Hugging Face's logo

tensorblock
/
OpenCrystal-12B-L3.1-128K-GGUF

Transformers
GGUF
mergekit
Merge
Not-For-All-Audiences
TensorBlock
GGUF
conversational
Model card Files
xet
 Community
morriszms commited on
Commit
d1dc180
·
verified ·
1 Parent(s): ad32179

Upload folder using huggingface_hub

Browse files
Files changed (14) hide show
  1. .gitattributes +12 -0
  2. OpenCrystal-12B-L3.1-128K-Q2_K.gguf +3 -0
  3. OpenCrystal-12B-L3.1-128K-Q3_K_L.gguf +3 -0
  4. OpenCrystal-12B-L3.1-128K-Q3_K_M.gguf +3 -0
  5. OpenCrystal-12B-L3.1-128K-Q3_K_S.gguf +3 -0
  6. OpenCrystal-12B-L3.1-128K-Q4_0.gguf +3 -0
  7. OpenCrystal-12B-L3.1-128K-Q4_K_M.gguf +3 -0
  8. OpenCrystal-12B-L3.1-128K-Q4_K_S.gguf +3 -0
  9. OpenCrystal-12B-L3.1-128K-Q5_0.gguf +3 -0
  10. OpenCrystal-12B-L3.1-128K-Q5_K_M.gguf +3 -0
  11. OpenCrystal-12B-L3.1-128K-Q5_K_S.gguf +3 -0
  12. OpenCrystal-12B-L3.1-128K-Q6_K.gguf +3 -0
  13. OpenCrystal-12B-L3.1-128K-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
+ OpenCrystal-12B-L3.1-128K-Q2_K.gguf filter=lfs diff=lfs merge=lfs -text
37
+ OpenCrystal-12B-L3.1-128K-Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text
38
+ OpenCrystal-12B-L3.1-128K-Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text
39
+ OpenCrystal-12B-L3.1-128K-Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text
40
+ OpenCrystal-12B-L3.1-128K-Q4_0.gguf filter=lfs diff=lfs merge=lfs -text
41
+ OpenCrystal-12B-L3.1-128K-Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text
42
+ OpenCrystal-12B-L3.1-128K-Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text
43
+ OpenCrystal-12B-L3.1-128K-Q5_0.gguf filter=lfs diff=lfs merge=lfs -text
44
+ OpenCrystal-12B-L3.1-128K-Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text
45
+ OpenCrystal-12B-L3.1-128K-Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text
46
+ OpenCrystal-12B-L3.1-128K-Q6_K.gguf filter=lfs diff=lfs merge=lfs -text
47
+ OpenCrystal-12B-L3.1-128K-Q8_0.gguf filter=lfs diff=lfs merge=lfs -text
OpenCrystal-12B-L3.1-128K-Q2_K.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3829100df3c3e73b727db5774f2ad725e4f1f3742a8b4580abe0e4fc23295d44
3
+ size 4463125952
OpenCrystal-12B-L3.1-128K-Q3_K_L.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:57db85b7d02aae9c36ee060c6f31ad29b1f76e5d4700c3a5faf857d500b98463
3
+ size 6150686144
OpenCrystal-12B-L3.1-128K-Q3_K_M.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bdff3f2720bcf075cfc85ba4b65e4a6f780e12c6e9340d67b09a9187ac7561c0
3
+ size 5695604160
OpenCrystal-12B-L3.1-128K-Q3_K_S.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:763d804872a1aafd25da66441eefe9046fdd0883c621db3714e8287af07f0450
3
+ size 5164500416
OpenCrystal-12B-L3.1-128K-Q4_0.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:299ddc3fe94ad4a8001756a7ab276fcc33fef8676563698f1b446e8e5d61a627
3
+ size 6624683456
OpenCrystal-12B-L3.1-128K-Q4_K_M.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ab8fcccbf3f8937629fd81316e1523ce531ab6da8ced398f03e37d74cd543ab4
3
+ size 7013967296
OpenCrystal-12B-L3.1-128K-Q4_K_S.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:945a9b786efcc1add5ee9facf2a42a7f90770afb88e160ac1522bae13f831cfa
3
+ size 6670820800
OpenCrystal-12B-L3.1-128K-Q5_0.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8ca79f97c870952a94c689e0d17eba7c54c6d536606c81cdd27e962b42f48645
3
+ size 7998973376
OpenCrystal-12B-L3.1-128K-Q5_K_M.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7d59106f6390f9db5264e42862b34c27b025d22104e2f89c3b69a4565fe2d8cc
3
+ size 8199513536
OpenCrystal-12B-L3.1-128K-Q5_K_S.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2939ff18e481fcb515996f8b8c3168f717c35142cd3c69e8331514d678f5139b
3
+ size 7998973376
OpenCrystal-12B-L3.1-128K-Q6_K.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d17492cfce74a43f6ff5cce9d76cb84e41e47a76f9af35788dbd475700061766
3
+ size 9459156416
OpenCrystal-12B-L3.1-128K-Q8_0.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c5f061c0807725de94f20f80dbb0a2b827ec229b8681cfb9ce85404a7eef9149
3
+ size 12249073088
README.md ADDED
@@ -0,0 +1,86 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ library_name: transformers
3
+ tags:
4
+ - mergekit
5
+ - merge
6
+ - not-for-all-audiences
7
+ - TensorBlock
8
+ - GGUF
9
+ base_model: Darkknight535/OpenCrystal-12B-L3.1-128K
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
+ ## Darkknight535/OpenCrystal-12B-L3.1-128K - GGUF
24
+
25
+ This repo contains GGUF format model files for [Darkknight535/OpenCrystal-12B-L3.1-128K](https://huggingface.co/Darkknight535/OpenCrystal-12B-L3.1-128K).
26
+
27
+ 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).
28
+
29
+ <div style="text-align: left; margin: 20px 0;">
30
+ <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;">
31
+ Run them on the TensorBlock client using your local machine ↗
32
+ </a>
33
+ </div>
34
+
35
+ ## Prompt template
36
+
37
+ ```
38
+ <|begin_of_text|><|start_header_id|>system<|end_header_id|>
39
+
40
+ Cutting Knowledge Date: December 2023
41
+ Today Date: 26 Jul 2024
42
+
43
+ {system_prompt}<|eot_id|><|start_header_id|>user<|end_header_id|>
44
+
45
+ {prompt}<|eot_id|><|start_header_id|>assistant<|end_header_id|>
46
+ ```
47
+
48
+ ## Model file specification
49
+
50
+ | Filename | Quant type | File Size | Description |
51
+ | -------- | ---------- | --------- | ----------- |
52
+ | [OpenCrystal-12B-L3.1-128K-Q2_K.gguf](https://huggingface.co/tensorblock/OpenCrystal-12B-L3.1-128K-GGUF/blob/main/OpenCrystal-12B-L3.1-128K-Q2_K.gguf) | Q2_K | 4.463 GB | smallest, significant quality loss - not recommended for most purposes |
53
+ | [OpenCrystal-12B-L3.1-128K-Q3_K_S.gguf](https://huggingface.co/tensorblock/OpenCrystal-12B-L3.1-128K-GGUF/blob/main/OpenCrystal-12B-L3.1-128K-Q3_K_S.gguf) | Q3_K_S | 5.165 GB | very small, high quality loss |
54
+ | [OpenCrystal-12B-L3.1-128K-Q3_K_M.gguf](https://huggingface.co/tensorblock/OpenCrystal-12B-L3.1-128K-GGUF/blob/main/OpenCrystal-12B-L3.1-128K-Q3_K_M.gguf) | Q3_K_M | 5.696 GB | very small, high quality loss |
55
+ | [OpenCrystal-12B-L3.1-128K-Q3_K_L.gguf](https://huggingface.co/tensorblock/OpenCrystal-12B-L3.1-128K-GGUF/blob/main/OpenCrystal-12B-L3.1-128K-Q3_K_L.gguf) | Q3_K_L | 6.151 GB | small, substantial quality loss |
56
+ | [OpenCrystal-12B-L3.1-128K-Q4_0.gguf](https://huggingface.co/tensorblock/OpenCrystal-12B-L3.1-128K-GGUF/blob/main/OpenCrystal-12B-L3.1-128K-Q4_0.gguf) | Q4_0 | 6.625 GB | legacy; small, very high quality loss - prefer using Q3_K_M |
57
+ | [OpenCrystal-12B-L3.1-128K-Q4_K_S.gguf](https://huggingface.co/tensorblock/OpenCrystal-12B-L3.1-128K-GGUF/blob/main/OpenCrystal-12B-L3.1-128K-Q4_K_S.gguf) | Q4_K_S | 6.671 GB | small, greater quality loss |
58
+ | [OpenCrystal-12B-L3.1-128K-Q4_K_M.gguf](https://huggingface.co/tensorblock/OpenCrystal-12B-L3.1-128K-GGUF/blob/main/OpenCrystal-12B-L3.1-128K-Q4_K_M.gguf) | Q4_K_M | 7.014 GB | medium, balanced quality - recommended |
59
+ | [OpenCrystal-12B-L3.1-128K-Q5_0.gguf](https://huggingface.co/tensorblock/OpenCrystal-12B-L3.1-128K-GGUF/blob/main/OpenCrystal-12B-L3.1-128K-Q5_0.gguf) | Q5_0 | 7.999 GB | legacy; medium, balanced quality - prefer using Q4_K_M |
60
+ | [OpenCrystal-12B-L3.1-128K-Q5_K_S.gguf](https://huggingface.co/tensorblock/OpenCrystal-12B-L3.1-128K-GGUF/blob/main/OpenCrystal-12B-L3.1-128K-Q5_K_S.gguf) | Q5_K_S | 7.999 GB | large, low quality loss - recommended |
61
+ | [OpenCrystal-12B-L3.1-128K-Q5_K_M.gguf](https://huggingface.co/tensorblock/OpenCrystal-12B-L3.1-128K-GGUF/blob/main/OpenCrystal-12B-L3.1-128K-Q5_K_M.gguf) | Q5_K_M | 8.200 GB | large, very low quality loss - recommended |
62
+ | [OpenCrystal-12B-L3.1-128K-Q6_K.gguf](https://huggingface.co/tensorblock/OpenCrystal-12B-L3.1-128K-GGUF/blob/main/OpenCrystal-12B-L3.1-128K-Q6_K.gguf) | Q6_K | 9.459 GB | very large, extremely low quality loss |
63
+ | [OpenCrystal-12B-L3.1-128K-Q8_0.gguf](https://huggingface.co/tensorblock/OpenCrystal-12B-L3.1-128K-GGUF/blob/main/OpenCrystal-12B-L3.1-128K-Q8_0.gguf) | Q8_0 | 12.249 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/OpenCrystal-12B-L3.1-128K-GGUF --include "OpenCrystal-12B-L3.1-128K-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/OpenCrystal-12B-L3.1-128K-GGUF --local-dir MY_LOCAL_DIR --local-dir-use-symlinks False --include='*Q4_K*gguf'
86
+ ```