Hugging Face's logo

tensorblock
/
PULI-LlumiX-32K-GGUF

GGUF
Hungarian
English
puli
TensorBlock
GGUF
Inference Endpoints
Model card Files Community
morriszms commited on
Commit
0316851
•
1 Parent(s): 1d1d318

Upload folder using huggingface_hub

Browse files
Files changed (14) hide show
  1. .gitattributes +12 -0
  2. PULI-LlumiX-32K-Q2_K.gguf +3 -0
  3. PULI-LlumiX-32K-Q3_K_L.gguf +3 -0
  4. PULI-LlumiX-32K-Q3_K_M.gguf +3 -0
  5. PULI-LlumiX-32K-Q3_K_S.gguf +3 -0
  6. PULI-LlumiX-32K-Q4_0.gguf +3 -0
  7. PULI-LlumiX-32K-Q4_K_M.gguf +3 -0
  8. PULI-LlumiX-32K-Q4_K_S.gguf +3 -0
  9. PULI-LlumiX-32K-Q5_0.gguf +3 -0
  10. PULI-LlumiX-32K-Q5_K_M.gguf +3 -0
  11. PULI-LlumiX-32K-Q5_K_S.gguf +3 -0
  12. PULI-LlumiX-32K-Q6_K.gguf +3 -0
  13. PULI-LlumiX-32K-Q8_0.gguf +3 -0
  14. README.md +74 -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
+ PULI-LlumiX-32K-Q2_K.gguf filter=lfs diff=lfs merge=lfs -text
37
+ PULI-LlumiX-32K-Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text
38
+ PULI-LlumiX-32K-Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text
39
+ PULI-LlumiX-32K-Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text
40
+ PULI-LlumiX-32K-Q4_0.gguf filter=lfs diff=lfs merge=lfs -text
41
+ PULI-LlumiX-32K-Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text
42
+ PULI-LlumiX-32K-Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text
43
+ PULI-LlumiX-32K-Q5_0.gguf filter=lfs diff=lfs merge=lfs -text
44
+ PULI-LlumiX-32K-Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text
45
+ PULI-LlumiX-32K-Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text
46
+ PULI-LlumiX-32K-Q6_K.gguf filter=lfs diff=lfs merge=lfs -text
47
+ PULI-LlumiX-32K-Q8_0.gguf filter=lfs diff=lfs merge=lfs -text
PULI-LlumiX-32K-Q2_K.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:53ec4088a10cf379991ea86d42e65086f15aa6692b8c45856f6059950f8aabf8
3
+ size 2532864384
PULI-LlumiX-32K-Q3_K_L.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:453577b44c8ca2690d68730b2adb008c01ac4ac47ef19f6b5744a9f844698a5b
3
+ size 3597111680
PULI-LlumiX-32K-Q3_K_M.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0ff8840e96aa57689b051e46e030ce1fb5b47e20350d5bccd37f4c41556aa209
3
+ size 3298005376
PULI-LlumiX-32K-Q3_K_S.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a758c8ac1aa302ee35ce8ff310d6a50290e84d67a6f94827993347d2576bf1ed
3
+ size 2948305280
PULI-LlumiX-32K-Q4_0.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:78d21b544af3d63d002d71407ce86b647f4f51c69518980b9e196363a3b6b937
3
+ size 3825807744
PULI-LlumiX-32K-Q4_K_M.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:687e8bffce4b51e7a155efa876d49c3a5cc1bdba567dbfe40c607989a69fb0c2
3
+ size 4081004928
PULI-LlumiX-32K-Q4_K_S.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e32f6f8b4dd6df8d0404449272be9858e075f1934f9d036c166ad8a139bd69e9
3
+ size 3856740736
PULI-LlumiX-32K-Q5_0.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:72da6d3304e04b145a083d9700dd5d9db0a4b82342d6dcf62cf8aac8800072e2
3
+ size 4651692416
PULI-LlumiX-32K-Q5_K_M.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:168335ff6e9b8e49d5f6c27df9bf7abcdf5aafe7c99fedd025ea7ce604af2b60
3
+ size 4783157632
PULI-LlumiX-32K-Q5_K_S.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f2a7aa69947056f7d39bb8aacbd1d85044bdbd3a1f5f672cb0f4845cffc6ce90
3
+ size 4651692416
PULI-LlumiX-32K-Q6_K.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:41be56d8b578c80cf73c29bbe657f356af544a4527958617ffe3f2d90791a6cb
3
+ size 5529194880
PULI-LlumiX-32K-Q8_0.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:71f66ec1968a3af5bffb092a3c4197bff02467c6ceb8cc3d86016acc1ffc525c
3
+ size 7161090432
README.md ADDED
@@ -0,0 +1,74 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ license: llama2
3
+ language:
4
+ - hu
5
+ - en
6
+ tags:
7
+ - puli
8
+ - TensorBlock
9
+ - GGUF
10
+ base_model: NYTK/PULI-LlumiX-32K
11
+ ---
12
+
13
+ <div style="width: auto; margin-left: auto; margin-right: auto">
14
+ <img src="https://i.imgur.com/jC7kdl8.jpeg" alt="TensorBlock" style="width: 100%; min-width: 400px; display: block; margin: auto;">
15
+ </div>
16
+ <div style="display: flex; justify-content: space-between; width: 100%;">
17
+ <div style="display: flex; flex-direction: column; align-items: flex-start;">
18
+ <p style="margin-top: 0.5em; margin-bottom: 0em;">
19
+ 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>
20
+ </p>
21
+ </div>
22
+ </div>
23
+
24
+ ## NYTK/PULI-LlumiX-32K - GGUF
25
+
26
+ This repo contains GGUF format model files for [NYTK/PULI-LlumiX-32K](https://huggingface.co/NYTK/PULI-LlumiX-32K).
27
+
28
+ 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).
29
+
30
+ ## Prompt template
31
+
32
+ ```
33
+
34
+ ```
35
+
36
+ ## Model file specification
37
+
38
+ | Filename | Quant type | File Size | Description |
39
+ | -------- | ---------- | --------- | ----------- |
40
+ | [PULI-LlumiX-32K-Q2_K.gguf](https://huggingface.co/tensorblock/PULI-LlumiX-32K-GGUF/tree/main/PULI-LlumiX-32K-Q2_K.gguf) | Q2_K | 2.359 GB | smallest, significant quality loss - not recommended for most purposes |
41
+ | [PULI-LlumiX-32K-Q3_K_S.gguf](https://huggingface.co/tensorblock/PULI-LlumiX-32K-GGUF/tree/main/PULI-LlumiX-32K-Q3_K_S.gguf) | Q3_K_S | 2.746 GB | very small, high quality loss |
42
+ | [PULI-LlumiX-32K-Q3_K_M.gguf](https://huggingface.co/tensorblock/PULI-LlumiX-32K-GGUF/tree/main/PULI-LlumiX-32K-Q3_K_M.gguf) | Q3_K_M | 3.072 GB | very small, high quality loss |
43
+ | [PULI-LlumiX-32K-Q3_K_L.gguf](https://huggingface.co/tensorblock/PULI-LlumiX-32K-GGUF/tree/main/PULI-LlumiX-32K-Q3_K_L.gguf) | Q3_K_L | 3.350 GB | small, substantial quality loss |
44
+ | [PULI-LlumiX-32K-Q4_0.gguf](https://huggingface.co/tensorblock/PULI-LlumiX-32K-GGUF/tree/main/PULI-LlumiX-32K-Q4_0.gguf) | Q4_0 | 3.563 GB | legacy; small, very high quality loss - prefer using Q3_K_M |
45
+ | [PULI-LlumiX-32K-Q4_K_S.gguf](https://huggingface.co/tensorblock/PULI-LlumiX-32K-GGUF/tree/main/PULI-LlumiX-32K-Q4_K_S.gguf) | Q4_K_S | 3.592 GB | small, greater quality loss |
46
+ | [PULI-LlumiX-32K-Q4_K_M.gguf](https://huggingface.co/tensorblock/PULI-LlumiX-32K-GGUF/tree/main/PULI-LlumiX-32K-Q4_K_M.gguf) | Q4_K_M | 3.801 GB | medium, balanced quality - recommended |
47
+ | [PULI-LlumiX-32K-Q5_0.gguf](https://huggingface.co/tensorblock/PULI-LlumiX-32K-GGUF/tree/main/PULI-LlumiX-32K-Q5_0.gguf) | Q5_0 | 4.332 GB | legacy; medium, balanced quality - prefer using Q4_K_M |
48
+ | [PULI-LlumiX-32K-Q5_K_S.gguf](https://huggingface.co/tensorblock/PULI-LlumiX-32K-GGUF/tree/main/PULI-LlumiX-32K-Q5_K_S.gguf) | Q5_K_S | 4.332 GB | large, low quality loss - recommended |
49
+ | [PULI-LlumiX-32K-Q5_K_M.gguf](https://huggingface.co/tensorblock/PULI-LlumiX-32K-GGUF/tree/main/PULI-LlumiX-32K-Q5_K_M.gguf) | Q5_K_M | 4.455 GB | large, very low quality loss - recommended |
50
+ | [PULI-LlumiX-32K-Q6_K.gguf](https://huggingface.co/tensorblock/PULI-LlumiX-32K-GGUF/tree/main/PULI-LlumiX-32K-Q6_K.gguf) | Q6_K | 5.149 GB | very large, extremely low quality loss |
51
+ | [PULI-LlumiX-32K-Q8_0.gguf](https://huggingface.co/tensorblock/PULI-LlumiX-32K-GGUF/tree/main/PULI-LlumiX-32K-Q8_0.gguf) | Q8_0 | 6.669 GB | very large, extremely low quality loss - not recommended |
52
+
53
+
54
+ ## Downloading instruction
55
+
56
+ ### Command line
57
+
58
+ Firstly, install Huggingface Client
59
+
60
+ ```shell
61
+ pip install -U "huggingface_hub[cli]"
62
+ ```
63
+
64
+ Then, downoad the individual model file the a local directory
65
+
66
+ ```shell
67
+ huggingface-cli download tensorblock/PULI-LlumiX-32K-GGUF --include "PULI-LlumiX-32K-Q2_K.gguf" --local-dir MY_LOCAL_DIR
68
+ ```
69
+
70
+ If you wanna download multiple model files with a pattern (e.g., `*Q4_K*gguf`), you can try:
71
+
72
+ ```shell
73
+ huggingface-cli download tensorblock/PULI-LlumiX-32K-GGUF --local-dir MY_LOCAL_DIR --local-dir-use-symlinks False --include='*Q4_K*gguf'
74
+ ```