Hugging Face's logo

tensorblock
/
Spaetzle-v60-7b-GGUF

GGUF
German
English
Merge
mergekit
lazymergekit
abideen/AlphaMonarch-dora
TensorBlock
GGUF
Inference Endpoints
conversational
Model card Files Community
morriszms commited on
Commit
1f105bf
•
1 Parent(s): 7f56fa2

Upload folder using huggingface_hub

Browse files
Files changed (14) hide show
  1. .gitattributes +12 -0
  2. README.md +81 -0
  3. Spaetzle-v60-7b-Q2_K.gguf +3 -0
  4. Spaetzle-v60-7b-Q3_K_L.gguf +3 -0
  5. Spaetzle-v60-7b-Q3_K_M.gguf +3 -0
  6. Spaetzle-v60-7b-Q3_K_S.gguf +3 -0
  7. Spaetzle-v60-7b-Q4_0.gguf +3 -0
  8. Spaetzle-v60-7b-Q4_K_M.gguf +3 -0
  9. Spaetzle-v60-7b-Q4_K_S.gguf +3 -0
  10. Spaetzle-v60-7b-Q5_0.gguf +3 -0
  11. Spaetzle-v60-7b-Q5_K_M.gguf +3 -0
  12. Spaetzle-v60-7b-Q5_K_S.gguf +3 -0
  13. Spaetzle-v60-7b-Q6_K.gguf +3 -0
  14. Spaetzle-v60-7b-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
+ Spaetzle-v60-7b-Q2_K.gguf filter=lfs diff=lfs merge=lfs -text
37
+ Spaetzle-v60-7b-Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text
38
+ Spaetzle-v60-7b-Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text
39
+ Spaetzle-v60-7b-Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text
40
+ Spaetzle-v60-7b-Q4_0.gguf filter=lfs diff=lfs merge=lfs -text
41
+ Spaetzle-v60-7b-Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text
42
+ Spaetzle-v60-7b-Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text
43
+ Spaetzle-v60-7b-Q5_0.gguf filter=lfs diff=lfs merge=lfs -text
44
+ Spaetzle-v60-7b-Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text
45
+ Spaetzle-v60-7b-Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text
46
+ Spaetzle-v60-7b-Q6_K.gguf filter=lfs diff=lfs merge=lfs -text
47
+ Spaetzle-v60-7b-Q8_0.gguf filter=lfs diff=lfs merge=lfs -text
README.md ADDED
@@ -0,0 +1,81 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ tags:
3
+ - merge
4
+ - mergekit
5
+ - lazymergekit
6
+ - abideen/AlphaMonarch-dora
7
+ - TensorBlock
8
+ - GGUF
9
+ base_model: cstr/Spaetzle-v60-7b
10
+ license: cc-by-nc-4.0
11
+ language:
12
+ - de
13
+ - en
14
+ ---
15
+
16
+ <div style="width: auto; margin-left: auto; margin-right: auto">
17
+ <img src="https://i.imgur.com/jC7kdl8.jpeg" alt="TensorBlock" style="width: 100%; min-width: 400px; display: block; margin: auto;">
18
+ </div>
19
+ <div style="display: flex; justify-content: space-between; width: 100%;">
20
+ <div style="display: flex; flex-direction: column; align-items: flex-start;">
21
+ <p style="margin-top: 0.5em; margin-bottom: 0em;">
22
+ 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>
23
+ </p>
24
+ </div>
25
+ </div>
26
+
27
+ ## cstr/Spaetzle-v60-7b - GGUF
28
+
29
+ This repo contains GGUF format model files for [cstr/Spaetzle-v60-7b](https://huggingface.co/cstr/Spaetzle-v60-7b).
30
+
31
+ 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).
32
+
33
+ ## Prompt template
34
+
35
+ ```
36
+ <|im_start|>system
37
+ {system_prompt}<|im_end|>
38
+ <|im_start|>user
39
+ {prompt}<|im_end|>
40
+ <|im_start|>assistant
41
+ ```
42
+
43
+ ## Model file specification
44
+
45
+ | Filename | Quant type | File Size | Description |
46
+ | -------- | ---------- | --------- | ----------- |
47
+ | [Spaetzle-v60-7b-Q2_K.gguf](https://huggingface.co/tensorblock/Spaetzle-v60-7b-GGUF/tree/main/Spaetzle-v60-7b-Q2_K.gguf) | Q2_K | 2.532 GB | smallest, significant quality loss - not recommended for most purposes |
48
+ | [Spaetzle-v60-7b-Q3_K_S.gguf](https://huggingface.co/tensorblock/Spaetzle-v60-7b-GGUF/tree/main/Spaetzle-v60-7b-Q3_K_S.gguf) | Q3_K_S | 2.947 GB | very small, high quality loss |
49
+ | [Spaetzle-v60-7b-Q3_K_M.gguf](https://huggingface.co/tensorblock/Spaetzle-v60-7b-GGUF/tree/main/Spaetzle-v60-7b-Q3_K_M.gguf) | Q3_K_M | 3.277 GB | very small, high quality loss |
50
+ | [Spaetzle-v60-7b-Q3_K_L.gguf](https://huggingface.co/tensorblock/Spaetzle-v60-7b-GGUF/tree/main/Spaetzle-v60-7b-Q3_K_L.gguf) | Q3_K_L | 3.560 GB | small, substantial quality loss |
51
+ | [Spaetzle-v60-7b-Q4_0.gguf](https://huggingface.co/tensorblock/Spaetzle-v60-7b-GGUF/tree/main/Spaetzle-v60-7b-Q4_0.gguf) | Q4_0 | 3.827 GB | legacy; small, very high quality loss - prefer using Q3_K_M |
52
+ | [Spaetzle-v60-7b-Q4_K_S.gguf](https://huggingface.co/tensorblock/Spaetzle-v60-7b-GGUF/tree/main/Spaetzle-v60-7b-Q4_K_S.gguf) | Q4_K_S | 3.856 GB | small, greater quality loss |
53
+ | [Spaetzle-v60-7b-Q4_K_M.gguf](https://huggingface.co/tensorblock/Spaetzle-v60-7b-GGUF/tree/main/Spaetzle-v60-7b-Q4_K_M.gguf) | Q4_K_M | 4.068 GB | medium, balanced quality - recommended |
54
+ | [Spaetzle-v60-7b-Q5_0.gguf](https://huggingface.co/tensorblock/Spaetzle-v60-7b-GGUF/tree/main/Spaetzle-v60-7b-Q5_0.gguf) | Q5_0 | 4.654 GB | legacy; medium, balanced quality - prefer using Q4_K_M |
55
+ | [Spaetzle-v60-7b-Q5_K_S.gguf](https://huggingface.co/tensorblock/Spaetzle-v60-7b-GGUF/tree/main/Spaetzle-v60-7b-Q5_K_S.gguf) | Q5_K_S | 4.654 GB | large, low quality loss - recommended |
56
+ | [Spaetzle-v60-7b-Q5_K_M.gguf](https://huggingface.co/tensorblock/Spaetzle-v60-7b-GGUF/tree/main/Spaetzle-v60-7b-Q5_K_M.gguf) | Q5_K_M | 4.779 GB | large, very low quality loss - recommended |
57
+ | [Spaetzle-v60-7b-Q6_K.gguf](https://huggingface.co/tensorblock/Spaetzle-v60-7b-GGUF/tree/main/Spaetzle-v60-7b-Q6_K.gguf) | Q6_K | 5.534 GB | very large, extremely low quality loss |
58
+ | [Spaetzle-v60-7b-Q8_0.gguf](https://huggingface.co/tensorblock/Spaetzle-v60-7b-GGUF/tree/main/Spaetzle-v60-7b-Q8_0.gguf) | Q8_0 | 7.167 GB | very large, extremely low quality loss - not recommended |
59
+
60
+
61
+ ## Downloading instruction
62
+
63
+ ### Command line
64
+
65
+ Firstly, install Huggingface Client
66
+
67
+ ```shell
68
+ pip install -U "huggingface_hub[cli]"
69
+ ```
70
+
71
+ Then, downoad the individual model file the a local directory
72
+
73
+ ```shell
74
+ huggingface-cli download tensorblock/Spaetzle-v60-7b-GGUF --include "Spaetzle-v60-7b-Q2_K.gguf" --local-dir MY_LOCAL_DIR
75
+ ```
76
+
77
+ If you wanna download multiple model files with a pattern (e.g., `*Q4_K*gguf`), you can try:
78
+
79
+ ```shell
80
+ huggingface-cli download tensorblock/Spaetzle-v60-7b-GGUF --local-dir MY_LOCAL_DIR --local-dir-use-symlinks False --include='*Q4_K*gguf'
81
+ ```
Spaetzle-v60-7b-Q2_K.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fe66a8af4b3b2ddc710be76f88615a0a9fd876cea96644a208469a2f64697868
3
+ size 2719243040
Spaetzle-v60-7b-Q3_K_L.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3b542d0e4e48c95f1dfb9a85daa9db0c967c6a65f5e2b3815ae172e0ec8dcc71
3
+ size 3822025504
Spaetzle-v60-7b-Q3_K_M.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b0c331888f0840202c6997ef83e7b598ff322c5f10adf963fd13b1e795611a82
3
+ size 3518987040
Spaetzle-v60-7b-Q3_K_S.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:99b4ff1e23aa2eb7297856330abdd28e8cff526086586a2483bacb037ef634b5
3
+ size 3164568352
Spaetzle-v60-7b-Q4_0.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0bccbd3801c85eb863a1379cba05e2fd934087be9251f2f6902c60466eed7ade
3
+ size 4108917536
Spaetzle-v60-7b-Q4_K_M.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b7ef2a08382f4e82bb2c05ccef9d37354723b1db08810f483f304f29de096b6a
3
+ size 4368440096
Spaetzle-v60-7b-Q4_K_S.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f9c225bd60c4d3826e1e8547cefcc5b01068f0870ab9a50e023757c4ac2ee593
3
+ size 4140374816
Spaetzle-v60-7b-Q5_0.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1c44741168dddea0ec7d8457c4df4138eb0876004606d98848d6176020b2b803
3
+ size 4997716768
Spaetzle-v60-7b-Q5_K_M.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8d0c8f9821bc94ffa4d088bbd842d43179a0e7a99738eb7a8b73703b50828220
3
+ size 5131410208
Spaetzle-v60-7b-Q5_K_S.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c1918d2ee8b627f18e426e7ac850329ea16d55a918324e2dc181998c9087f3ab
3
+ size 4997716768
Spaetzle-v60-7b-Q6_K.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0c920a238fed4b5c81d0a68205dc61c45b57a7b02741807b3d000768c35c5632
3
+ size 5942065952
Spaetzle-v60-7b-Q8_0.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a0c209e5d68073a219cf650b1f092f830e129241630f5b1b4a00a29668305cfa
3
+ size 7695858464