Hugging Face's logo

tensorblock
/
Vikhr-7B-instruct_0.4-GGUF

Transformers
GGUF
Russian
English
TensorBlock
GGUF
Inference Endpoints
conversational
Model card Files Community
morriszms commited on
Commit
7277430
•
1 Parent(s): 1aa9822

Upload folder using huggingface_hub

Browse files
Files changed (14) hide show
  1. .gitattributes +12 -0
  2. README.md +77 -0
  3. Vikhr-7B-instruct_0.4-Q2_K.gguf +3 -0
  4. Vikhr-7B-instruct_0.4-Q3_K_L.gguf +3 -0
  5. Vikhr-7B-instruct_0.4-Q3_K_M.gguf +3 -0
  6. Vikhr-7B-instruct_0.4-Q3_K_S.gguf +3 -0
  7. Vikhr-7B-instruct_0.4-Q4_0.gguf +3 -0
  8. Vikhr-7B-instruct_0.4-Q4_K_M.gguf +3 -0
  9. Vikhr-7B-instruct_0.4-Q4_K_S.gguf +3 -0
  10. Vikhr-7B-instruct_0.4-Q5_0.gguf +3 -0
  11. Vikhr-7B-instruct_0.4-Q5_K_M.gguf +3 -0
  12. Vikhr-7B-instruct_0.4-Q5_K_S.gguf +3 -0
  13. Vikhr-7B-instruct_0.4-Q6_K.gguf +3 -0
  14. Vikhr-7B-instruct_0.4-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_0.4-Q2_K.gguf filter=lfs diff=lfs merge=lfs -text
37
+ Vikhr-7B-instruct_0.4-Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text
38
+ Vikhr-7B-instruct_0.4-Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text
39
+ Vikhr-7B-instruct_0.4-Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text
40
+ Vikhr-7B-instruct_0.4-Q4_0.gguf filter=lfs diff=lfs merge=lfs -text
41
+ Vikhr-7B-instruct_0.4-Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text
42
+ Vikhr-7B-instruct_0.4-Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text
43
+ Vikhr-7B-instruct_0.4-Q5_0.gguf filter=lfs diff=lfs merge=lfs -text
44
+ Vikhr-7B-instruct_0.4-Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text
45
+ Vikhr-7B-instruct_0.4-Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text
46
+ Vikhr-7B-instruct_0.4-Q6_K.gguf filter=lfs diff=lfs merge=lfs -text
47
+ Vikhr-7B-instruct_0.4-Q8_0.gguf filter=lfs diff=lfs merge=lfs -text
README.md ADDED
@@ -0,0 +1,77 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ library_name: transformers
3
+ language:
4
+ - ru
5
+ - en
6
+ tags:
7
+ - TensorBlock
8
+ - GGUF
9
+ base_model: Vikhrmodels/Vikhr-7B-instruct_0.4
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
+ ## Vikhrmodels/Vikhr-7B-instruct_0.4 - GGUF
24
+
25
+ This repo contains GGUF format model files for [Vikhrmodels/Vikhr-7B-instruct_0.4](https://huggingface.co/Vikhrmodels/Vikhr-7B-instruct_0.4).
26
+
27
+ 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).
28
+
29
+ ## Prompt template
30
+
31
+ ```
32
+ <s><|im_start|>system
33
+ {system_prompt}<|im_end|>
34
+ <|im_start|>user
35
+ {prompt}<|im_end|>
36
+ <|im_start|>assistant
37
+ ```
38
+
39
+ ## Model file specification
40
+
41
+ | Filename | Quant type | File Size | Description |
42
+ | -------- | ---------- | --------- | ----------- |
43
+ | [Vikhr-7B-instruct_0.4-Q2_K.gguf](https://huggingface.co/tensorblock/Vikhr-7B-instruct_0.4-GGUF/tree/main/Vikhr-7B-instruct_0.4-Q2_K.gguf) | Q2_K | 2.740 GB | smallest, significant quality loss - not recommended for most purposes |
44
+ | [Vikhr-7B-instruct_0.4-Q3_K_S.gguf](https://huggingface.co/tensorblock/Vikhr-7B-instruct_0.4-GGUF/tree/main/Vikhr-7B-instruct_0.4-Q3_K_S.gguf) | Q3_K_S | 3.173 GB | very small, high quality loss |
45
+ | [Vikhr-7B-instruct_0.4-Q3_K_M.gguf](https://huggingface.co/tensorblock/Vikhr-7B-instruct_0.4-GGUF/tree/main/Vikhr-7B-instruct_0.4-Q3_K_M.gguf) | Q3_K_M | 3.503 GB | very small, high quality loss |
46
+ | [Vikhr-7B-instruct_0.4-Q3_K_L.gguf](https://huggingface.co/tensorblock/Vikhr-7B-instruct_0.4-GGUF/tree/main/Vikhr-7B-instruct_0.4-Q3_K_L.gguf) | Q3_K_L | 3.785 GB | small, substantial quality loss |
47
+ | [Vikhr-7B-instruct_0.4-Q4_0.gguf](https://huggingface.co/tensorblock/Vikhr-7B-instruct_0.4-GGUF/tree/main/Vikhr-7B-instruct_0.4-Q4_0.gguf) | Q4_0 | 4.077 GB | legacy; small, very high quality loss - prefer using Q3_K_M |
48
+ | [Vikhr-7B-instruct_0.4-Q4_K_S.gguf](https://huggingface.co/tensorblock/Vikhr-7B-instruct_0.4-GGUF/tree/main/Vikhr-7B-instruct_0.4-Q4_K_S.gguf) | Q4_K_S | 4.106 GB | small, greater quality loss |
49
+ | [Vikhr-7B-instruct_0.4-Q4_K_M.gguf](https://huggingface.co/tensorblock/Vikhr-7B-instruct_0.4-GGUF/tree/main/Vikhr-7B-instruct_0.4-Q4_K_M.gguf) | Q4_K_M | 4.318 GB | medium, balanced quality - recommended |
50
+ | [Vikhr-7B-instruct_0.4-Q5_0.gguf](https://huggingface.co/tensorblock/Vikhr-7B-instruct_0.4-GGUF/tree/main/Vikhr-7B-instruct_0.4-Q5_0.gguf) | Q5_0 | 4.927 GB | legacy; medium, balanced quality - prefer using Q4_K_M |
51
+ | [Vikhr-7B-instruct_0.4-Q5_K_S.gguf](https://huggingface.co/tensorblock/Vikhr-7B-instruct_0.4-GGUF/tree/main/Vikhr-7B-instruct_0.4-Q5_K_S.gguf) | Q5_K_S | 4.927 GB | large, low quality loss - recommended |
52
+ | [Vikhr-7B-instruct_0.4-Q5_K_M.gguf](https://huggingface.co/tensorblock/Vikhr-7B-instruct_0.4-GGUF/tree/main/Vikhr-7B-instruct_0.4-Q5_K_M.gguf) | Q5_K_M | 5.051 GB | large, very low quality loss - recommended |
53
+ | [Vikhr-7B-instruct_0.4-Q6_K.gguf](https://huggingface.co/tensorblock/Vikhr-7B-instruct_0.4-GGUF/tree/main/Vikhr-7B-instruct_0.4-Q6_K.gguf) | Q6_K | 5.830 GB | very large, extremely low quality loss |
54
+ | [Vikhr-7B-instruct_0.4-Q8_0.gguf](https://huggingface.co/tensorblock/Vikhr-7B-instruct_0.4-GGUF/tree/main/Vikhr-7B-instruct_0.4-Q8_0.gguf) | Q8_0 | 7.550 GB | very large, extremely low quality loss - not recommended |
55
+
56
+
57
+ ## Downloading instruction
58
+
59
+ ### Command line
60
+
61
+ Firstly, install Huggingface Client
62
+
63
+ ```shell
64
+ pip install -U "huggingface_hub[cli]"
65
+ ```
66
+
67
+ Then, downoad the individual model file the a local directory
68
+
69
+ ```shell
70
+ huggingface-cli download tensorblock/Vikhr-7B-instruct_0.4-GGUF --include "Vikhr-7B-instruct_0.4-Q2_K.gguf" --local-dir MY_LOCAL_DIR
71
+ ```
72
+
73
+ If you wanna download multiple model files with a pattern (e.g., `*Q4_K*gguf`), you can try:
74
+
75
+ ```shell
76
+ huggingface-cli download tensorblock/Vikhr-7B-instruct_0.4-GGUF --local-dir MY_LOCAL_DIR --local-dir-use-symlinks False --include='*Q4_K*gguf'
77
+ ```
Vikhr-7B-instruct_0.4-Q2_K.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:45773dae8793f903fb4ff63844c3a8efa2208193e6e924923713f0e43e1a1c41
3
+ size 2942269120
Vikhr-7B-instruct_0.4-Q3_K_L.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3c82730e1faed9922ad1d593d6b5c23e893c4cb54ed9ed5a695bf1241c0db246
3
+ size 4064644768
Vikhr-7B-instruct_0.4-Q3_K_M.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:dfe6b86874b4721aea2f587d2403cc8188ca3e75dc2acac5abb216e4e4170ec2
3
+ size 3761606304
Vikhr-7B-instruct_0.4-Q3_K_S.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:36cbccbfc2547e378649b47f8ac3ee4b7710e8ecb72516952dd7edb3ba406a21
3
+ size 3407187616
Vikhr-7B-instruct_0.4-Q4_0.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a7b281c274d53c71cf6e954957eced3aa45b81ca24d7fabfb68a970a90300538
3
+ size 4377158656
Vikhr-7B-instruct_0.4-Q4_K_M.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:aa776f155e45199531e17a34636aa41be8fa2a6751b5d52cbe8f770e74e7f7d8
3
+ size 4636681216
Vikhr-7B-instruct_0.4-Q4_K_S.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2d788f778b9ec19711c18b665a17354dbb705ac30701bda8f11b25a1e216152b
3
+ size 4408615936
Vikhr-7B-instruct_0.4-Q5_0.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3d88a153b1d97e5e32949508850c6c3ce260a73de7efaf8f0dcc5a8a9105c925
3
+ size 5290072576
Vikhr-7B-instruct_0.4-Q5_K_M.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:64e4c3248436b0df79eac6c05de45c94c6e731f6de2a8b09f6c2260ebc7a5971
3
+ size 5423766016
Vikhr-7B-instruct_0.4-Q5_K_S.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8be44387636bdc5f8df48310b4dbefe494c384ddce358f1d3b3b7827e83a08f5
3
+ size 5290072576
Vikhr-7B-instruct_0.4-Q6_K.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5145f6b9b8c4db228768af7a7d8d95963e8d0463b11c2e57d9d2a9a9188c5fe8
3
+ size 6260043616
Vikhr-7B-instruct_0.4-Q8_0.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8dfe815566895fcc457582eec332f6a5ae699fbcee23c4cb1ca16c750109ac9f
3
+ size 8107280544