Hugging Face's logo

tensorblock
/
Vikhr-7B-instruct_0.2-GGUF

GGUF
Russian
English
TensorBlock
GGUF
Inference Endpoints
Model card Files Community
morriszms commited on
Commit
6a5fea3
·
verified ·
1 Parent(s): 3266851

Upload folder using huggingface_hub

Browse files
Files changed (14) hide show
  1. .gitattributes +12 -0
  2. README.md +81 -0
  3. Vikhr-7B-instruct_0.2-Q2_K.gguf +3 -0
  4. Vikhr-7B-instruct_0.2-Q3_K_L.gguf +3 -0
  5. Vikhr-7B-instruct_0.2-Q3_K_M.gguf +3 -0
  6. Vikhr-7B-instruct_0.2-Q3_K_S.gguf +3 -0
  7. Vikhr-7B-instruct_0.2-Q4_0.gguf +3 -0
  8. Vikhr-7B-instruct_0.2-Q4_K_M.gguf +3 -0
  9. Vikhr-7B-instruct_0.2-Q4_K_S.gguf +3 -0
  10. Vikhr-7B-instruct_0.2-Q5_0.gguf +3 -0
  11. Vikhr-7B-instruct_0.2-Q5_K_M.gguf +3 -0
  12. Vikhr-7B-instruct_0.2-Q5_K_S.gguf +3 -0
  13. Vikhr-7B-instruct_0.2-Q6_K.gguf +3 -0
  14. Vikhr-7B-instruct_0.2-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
+ Vikhr-7B-instruct_0.2-Q2_K.gguf filter=lfs diff=lfs merge=lfs -text
37
+ Vikhr-7B-instruct_0.2-Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text
38
+ Vikhr-7B-instruct_0.2-Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text
39
+ Vikhr-7B-instruct_0.2-Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text
40
+ Vikhr-7B-instruct_0.2-Q4_0.gguf filter=lfs diff=lfs merge=lfs -text
41
+ Vikhr-7B-instruct_0.2-Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text
42
+ Vikhr-7B-instruct_0.2-Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text
43
+ Vikhr-7B-instruct_0.2-Q5_0.gguf filter=lfs diff=lfs merge=lfs -text
44
+ Vikhr-7B-instruct_0.2-Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text
45
+ Vikhr-7B-instruct_0.2-Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text
46
+ Vikhr-7B-instruct_0.2-Q6_K.gguf filter=lfs diff=lfs merge=lfs -text
47
+ Vikhr-7B-instruct_0.2-Q8_0.gguf filter=lfs diff=lfs merge=lfs -text
README.md ADDED
@@ -0,0 +1,81 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ language:
3
+ - ru
4
+ - en
5
+ datasets:
6
+ - zjkarina/Vikhr_instruct
7
+ - dichspace/darulm
8
+ base_model: Vikhrmodels/Vikhr-7B-instruct_0.2
9
+ tags:
10
+ - TensorBlock
11
+ - GGUF
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
+ ## Vikhrmodels/Vikhr-7B-instruct_0.2 - GGUF
26
+
27
+ This repo contains GGUF format model files for [Vikhrmodels/Vikhr-7B-instruct_0.2](https://huggingface.co/Vikhrmodels/Vikhr-7B-instruct_0.2).
28
+
29
+ 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).
30
+
31
+ <div style="text-align: left; margin: 20px 0;">
32
+ <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;">
33
+ Run them on the TensorBlock client using your local machine ↗
34
+ </a>
35
+ </div>
36
+
37
+ ## Prompt template
38
+
39
+ ```
40
+
41
+ ```
42
+
43
+ ## Model file specification
44
+
45
+ | Filename | Quant type | File Size | Description |
46
+ | -------- | ---------- | --------- | ----------- |
47
+ | [Vikhr-7B-instruct_0.2-Q2_K.gguf](https://huggingface.co/tensorblock/Vikhr-7B-instruct_0.2-GGUF/blob/main/Vikhr-7B-instruct_0.2-Q2_K.gguf) | Q2_K | 2.667 GB | smallest, significant quality loss - not recommended for most purposes |
48
+ | [Vikhr-7B-instruct_0.2-Q3_K_S.gguf](https://huggingface.co/tensorblock/Vikhr-7B-instruct_0.2-GGUF/blob/main/Vikhr-7B-instruct_0.2-Q3_K_S.gguf) | Q3_K_S | 3.094 GB | very small, high quality loss |
49
+ | [Vikhr-7B-instruct_0.2-Q3_K_M.gguf](https://huggingface.co/tensorblock/Vikhr-7B-instruct_0.2-GGUF/blob/main/Vikhr-7B-instruct_0.2-Q3_K_M.gguf) | Q3_K_M | 3.443 GB | very small, high quality loss |
50
+ | [Vikhr-7B-instruct_0.2-Q3_K_L.gguf](https://huggingface.co/tensorblock/Vikhr-7B-instruct_0.2-GGUF/blob/main/Vikhr-7B-instruct_0.2-Q3_K_L.gguf) | Q3_K_L | 3.743 GB | small, substantial quality loss |
51
+ | [Vikhr-7B-instruct_0.2-Q4_0.gguf](https://huggingface.co/tensorblock/Vikhr-7B-instruct_0.2-GGUF/blob/main/Vikhr-7B-instruct_0.2-Q4_0.gguf) | Q4_0 | 3.987 GB | legacy; small, very high quality loss - prefer using Q3_K_M |
52
+ | [Vikhr-7B-instruct_0.2-Q4_K_S.gguf](https://huggingface.co/tensorblock/Vikhr-7B-instruct_0.2-GGUF/blob/main/Vikhr-7B-instruct_0.2-Q4_K_S.gguf) | Q4_K_S | 4.018 GB | small, greater quality loss |
53
+ | [Vikhr-7B-instruct_0.2-Q4_K_M.gguf](https://huggingface.co/tensorblock/Vikhr-7B-instruct_0.2-GGUF/blob/main/Vikhr-7B-instruct_0.2-Q4_K_M.gguf) | Q4_K_M | 4.242 GB | medium, balanced quality - recommended |
54
+ | [Vikhr-7B-instruct_0.2-Q5_0.gguf](https://huggingface.co/tensorblock/Vikhr-7B-instruct_0.2-GGUF/blob/main/Vikhr-7B-instruct_0.2-Q5_0.gguf) | Q5_0 | 4.827 GB | legacy; medium, balanced quality - prefer using Q4_K_M |
55
+ | [Vikhr-7B-instruct_0.2-Q5_K_S.gguf](https://huggingface.co/tensorblock/Vikhr-7B-instruct_0.2-GGUF/blob/main/Vikhr-7B-instruct_0.2-Q5_K_S.gguf) | Q5_K_S | 4.827 GB | large, low quality loss - recommended |
56
+ | [Vikhr-7B-instruct_0.2-Q5_K_M.gguf](https://huggingface.co/tensorblock/Vikhr-7B-instruct_0.2-GGUF/blob/main/Vikhr-7B-instruct_0.2-Q5_K_M.gguf) | Q5_K_M | 4.958 GB | large, very low quality loss - recommended |
57
+ | [Vikhr-7B-instruct_0.2-Q6_K.gguf](https://huggingface.co/tensorblock/Vikhr-7B-instruct_0.2-GGUF/blob/main/Vikhr-7B-instruct_0.2-Q6_K.gguf) | Q6_K | 5.720 GB | very large, extremely low quality loss |
58
+ | [Vikhr-7B-instruct_0.2-Q8_0.gguf](https://huggingface.co/tensorblock/Vikhr-7B-instruct_0.2-GGUF/blob/main/Vikhr-7B-instruct_0.2-Q8_0.gguf) | Q8_0 | 7.408 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/Vikhr-7B-instruct_0.2-GGUF --include "Vikhr-7B-instruct_0.2-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/Vikhr-7B-instruct_0.2-GGUF --local-dir MY_LOCAL_DIR --local-dir-use-symlinks False --include='*Q4_K*gguf'
81
+ ```
Vikhr-7B-instruct_0.2-Q2_K.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ead3ad8e8bec8d9837128650d46acdc0315cf8ea03b5ee2f317d593661b7aa0f
3
+ size 2666585760
Vikhr-7B-instruct_0.2-Q3_K_L.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c60cfbfac4f68a04bfb04bfeaa29cfb09b71186420138f325c9fbae41c29e146
3
+ size 3742587552
Vikhr-7B-instruct_0.2-Q3_K_M.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1138b84e87a8d9f2a13d9ca40c5da5d677f9070bbcf6a03ec2f38e6b7dbcffd9
3
+ size 3443481248
Vikhr-7B-instruct_0.2-Q3_K_S.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1ec624470f21514d1f3853f89de5854464da0de7e2df72b08bb7bc5f08390ede
3
+ size 3093781152
Vikhr-7B-instruct_0.2-Q4_0.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e85edbbd0aed555bbb69f3feea1afcf2d1b46867dbf00005b0097b914017eba4
3
+ size 3986654880
Vikhr-7B-instruct_0.2-Q4_K_M.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4289b03d57129f30583d5246440d7382fe9a8b86f01f7704bcafd1c66b8b89e5
3
+ size 4241852064
Vikhr-7B-instruct_0.2-Q4_K_S.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8fd5519202e3c3d4fe37516ab53157216e621d935ace95cd9619d66f2864f1af
3
+ size 4017587872
Vikhr-7B-instruct_0.2-Q5_0.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d88711edb155569f2387020b06b886bc0759b2025239fcf6ce0d2b4abf3ddcd3
3
+ size 4827006624
Vikhr-7B-instruct_0.2-Q5_K_M.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:96d28a0e27db49904bbe9083f19187702524281aaf33cdb51b3c37dee9a71b51
3
+ size 4958471840
Vikhr-7B-instruct_0.2-Q5_K_S.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f50d341e16db82b90e928f9fe994a64e4a95ab827e450a3098ab5cd8450075cb
3
+ size 4827006624
Vikhr-7B-instruct_0.2-Q6_K.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:103a3de19cbbc64a1256b9b8a94b4477178426fceb09cacfcb16e8e46756878b
3
+ size 5719880352
Vikhr-7B-instruct_0.2-Q8_0.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:090bf78e4891fb029ebcde0fd375f5161f8426b9b5106c2e7148c3e3d134789e
3
+ size 7407835808