Hugging Face's logo

tensorblock
/
llama3-8b-spaetzle-v37-GGUF

GGUF
Merge
mergekit
lazymergekit
HeshamHaroon/Arabic-llama3
mlabonne/NeuralDaredevil-8B-abliterated
TensorBlock
GGUF
Inference Endpoints
conversational
Model card Files Community
morriszms commited on
Commit
9840c18
•
1 Parent(s): f109891

Upload folder using huggingface_hub

Browse files
Files changed (14) hide show
  1. .gitattributes +12 -0
  2. README.md +79 -0
  3. llama3-8b-spaetzle-v37-Q2_K.gguf +3 -0
  4. llama3-8b-spaetzle-v37-Q3_K_L.gguf +3 -0
  5. llama3-8b-spaetzle-v37-Q3_K_M.gguf +3 -0
  6. llama3-8b-spaetzle-v37-Q3_K_S.gguf +3 -0
  7. llama3-8b-spaetzle-v37-Q4_0.gguf +3 -0
  8. llama3-8b-spaetzle-v37-Q4_K_M.gguf +3 -0
  9. llama3-8b-spaetzle-v37-Q4_K_S.gguf +3 -0
  10. llama3-8b-spaetzle-v37-Q5_0.gguf +3 -0
  11. llama3-8b-spaetzle-v37-Q5_K_M.gguf +3 -0
  12. llama3-8b-spaetzle-v37-Q5_K_S.gguf +3 -0
  13. llama3-8b-spaetzle-v37-Q6_K.gguf +3 -0
  14. llama3-8b-spaetzle-v37-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
+ llama3-8b-spaetzle-v37-Q2_K.gguf filter=lfs diff=lfs merge=lfs -text
37
+ llama3-8b-spaetzle-v37-Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text
38
+ llama3-8b-spaetzle-v37-Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text
39
+ llama3-8b-spaetzle-v37-Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text
40
+ llama3-8b-spaetzle-v37-Q4_0.gguf filter=lfs diff=lfs merge=lfs -text
41
+ llama3-8b-spaetzle-v37-Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text
42
+ llama3-8b-spaetzle-v37-Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text
43
+ llama3-8b-spaetzle-v37-Q5_0.gguf filter=lfs diff=lfs merge=lfs -text
44
+ llama3-8b-spaetzle-v37-Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text
45
+ llama3-8b-spaetzle-v37-Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text
46
+ llama3-8b-spaetzle-v37-Q6_K.gguf filter=lfs diff=lfs merge=lfs -text
47
+ llama3-8b-spaetzle-v37-Q8_0.gguf filter=lfs diff=lfs merge=lfs -text
README.md ADDED
@@ -0,0 +1,79 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ tags:
3
+ - merge
4
+ - mergekit
5
+ - lazymergekit
6
+ - HeshamHaroon/Arabic-llama3
7
+ - mlabonne/NeuralDaredevil-8B-abliterated
8
+ - TensorBlock
9
+ - GGUF
10
+ base_model: cstr/llama3-8b-spaetzle-v37
11
+ license: llama3
12
+ ---
13
+
14
+ <div style="width: auto; margin-left: auto; margin-right: auto">
15
+ <img src="https://i.imgur.com/jC7kdl8.jpeg" alt="TensorBlock" style="width: 100%; min-width: 400px; display: block; margin: auto;">
16
+ </div>
17
+ <div style="display: flex; justify-content: space-between; width: 100%;">
18
+ <div style="display: flex; flex-direction: column; align-items: flex-start;">
19
+ <p style="margin-top: 0.5em; margin-bottom: 0em;">
20
+ 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>
21
+ </p>
22
+ </div>
23
+ </div>
24
+
25
+ ## cstr/llama3-8b-spaetzle-v37 - GGUF
26
+
27
+ This repo contains GGUF format model files for [cstr/llama3-8b-spaetzle-v37](https://huggingface.co/cstr/llama3-8b-spaetzle-v37).
28
+
29
+ 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).
30
+
31
+ ## Prompt template
32
+
33
+ ```
34
+ <|begin_of_text|><|start_header_id|>system<|end_header_id|>
35
+
36
+ {system_prompt}<|eot_id|><|start_header_id|>user<|end_header_id|>
37
+
38
+ {prompt}<|eot_id|><|start_header_id|>assistant<|end_header_id|>
39
+ ```
40
+
41
+ ## Model file specification
42
+
43
+ | Filename | Quant type | File Size | Description |
44
+ | -------- | ---------- | --------- | ----------- |
45
+ | [llama3-8b-spaetzle-v37-Q2_K.gguf](https://huggingface.co/tensorblock/llama3-8b-spaetzle-v37-GGUF/tree/main/llama3-8b-spaetzle-v37-Q2_K.gguf) | Q2_K | 2.961 GB | smallest, significant quality loss - not recommended for most purposes |
46
+ | [llama3-8b-spaetzle-v37-Q3_K_S.gguf](https://huggingface.co/tensorblock/llama3-8b-spaetzle-v37-GGUF/tree/main/llama3-8b-spaetzle-v37-Q3_K_S.gguf) | Q3_K_S | 3.413 GB | very small, high quality loss |
47
+ | [llama3-8b-spaetzle-v37-Q3_K_M.gguf](https://huggingface.co/tensorblock/llama3-8b-spaetzle-v37-GGUF/tree/main/llama3-8b-spaetzle-v37-Q3_K_M.gguf) | Q3_K_M | 3.743 GB | very small, high quality loss |
48
+ | [llama3-8b-spaetzle-v37-Q3_K_L.gguf](https://huggingface.co/tensorblock/llama3-8b-spaetzle-v37-GGUF/tree/main/llama3-8b-spaetzle-v37-Q3_K_L.gguf) | Q3_K_L | 4.025 GB | small, substantial quality loss |
49
+ | [llama3-8b-spaetzle-v37-Q4_0.gguf](https://huggingface.co/tensorblock/llama3-8b-spaetzle-v37-GGUF/tree/main/llama3-8b-spaetzle-v37-Q4_0.gguf) | Q4_0 | 4.341 GB | legacy; small, very high quality loss - prefer using Q3_K_M |
50
+ | [llama3-8b-spaetzle-v37-Q4_K_S.gguf](https://huggingface.co/tensorblock/llama3-8b-spaetzle-v37-GGUF/tree/main/llama3-8b-spaetzle-v37-Q4_K_S.gguf) | Q4_K_S | 4.370 GB | small, greater quality loss |
51
+ | [llama3-8b-spaetzle-v37-Q4_K_M.gguf](https://huggingface.co/tensorblock/llama3-8b-spaetzle-v37-GGUF/tree/main/llama3-8b-spaetzle-v37-Q4_K_M.gguf) | Q4_K_M | 4.583 GB | medium, balanced quality - recommended |
52
+ | [llama3-8b-spaetzle-v37-Q5_0.gguf](https://huggingface.co/tensorblock/llama3-8b-spaetzle-v37-GGUF/tree/main/llama3-8b-spaetzle-v37-Q5_0.gguf) | Q5_0 | 5.215 GB | legacy; medium, balanced quality - prefer using Q4_K_M |
53
+ | [llama3-8b-spaetzle-v37-Q5_K_S.gguf](https://huggingface.co/tensorblock/llama3-8b-spaetzle-v37-GGUF/tree/main/llama3-8b-spaetzle-v37-Q5_K_S.gguf) | Q5_K_S | 5.215 GB | large, low quality loss - recommended |
54
+ | [llama3-8b-spaetzle-v37-Q5_K_M.gguf](https://huggingface.co/tensorblock/llama3-8b-spaetzle-v37-GGUF/tree/main/llama3-8b-spaetzle-v37-Q5_K_M.gguf) | Q5_K_M | 5.339 GB | large, very low quality loss - recommended |
55
+ | [llama3-8b-spaetzle-v37-Q6_K.gguf](https://huggingface.co/tensorblock/llama3-8b-spaetzle-v37-GGUF/tree/main/llama3-8b-spaetzle-v37-Q6_K.gguf) | Q6_K | 6.143 GB | very large, extremely low quality loss |
56
+ | [llama3-8b-spaetzle-v37-Q8_0.gguf](https://huggingface.co/tensorblock/llama3-8b-spaetzle-v37-GGUF/tree/main/llama3-8b-spaetzle-v37-Q8_0.gguf) | Q8_0 | 7.954 GB | very large, extremely low quality loss - not recommended |
57
+
58
+
59
+ ## Downloading instruction
60
+
61
+ ### Command line
62
+
63
+ Firstly, install Huggingface Client
64
+
65
+ ```shell
66
+ pip install -U "huggingface_hub[cli]"
67
+ ```
68
+
69
+ Then, downoad the individual model file the a local directory
70
+
71
+ ```shell
72
+ huggingface-cli download tensorblock/llama3-8b-spaetzle-v37-GGUF --include "llama3-8b-spaetzle-v37-Q2_K.gguf" --local-dir MY_LOCAL_DIR
73
+ ```
74
+
75
+ If you wanna download multiple model files with a pattern (e.g., `*Q4_K*gguf`), you can try:
76
+
77
+ ```shell
78
+ huggingface-cli download tensorblock/llama3-8b-spaetzle-v37-GGUF --local-dir MY_LOCAL_DIR --local-dir-use-symlinks False --include='*Q4_K*gguf'
79
+ ```
llama3-8b-spaetzle-v37-Q2_K.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9e4a1f7c6d92781b05c5ffd1333bfe8f6f378dd5e33311f2abbfcf0bf238fb26
3
+ size 3179132128
llama3-8b-spaetzle-v37-Q3_K_L.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e667fa1a8905011fd8410539c1565f0e241bdba4f8da6cc13d3b823436e267aa
3
+ size 4321957088
llama3-8b-spaetzle-v37-Q3_K_M.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4df86ea49618aa2070ba81144ece17739a8233f496c86ac8bfebcadae2f75d3e
3
+ size 4018918624
llama3-8b-spaetzle-v37-Q3_K_S.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:20a9225a1d535b3414966be05899fc7925987277a5f365ce49b060c348b03e73
3
+ size 3664499936
llama3-8b-spaetzle-v37-Q4_0.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b9d75329cb304fa19dcd879e0ea05d2c972ce0044f1c7be5fce58b9328c99d8a
3
+ size 4661212384
llama3-8b-spaetzle-v37-Q4_K_M.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3691a381d2ca71753a3fc9db3b0372e04c7e0275253d231c79f0f1e5fcfa4d37
3
+ size 4920734944
llama3-8b-spaetzle-v37-Q4_K_S.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:75344db3654ca687611b82e8a46c56595561e956e7e64302d2d553d045af82c2
3
+ size 4692669664
llama3-8b-spaetzle-v37-Q5_0.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:01e91e28f3bfb646882027cff51a4f3d3cb9fcc74f77d86ebf4377699f791ea7
3
+ size 5599294688
llama3-8b-spaetzle-v37-Q5_K_M.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:987a5f749597fa425b16f910daef27931d3235fa1511b84c6d9106fcedcf9115
3
+ size 5732988128
llama3-8b-spaetzle-v37-Q5_K_S.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4b416af32928d75d5f16b2f3cc99f06fba9e44f453591d553ac647fef62b28c9
3
+ size 5599294688
llama3-8b-spaetzle-v37-Q6_K.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0bfc1de15cb6b48dc154a061aace620bf4bb09e10e5974ae6f743d3f1fd0f548
3
+ size 6596007136
llama3-8b-spaetzle-v37-Q8_0.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fa83c38d43b3dddec48f07a94b81a1c1c4fdaf5f4bb5ecbc8520a34ec8e0df51
3
+ size 8540771552