Upload folder using huggingface_hub
Browse files- .gitattributes +12 -0
- QVikhr-2.5-1.5B-Instruct-SMPO-Q2_K.gguf +3 -0
- QVikhr-2.5-1.5B-Instruct-SMPO-Q3_K_L.gguf +3 -0
- QVikhr-2.5-1.5B-Instruct-SMPO-Q3_K_M.gguf +3 -0
- QVikhr-2.5-1.5B-Instruct-SMPO-Q3_K_S.gguf +3 -0
- QVikhr-2.5-1.5B-Instruct-SMPO-Q4_0.gguf +3 -0
- QVikhr-2.5-1.5B-Instruct-SMPO-Q4_K_M.gguf +3 -0
- QVikhr-2.5-1.5B-Instruct-SMPO-Q4_K_S.gguf +3 -0
- QVikhr-2.5-1.5B-Instruct-SMPO-Q5_0.gguf +3 -0
- QVikhr-2.5-1.5B-Instruct-SMPO-Q5_K_M.gguf +3 -0
- QVikhr-2.5-1.5B-Instruct-SMPO-Q5_K_S.gguf +3 -0
- QVikhr-2.5-1.5B-Instruct-SMPO-Q6_K.gguf +3 -0
- QVikhr-2.5-1.5B-Instruct-SMPO-Q8_0.gguf +3 -0
- README.md +85 -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 |
+
QVikhr-2.5-1.5B-Instruct-SMPO-Q2_K.gguf filter=lfs diff=lfs merge=lfs -text
|
37 |
+
QVikhr-2.5-1.5B-Instruct-SMPO-Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text
|
38 |
+
QVikhr-2.5-1.5B-Instruct-SMPO-Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text
|
39 |
+
QVikhr-2.5-1.5B-Instruct-SMPO-Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text
|
40 |
+
QVikhr-2.5-1.5B-Instruct-SMPO-Q4_0.gguf filter=lfs diff=lfs merge=lfs -text
|
41 |
+
QVikhr-2.5-1.5B-Instruct-SMPO-Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text
|
42 |
+
QVikhr-2.5-1.5B-Instruct-SMPO-Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text
|
43 |
+
QVikhr-2.5-1.5B-Instruct-SMPO-Q5_0.gguf filter=lfs diff=lfs merge=lfs -text
|
44 |
+
QVikhr-2.5-1.5B-Instruct-SMPO-Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text
|
45 |
+
QVikhr-2.5-1.5B-Instruct-SMPO-Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text
|
46 |
+
QVikhr-2.5-1.5B-Instruct-SMPO-Q6_K.gguf filter=lfs diff=lfs merge=lfs -text
|
47 |
+
QVikhr-2.5-1.5B-Instruct-SMPO-Q8_0.gguf filter=lfs diff=lfs merge=lfs -text
|
QVikhr-2.5-1.5B-Instruct-SMPO-Q2_K.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:f4625fb1cf9f9d91077fc6c6e59137e5fab97102cb998947211e50a277b55a40
|
3 |
+
size 675957152
|
QVikhr-2.5-1.5B-Instruct-SMPO-Q3_K_L.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:cf22dd4999779c612c02dc06a56fc29917b7f61a8f4be6b0f96889efc3bb3979
|
3 |
+
size 879815072
|
QVikhr-2.5-1.5B-Instruct-SMPO-Q3_K_M.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:5bb63c96caf32d7eb7a5a8c01bd7bb73e9ce7dacbfde9b88de2daa8051ee84da
|
3 |
+
size 823830944
|
QVikhr-2.5-1.5B-Instruct-SMPO-Q3_K_S.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:d46320d890b3746cfbd904df677d18020e895bf56b5a2fcb032481cec90e1bc6
|
3 |
+
size 760596896
|
QVikhr-2.5-1.5B-Instruct-SMPO-Q4_0.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:027353252fb8ea9a821fc213eb6ea7df8b3e87b0a9bdbde74dd818e29ad0969b
|
3 |
+
size 934607264
|
QVikhr-2.5-1.5B-Instruct-SMPO-Q4_K_M.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:e3291f69e9e38f759ff36dfc409df8290691e53bb9b95df93787e261cb89ba8e
|
3 |
+
size 985700768
|
QVikhr-2.5-1.5B-Instruct-SMPO-Q4_K_S.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:26c8e1dcd26969eb50bd1cc179de47a4746bec45ccf2cf2e673850acae1eed64
|
3 |
+
size 939964832
|
QVikhr-2.5-1.5B-Instruct-SMPO-Q5_0.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:5dbb1c78608a3a7a6ded12130b954de5c0285ee4ae4132f2c1675bc40b6168a7
|
3 |
+
size 1098381728
|
QVikhr-2.5-1.5B-Instruct-SMPO-Q5_K_M.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:ec3ed2a6f6665b89345c94ffe29eddccaadaf0d49b9a72a8d9817f7bd2d17acd
|
3 |
+
size 1124702624
|
QVikhr-2.5-1.5B-Instruct-SMPO-Q5_K_S.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:9c1c3cd25500768b8ddb697a198e6b78095a17005b53c1719d4619f7e96a0d99
|
3 |
+
size 1098381728
|
QVikhr-2.5-1.5B-Instruct-SMPO-Q6_K.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:aba4b56431a12ea855bcad107bf70a7ad6792c4c8e16180be82e887664109db3
|
3 |
+
size 1272392096
|
QVikhr-2.5-1.5B-Instruct-SMPO-Q8_0.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:45c07344f23baa72e1136fa669da0e0f771c6230cfb6bc12af9134153e3b827e
|
3 |
+
size 1646124480
|
README.md
ADDED
@@ -0,0 +1,85 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
library_name: transformers
|
3 |
+
model_name: Vikhrmodels/QVikhr-2.5-1.5B-Instruct-SMPO
|
4 |
+
base_model: Vikhrmodels/QVikhr-2.5-1.5B-Instruct-SMPO
|
5 |
+
language:
|
6 |
+
- ru
|
7 |
+
- en
|
8 |
+
license: apache-2.0
|
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/QVikhr-2.5-1.5B-Instruct-SMPO - GGUF
|
26 |
+
|
27 |
+
This repo contains GGUF format model files for [Vikhrmodels/QVikhr-2.5-1.5B-Instruct-SMPO](https://huggingface.co/Vikhrmodels/QVikhr-2.5-1.5B-Instruct-SMPO).
|
28 |
+
|
29 |
+
The files were quantized using machines provided by [TensorBlock](https://tensorblock.co/), and they are compatible with llama.cpp as of [commit b4823](https://github.com/ggml-org/llama.cpp/commit/5bbe6a9fe9a8796a9389c85accec89dbc4d91e39).
|
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 |
+
<|im_start|>system
|
41 |
+
{system_prompt}<|im_end|>
|
42 |
+
<|im_start|>user
|
43 |
+
{prompt}<|im_end|>
|
44 |
+
<|im_start|>assistant
|
45 |
+
```
|
46 |
+
|
47 |
+
## Model file specification
|
48 |
+
|
49 |
+
| Filename | Quant type | File Size | Description |
|
50 |
+
| -------- | ---------- | --------- | ----------- |
|
51 |
+
| [QVikhr-2.5-1.5B-Instruct-SMPO-Q2_K.gguf](https://huggingface.co/tensorblock/QVikhr-2.5-1.5B-Instruct-SMPO-GGUF/blob/main/QVikhr-2.5-1.5B-Instruct-SMPO-Q2_K.gguf) | Q2_K | 0.676 GB | smallest, significant quality loss - not recommended for most purposes |
|
52 |
+
| [QVikhr-2.5-1.5B-Instruct-SMPO-Q3_K_S.gguf](https://huggingface.co/tensorblock/QVikhr-2.5-1.5B-Instruct-SMPO-GGUF/blob/main/QVikhr-2.5-1.5B-Instruct-SMPO-Q3_K_S.gguf) | Q3_K_S | 0.761 GB | very small, high quality loss |
|
53 |
+
| [QVikhr-2.5-1.5B-Instruct-SMPO-Q3_K_M.gguf](https://huggingface.co/tensorblock/QVikhr-2.5-1.5B-Instruct-SMPO-GGUF/blob/main/QVikhr-2.5-1.5B-Instruct-SMPO-Q3_K_M.gguf) | Q3_K_M | 0.824 GB | very small, high quality loss |
|
54 |
+
| [QVikhr-2.5-1.5B-Instruct-SMPO-Q3_K_L.gguf](https://huggingface.co/tensorblock/QVikhr-2.5-1.5B-Instruct-SMPO-GGUF/blob/main/QVikhr-2.5-1.5B-Instruct-SMPO-Q3_K_L.gguf) | Q3_K_L | 0.880 GB | small, substantial quality loss |
|
55 |
+
| [QVikhr-2.5-1.5B-Instruct-SMPO-Q4_0.gguf](https://huggingface.co/tensorblock/QVikhr-2.5-1.5B-Instruct-SMPO-GGUF/blob/main/QVikhr-2.5-1.5B-Instruct-SMPO-Q4_0.gguf) | Q4_0 | 0.935 GB | legacy; small, very high quality loss - prefer using Q3_K_M |
|
56 |
+
| [QVikhr-2.5-1.5B-Instruct-SMPO-Q4_K_S.gguf](https://huggingface.co/tensorblock/QVikhr-2.5-1.5B-Instruct-SMPO-GGUF/blob/main/QVikhr-2.5-1.5B-Instruct-SMPO-Q4_K_S.gguf) | Q4_K_S | 0.940 GB | small, greater quality loss |
|
57 |
+
| [QVikhr-2.5-1.5B-Instruct-SMPO-Q4_K_M.gguf](https://huggingface.co/tensorblock/QVikhr-2.5-1.5B-Instruct-SMPO-GGUF/blob/main/QVikhr-2.5-1.5B-Instruct-SMPO-Q4_K_M.gguf) | Q4_K_M | 0.986 GB | medium, balanced quality - recommended |
|
58 |
+
| [QVikhr-2.5-1.5B-Instruct-SMPO-Q5_0.gguf](https://huggingface.co/tensorblock/QVikhr-2.5-1.5B-Instruct-SMPO-GGUF/blob/main/QVikhr-2.5-1.5B-Instruct-SMPO-Q5_0.gguf) | Q5_0 | 1.098 GB | legacy; medium, balanced quality - prefer using Q4_K_M |
|
59 |
+
| [QVikhr-2.5-1.5B-Instruct-SMPO-Q5_K_S.gguf](https://huggingface.co/tensorblock/QVikhr-2.5-1.5B-Instruct-SMPO-GGUF/blob/main/QVikhr-2.5-1.5B-Instruct-SMPO-Q5_K_S.gguf) | Q5_K_S | 1.098 GB | large, low quality loss - recommended |
|
60 |
+
| [QVikhr-2.5-1.5B-Instruct-SMPO-Q5_K_M.gguf](https://huggingface.co/tensorblock/QVikhr-2.5-1.5B-Instruct-SMPO-GGUF/blob/main/QVikhr-2.5-1.5B-Instruct-SMPO-Q5_K_M.gguf) | Q5_K_M | 1.125 GB | large, very low quality loss - recommended |
|
61 |
+
| [QVikhr-2.5-1.5B-Instruct-SMPO-Q6_K.gguf](https://huggingface.co/tensorblock/QVikhr-2.5-1.5B-Instruct-SMPO-GGUF/blob/main/QVikhr-2.5-1.5B-Instruct-SMPO-Q6_K.gguf) | Q6_K | 1.272 GB | very large, extremely low quality loss |
|
62 |
+
| [QVikhr-2.5-1.5B-Instruct-SMPO-Q8_0.gguf](https://huggingface.co/tensorblock/QVikhr-2.5-1.5B-Instruct-SMPO-GGUF/blob/main/QVikhr-2.5-1.5B-Instruct-SMPO-Q8_0.gguf) | Q8_0 | 1.646 GB | very large, extremely low quality loss - not recommended |
|
63 |
+
|
64 |
+
|
65 |
+
## Downloading instruction
|
66 |
+
|
67 |
+
### Command line
|
68 |
+
|
69 |
+
Firstly, install Huggingface Client
|
70 |
+
|
71 |
+
```shell
|
72 |
+
pip install -U "huggingface_hub[cli]"
|
73 |
+
```
|
74 |
+
|
75 |
+
Then, downoad the individual model file the a local directory
|
76 |
+
|
77 |
+
```shell
|
78 |
+
huggingface-cli download tensorblock/QVikhr-2.5-1.5B-Instruct-SMPO-GGUF --include "QVikhr-2.5-1.5B-Instruct-SMPO-Q2_K.gguf" --local-dir MY_LOCAL_DIR
|
79 |
+
```
|
80 |
+
|
81 |
+
If you wanna download multiple model files with a pattern (e.g., `*Q4_K*gguf`), you can try:
|
82 |
+
|
83 |
+
```shell
|
84 |
+
huggingface-cli download tensorblock/QVikhr-2.5-1.5B-Instruct-SMPO-GGUF --local-dir MY_LOCAL_DIR --local-dir-use-symlinks False --include='*Q4_K*gguf'
|
85 |
+
```
|