Hugging Face's logo

tensorblock
/
Cotype-Nano-GGUF

Text Generation
Transformers
GGUF
Russian
English
TensorBlock
GGUF
conversational
Model card Files
xet
 Community
morriszms commited on
Commit
0f35ac0
·
verified ·
1 Parent(s): 2cfcd03

Upload folder using huggingface_hub

Browse files
Files changed (14) hide show
  1. .gitattributes +12 -0
  2. Cotype-Nano-Q2_K.gguf +3 -0
  3. Cotype-Nano-Q3_K_L.gguf +3 -0
  4. Cotype-Nano-Q3_K_M.gguf +3 -0
  5. Cotype-Nano-Q3_K_S.gguf +3 -0
  6. Cotype-Nano-Q4_0.gguf +3 -0
  7. Cotype-Nano-Q4_K_M.gguf +3 -0
  8. Cotype-Nano-Q4_K_S.gguf +3 -0
  9. Cotype-Nano-Q5_0.gguf +3 -0
  10. Cotype-Nano-Q5_K_M.gguf +3 -0
  11. Cotype-Nano-Q5_K_S.gguf +3 -0
  12. Cotype-Nano-Q6_K.gguf +3 -0
  13. Cotype-Nano-Q8_0.gguf +3 -0
  14. README.md +87 -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
+ Cotype-Nano-Q2_K.gguf filter=lfs diff=lfs merge=lfs -text
37
+ Cotype-Nano-Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text
38
+ Cotype-Nano-Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text
39
+ Cotype-Nano-Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text
40
+ Cotype-Nano-Q4_0.gguf filter=lfs diff=lfs merge=lfs -text
41
+ Cotype-Nano-Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text
42
+ Cotype-Nano-Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text
43
+ Cotype-Nano-Q5_0.gguf filter=lfs diff=lfs merge=lfs -text
44
+ Cotype-Nano-Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text
45
+ Cotype-Nano-Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text
46
+ Cotype-Nano-Q6_K.gguf filter=lfs diff=lfs merge=lfs -text
47
+ Cotype-Nano-Q8_0.gguf filter=lfs diff=lfs merge=lfs -text
Cotype-Nano-Q2_K.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0ea43bedbd5c2e12cecdc9810eb0a45f46bc6fb71bb28f1efdb622b74446fcc2
3
+ size 676304384
Cotype-Nano-Q3_K_L.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4403564b98b4b4c8b4c5bfbf29b15101eaf4e1e687bdfb4f39c0d1f53eac391b
3
+ size 880162304
Cotype-Nano-Q3_K_M.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fd51c3e90c7dbce02dd8c1feb355044c43af800cd65f5eba2a69fa40aa7da0f9
3
+ size 824178176
Cotype-Nano-Q3_K_S.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2ced6b1c888d4c23d8e3cbe90c22b61f367f22f614407ce2c87117aa5c615898
3
+ size 760944128
Cotype-Nano-Q4_0.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bd4aac7aae02cb12b666ed63b27ab9f8679e022c948436618c1ccd8e62b3f20a
3
+ size 934954496
Cotype-Nano-Q4_K_M.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f71b3641326cdfc45eb05f45313c2306d9e489188ad6bca424e2fb2eefe508b1
3
+ size 986048000
Cotype-Nano-Q4_K_S.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:be5a97cda815752d45832d8ee5c79beb79c3ae1f96e8c923a8dfcb00f240a1b5
3
+ size 940312064
Cotype-Nano-Q5_0.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c012880d412cae7b2e2c1b2ffe0ec057d0fb92b9f322354c04f0f35148bdf564
3
+ size 1098728960
Cotype-Nano-Q5_K_M.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:48db2ea34d71b8664097ca93e4db132742e0ad51092de66a049be23ae6c30999
3
+ size 1125049856
Cotype-Nano-Q5_K_S.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a2fb16556134a989bd2ce759a08ba0b029f6fda9d21366f6ad5c7d067c08c681
3
+ size 1098728960
Cotype-Nano-Q6_K.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:99bd3068d5b71e218ffc9bbe0a277f8a0f7f65f6960abb9c1b36053d497a9241
3
+ size 1272739328
Cotype-Nano-Q8_0.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e946a7990fa05372857ef1fd4a8439b6805cd2c6e32e195f1cdabc2494ab2aa1
3
+ size 1646572544
README.md ADDED
@@ -0,0 +1,87 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ library_name: transformers
3
+ language:
4
+ - ru
5
+ - en
6
+ pipeline_tag: text-generation
7
+ license: other
8
+ license_name: apache-2.0
9
+ license_link: https://huggingface.co/MTSAIR/Cotype-Nano/blob/main/Apache%20License%20MTS%20AI.docx
10
+ base_model: MTSAIR/Cotype-Nano
11
+ tags:
12
+ - TensorBlock
13
+ - GGUF
14
+ ---
15
+
16
+ <div style="width: auto; margin-left: auto; margin-right: auto">
17
+ <img src="https://i.imgur.com/jC7kdl8.jpeg" alt="TensorBlock" style="width: 100%; min-width: 400px; display: block; margin: auto;">
18
+ </div>
19
+ <div style="display: flex; justify-content: space-between; width: 100%;">
20
+ <div style="display: flex; flex-direction: column; align-items: flex-start;">
21
+ <p style="margin-top: 0.5em; margin-bottom: 0em;">
22
+ 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>
23
+ </p>
24
+ </div>
25
+ </div>
26
+
27
+ ## MTSAIR/Cotype-Nano - GGUF
28
+
29
+ This repo contains GGUF format model files for [MTSAIR/Cotype-Nano](https://huggingface.co/MTSAIR/Cotype-Nano).
30
+
31
+ 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).
32
+
33
+ <div style="text-align: left; margin: 20px 0;">
34
+ <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;">
35
+ Run them on the TensorBlock client using your local machine ↗
36
+ </a>
37
+ </div>
38
+
39
+ ## Prompt template
40
+
41
+ ```
42
+ <|im_start|>system
43
+ {system_prompt}<|im_end|>
44
+ <|im_start|>user
45
+ {prompt}<|im_end|>
46
+ <|im_start|>assistant
47
+ ```
48
+
49
+ ## Model file specification
50
+
51
+ | Filename | Quant type | File Size | Description |
52
+ | -------- | ---------- | --------- | ----------- |
53
+ | [Cotype-Nano-Q2_K.gguf](https://huggingface.co/tensorblock/Cotype-Nano-GGUF/blob/main/Cotype-Nano-Q2_K.gguf) | Q2_K | 0.676 GB | smallest, significant quality loss - not recommended for most purposes |
54
+ | [Cotype-Nano-Q3_K_S.gguf](https://huggingface.co/tensorblock/Cotype-Nano-GGUF/blob/main/Cotype-Nano-Q3_K_S.gguf) | Q3_K_S | 0.761 GB | very small, high quality loss |
55
+ | [Cotype-Nano-Q3_K_M.gguf](https://huggingface.co/tensorblock/Cotype-Nano-GGUF/blob/main/Cotype-Nano-Q3_K_M.gguf) | Q3_K_M | 0.824 GB | very small, high quality loss |
56
+ | [Cotype-Nano-Q3_K_L.gguf](https://huggingface.co/tensorblock/Cotype-Nano-GGUF/blob/main/Cotype-Nano-Q3_K_L.gguf) | Q3_K_L | 0.880 GB | small, substantial quality loss |
57
+ | [Cotype-Nano-Q4_0.gguf](https://huggingface.co/tensorblock/Cotype-Nano-GGUF/blob/main/Cotype-Nano-Q4_0.gguf) | Q4_0 | 0.935 GB | legacy; small, very high quality loss - prefer using Q3_K_M |
58
+ | [Cotype-Nano-Q4_K_S.gguf](https://huggingface.co/tensorblock/Cotype-Nano-GGUF/blob/main/Cotype-Nano-Q4_K_S.gguf) | Q4_K_S | 0.940 GB | small, greater quality loss |
59
+ | [Cotype-Nano-Q4_K_M.gguf](https://huggingface.co/tensorblock/Cotype-Nano-GGUF/blob/main/Cotype-Nano-Q4_K_M.gguf) | Q4_K_M | 0.986 GB | medium, balanced quality - recommended |
60
+ | [Cotype-Nano-Q5_0.gguf](https://huggingface.co/tensorblock/Cotype-Nano-GGUF/blob/main/Cotype-Nano-Q5_0.gguf) | Q5_0 | 1.099 GB | legacy; medium, balanced quality - prefer using Q4_K_M |
61
+ | [Cotype-Nano-Q5_K_S.gguf](https://huggingface.co/tensorblock/Cotype-Nano-GGUF/blob/main/Cotype-Nano-Q5_K_S.gguf) | Q5_K_S | 1.099 GB | large, low quality loss - recommended |
62
+ | [Cotype-Nano-Q5_K_M.gguf](https://huggingface.co/tensorblock/Cotype-Nano-GGUF/blob/main/Cotype-Nano-Q5_K_M.gguf) | Q5_K_M | 1.125 GB | large, very low quality loss - recommended |
63
+ | [Cotype-Nano-Q6_K.gguf](https://huggingface.co/tensorblock/Cotype-Nano-GGUF/blob/main/Cotype-Nano-Q6_K.gguf) | Q6_K | 1.273 GB | very large, extremely low quality loss |
64
+ | [Cotype-Nano-Q8_0.gguf](https://huggingface.co/tensorblock/Cotype-Nano-GGUF/blob/main/Cotype-Nano-Q8_0.gguf) | Q8_0 | 1.647 GB | very large, extremely low quality loss - not recommended |
65
+
66
+
67
+ ## Downloading instruction
68
+
69
+ ### Command line
70
+
71
+ Firstly, install Huggingface Client
72
+
73
+ ```shell
74
+ pip install -U "huggingface_hub[cli]"
75
+ ```
76
+
77
+ Then, downoad the individual model file the a local directory
78
+
79
+ ```shell
80
+ huggingface-cli download tensorblock/Cotype-Nano-GGUF --include "Cotype-Nano-Q2_K.gguf" --local-dir MY_LOCAL_DIR
81
+ ```
82
+
83
+ If you wanna download multiple model files with a pattern (e.g., `*Q4_K*gguf`), you can try:
84
+
85
+ ```shell
86
+ huggingface-cli download tensorblock/Cotype-Nano-GGUF --local-dir MY_LOCAL_DIR --local-dir-use-symlinks False --include='*Q4_K*gguf'
87
+ ```