-20241024-Q4_K_S.gguf](https://huggingface.co/tensorblock/KONI-Llama3.1-8B-Instruct-20241024-GGUF/blob/main/KONI-Llama3.1-8B-Instruct-20241024-Q4_K_S.gguf) | Q4_K_S | 4.693 GB | small, greater quality loss |
58
+ | [KONI-Llama3.1-8B-Instruct-20241024-Q4_K_M.gguf](https://huggingface.co/tensorblock/KONI-Llama3.1-8B-Instruct-20241024-GGUF/blob/main/KONI-Llama3.1-8B-Instruct-20241024-Q4_K_M.gguf) | Q4_K_M | 4.921 GB | medium, balanced quality - recommended |
59
+ | [KONI-Llama3.1-8B-Instruct-20241024-Q5_0.gguf](https://huggingface.co/tensorblock/KONI-Llama3.1-8B-Instruct-20241024-GGUF/blob/main/KONI-Llama3.1-8B-Instruct-20241024-Q5_0.gguf) | Q5_0 | 5.599 GB | legacy; medium, balanced quality - prefer using Q4_K_M |
60
+ | [KONI-Llama3.1-8B-Instruct-20241024-Q5_K_S.gguf](https://huggingface.co/tensorblock/KONI-Llama3.1-8B-Instruct-20241024-GGUF/blob/main/KONI-Llama3.1-8B-Instruct-20241024-Q5_K_S.gguf) | Q5_K_S | 5.599 GB | large, low quality loss - recommended |
61
+ | [KONI-Llama3.1-8B-Instruct-20241024-Q5_K_M.gguf](https://huggingface.co/tensorblock/KONI-Llama3.1-8B-Instruct-20241024-GGUF/blob/main/KONI-Llama3.1-8B-Instruct-20241024-Q5_K_M.gguf) | Q5_K_M | 5.733 GB | large, very low quality loss - recommended |
62
+ | [KONI-Llama3.1-8B-Instruct-20241024-Q6_K.gguf](https://huggingface.co/tensorblock/KONI-Llama3.1-8B-Instruct-20241024-GGUF/blob/main/KONI-Llama3.1-8B-Instruct-20241024-Q6_K.gguf) | Q6_K | 6.596 GB | very large, extremely low quality loss |
63
+ | [KONI-Llama3.1-8B-Instruct-20241024-Q8_0.gguf](https://huggingface.co/tensorblock/KONI-Llama3.1-8B-Instruct-20241024-GGUF/blob/main/KONI-Llama3.1-8B-Instruct-20241024-Q8_0.gguf) | Q8_0 | 8.541 GB | very large, extremely low quality loss - not recommended |
64
+
65
+
66
+ ## Downloading instruction
67
+
68
+ ### Command line
69
+
70
+ Firstly, install Huggingface Client
71
+
72
+ ```shell
73
+ pip install -U "huggingface_hub[cli]"
74
+ ```
75
+
76
+ Then, downoad the individual model file the a local directory
77
+
78
+ ```shell
79
+ huggingface-cli download tensorblock/KONI-Llama3.1-8B-Instruct-20241024-GGUF --include "KONI-Llama3.1-8B-Instruct-20241024-Q2_K.gguf" --local-dir MY_LOCAL_DIR
80
+ ```
81
+
82
+ If you wanna download multiple model files with a pattern (e.g., `*Q4_K*gguf`), you can try:
83
+
84
+ ```shell
85
+ huggingface-cli download tensorblock/KONI-Llama3.1-8B-Instruct-20241024-GGUF --local-dir MY_LOCAL_DIR --local-dir-use-symlinks False --include='*Q4_K*gguf'
86
+ ```