Upload folder using huggingface_hub
Browse files- .gitattributes +12 -0
- README.md +118 -0
- cogito-v1-preview-llama-3B-Q2_K.gguf +3 -0
- cogito-v1-preview-llama-3B-Q3_K_L.gguf +3 -0
- cogito-v1-preview-llama-3B-Q3_K_M.gguf +3 -0
- cogito-v1-preview-llama-3B-Q3_K_S.gguf +3 -0
- cogito-v1-preview-llama-3B-Q4_0.gguf +3 -0
- cogito-v1-preview-llama-3B-Q4_K_M.gguf +3 -0
- cogito-v1-preview-llama-3B-Q4_K_S.gguf +3 -0
- cogito-v1-preview-llama-3B-Q5_0.gguf +3 -0
- cogito-v1-preview-llama-3B-Q5_K_M.gguf +3 -0
- cogito-v1-preview-llama-3B-Q5_K_S.gguf +3 -0
- cogito-v1-preview-llama-3B-Q6_K.gguf +3 -0
- cogito-v1-preview-llama-3B-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 |
+
cogito-v1-preview-llama-3B-Q2_K.gguf filter=lfs diff=lfs merge=lfs -text
|
37 |
+
cogito-v1-preview-llama-3B-Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text
|
38 |
+
cogito-v1-preview-llama-3B-Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text
|
39 |
+
cogito-v1-preview-llama-3B-Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text
|
40 |
+
cogito-v1-preview-llama-3B-Q4_0.gguf filter=lfs diff=lfs merge=lfs -text
|
41 |
+
cogito-v1-preview-llama-3B-Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text
|
42 |
+
cogito-v1-preview-llama-3B-Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text
|
43 |
+
cogito-v1-preview-llama-3B-Q5_0.gguf filter=lfs diff=lfs merge=lfs -text
|
44 |
+
cogito-v1-preview-llama-3B-Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text
|
45 |
+
cogito-v1-preview-llama-3B-Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text
|
46 |
+
cogito-v1-preview-llama-3B-Q6_K.gguf filter=lfs diff=lfs merge=lfs -text
|
47 |
+
cogito-v1-preview-llama-3B-Q8_0.gguf filter=lfs diff=lfs merge=lfs -text
|
README.md
ADDED
@@ -0,0 +1,118 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
license: llama3.2
|
3 |
+
library_name: transformers
|
4 |
+
base_model: deepcogito/cogito-v1-preview-llama-3B
|
5 |
+
pipeline_tag: text-generation
|
6 |
+
tags:
|
7 |
+
- TensorBlock
|
8 |
+
- GGUF
|
9 |
+
---
|
10 |
+
|
11 |
+
<div style="width: auto; margin-left: auto; margin-right: auto">
|
12 |
+
<img src="https://i.imgur.com/jC7kdl8.jpeg" alt="TensorBlock" style="width: 100%; min-width: 400px; display: block; margin: auto;">
|
13 |
+
</div>
|
14 |
+
<div style="display: flex; justify-content: space-between; width: 100%;">
|
15 |
+
<div style="display: flex; flex-direction: column; align-items: flex-start;">
|
16 |
+
<p style="margin-top: 0.5em; margin-bottom: 0em;">
|
17 |
+
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>
|
18 |
+
</p>
|
19 |
+
</div>
|
20 |
+
</div>
|
21 |
+
|
22 |
+
## deepcogito/cogito-v1-preview-llama-3B - GGUF
|
23 |
+
|
24 |
+
This repo contains GGUF format model files for [deepcogito/cogito-v1-preview-llama-3B](https://huggingface.co/deepcogito/cogito-v1-preview-llama-3B).
|
25 |
+
|
26 |
+
The files were quantized using machines provided by [TensorBlock](https://tensorblock.co/), and they are compatible with llama.cpp as of [commit b5165](https://github.com/ggml-org/llama.cpp/commit/1d735c0b4fa0551c51c2f4ac888dd9a01f447985).
|
27 |
+
|
28 |
+
## Our projects
|
29 |
+
<table border="1" cellspacing="0" cellpadding="10">
|
30 |
+
<tr>
|
31 |
+
<th style="font-size: 25px;">Awesome MCP Servers</th>
|
32 |
+
<th style="font-size: 25px;">TensorBlock Studio</th>
|
33 |
+
</tr>
|
34 |
+
<tr>
|
35 |
+
<th><img src="https://imgur.com/2Xov7B7.jpeg" alt="Project A" width="450"/></th>
|
36 |
+
<th><img src="https://imgur.com/pJcmF5u.jpeg" alt="Project B" width="450"/></th>
|
37 |
+
</tr>
|
38 |
+
<tr>
|
39 |
+
<th>A comprehensive collection of Model Context Protocol (MCP) servers.</th>
|
40 |
+
<th>A lightweight, open, and extensible multi-LLM interaction studio.</th>
|
41 |
+
</tr>
|
42 |
+
<tr>
|
43 |
+
<th>
|
44 |
+
<a href="https://github.com/TensorBlock/awesome-mcp-servers" target="_blank" style="
|
45 |
+
display: inline-block;
|
46 |
+
padding: 8px 16px;
|
47 |
+
background-color: #FF7F50;
|
48 |
+
color: white;
|
49 |
+
text-decoration: none;
|
50 |
+
border-radius: 6px;
|
51 |
+
font-weight: bold;
|
52 |
+
font-family: sans-serif;
|
53 |
+
">👀 See what we built 👀</a>
|
54 |
+
</th>
|
55 |
+
<th>
|
56 |
+
<a href="https://github.com/TensorBlock/TensorBlock-Studio" target="_blank" style="
|
57 |
+
display: inline-block;
|
58 |
+
padding: 8px 16px;
|
59 |
+
background-color: #FF7F50;
|
60 |
+
color: white;
|
61 |
+
text-decoration: none;
|
62 |
+
border-radius: 6px;
|
63 |
+
font-weight: bold;
|
64 |
+
font-family: sans-serif;
|
65 |
+
">👀 See what we built 👀</a>
|
66 |
+
</th>
|
67 |
+
</tr>
|
68 |
+
</table>
|
69 |
+
|
70 |
+
## Prompt template
|
71 |
+
|
72 |
+
```
|
73 |
+
<|begin_of_text|><|start_header_id|>system<|end_header_id|>
|
74 |
+
|
75 |
+
{system_prompt}<|eot_id|><|start_header_id|>user<|end_header_id|>
|
76 |
+
|
77 |
+
{prompt}<|eot_id|><|start_header_id|>assistant<|end_header_id|>
|
78 |
+
```
|
79 |
+
|
80 |
+
## Model file specification
|
81 |
+
|
82 |
+
| Filename | Quant type | File Size | Description |
|
83 |
+
| -------- | ---------- | --------- | ----------- |
|
84 |
+
| [cogito-v1-preview-llama-3B-Q2_K.gguf](https://huggingface.co/tensorblock/deepcogito_cogito-v1-preview-llama-3B-GGUF/blob/main/cogito-v1-preview-llama-3B-Q2_K.gguf) | Q2_K | 1.493 GB | smallest, significant quality loss - not recommended for most purposes |
|
85 |
+
| [cogito-v1-preview-llama-3B-Q3_K_S.gguf](https://huggingface.co/tensorblock/deepcogito_cogito-v1-preview-llama-3B-GGUF/blob/main/cogito-v1-preview-llama-3B-Q3_K_S.gguf) | Q3_K_S | 1.712 GB | very small, high quality loss |
|
86 |
+
| [cogito-v1-preview-llama-3B-Q3_K_M.gguf](https://huggingface.co/tensorblock/deepcogito_cogito-v1-preview-llama-3B-GGUF/blob/main/cogito-v1-preview-llama-3B-Q3_K_M.gguf) | Q3_K_M | 1.856 GB | very small, high quality loss |
|
87 |
+
| [cogito-v1-preview-llama-3B-Q3_K_L.gguf](https://huggingface.co/tensorblock/deepcogito_cogito-v1-preview-llama-3B-GGUF/blob/main/cogito-v1-preview-llama-3B-Q3_K_L.gguf) | Q3_K_L | 1.985 GB | small, substantial quality loss |
|
88 |
+
| [cogito-v1-preview-llama-3B-Q4_0.gguf](https://huggingface.co/tensorblock/deepcogito_cogito-v1-preview-llama-3B-GGUF/blob/main/cogito-v1-preview-llama-3B-Q4_0.gguf) | Q4_0 | 2.139 GB | legacy; small, very high quality loss - prefer using Q3_K_M |
|
89 |
+
| [cogito-v1-preview-llama-3B-Q4_K_S.gguf](https://huggingface.co/tensorblock/deepcogito_cogito-v1-preview-llama-3B-GGUF/blob/main/cogito-v1-preview-llama-3B-Q4_K_S.gguf) | Q4_K_S | 2.150 GB | small, greater quality loss |
|
90 |
+
| [cogito-v1-preview-llama-3B-Q4_K_M.gguf](https://huggingface.co/tensorblock/deepcogito_cogito-v1-preview-llama-3B-GGUF/blob/main/cogito-v1-preview-llama-3B-Q4_K_M.gguf) | Q4_K_M | 2.241 GB | medium, balanced quality - recommended |
|
91 |
+
| [cogito-v1-preview-llama-3B-Q5_0.gguf](https://huggingface.co/tensorblock/deepcogito_cogito-v1-preview-llama-3B-GGUF/blob/main/cogito-v1-preview-llama-3B-Q5_0.gguf) | Q5_0 | 2.540 GB | legacy; medium, balanced quality - prefer using Q4_K_M |
|
92 |
+
| [cogito-v1-preview-llama-3B-Q5_K_S.gguf](https://huggingface.co/tensorblock/deepcogito_cogito-v1-preview-llama-3B-GGUF/blob/main/cogito-v1-preview-llama-3B-Q5_K_S.gguf) | Q5_K_S | 2.540 GB | large, low quality loss - recommended |
|
93 |
+
| [cogito-v1-preview-llama-3B-Q5_K_M.gguf](https://huggingface.co/tensorblock/deepcogito_cogito-v1-preview-llama-3B-GGUF/blob/main/cogito-v1-preview-llama-3B-Q5_K_M.gguf) | Q5_K_M | 2.593 GB | large, very low quality loss - recommended |
|
94 |
+
| [cogito-v1-preview-llama-3B-Q6_K.gguf](https://huggingface.co/tensorblock/deepcogito_cogito-v1-preview-llama-3B-GGUF/blob/main/cogito-v1-preview-llama-3B-Q6_K.gguf) | Q6_K | 2.967 GB | very large, extremely low quality loss |
|
95 |
+
| [cogito-v1-preview-llama-3B-Q8_0.gguf](https://huggingface.co/tensorblock/deepcogito_cogito-v1-preview-llama-3B-GGUF/blob/main/cogito-v1-preview-llama-3B-Q8_0.gguf) | Q8_0 | 3.841 GB | very large, extremely low quality loss - not recommended |
|
96 |
+
|
97 |
+
|
98 |
+
## Downloading instruction
|
99 |
+
|
100 |
+
### Command line
|
101 |
+
|
102 |
+
Firstly, install Huggingface Client
|
103 |
+
|
104 |
+
```shell
|
105 |
+
pip install -U "huggingface_hub[cli]"
|
106 |
+
```
|
107 |
+
|
108 |
+
Then, downoad the individual model file the a local directory
|
109 |
+
|
110 |
+
```shell
|
111 |
+
huggingface-cli download tensorblock/deepcogito_cogito-v1-preview-llama-3B-GGUF --include "cogito-v1-preview-llama-3B-Q2_K.gguf" --local-dir MY_LOCAL_DIR
|
112 |
+
```
|
113 |
+
|
114 |
+
If you wanna download multiple model files with a pattern (e.g., `*Q4_K*gguf`), you can try:
|
115 |
+
|
116 |
+
```shell
|
117 |
+
huggingface-cli download tensorblock/deepcogito_cogito-v1-preview-llama-3B-GGUF --local-dir MY_LOCAL_DIR --local-dir-use-symlinks False --include='*Q4_K*gguf'
|
118 |
+
```
|
cogito-v1-preview-llama-3B-Q2_K.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:6e872fbe89fbcb98cbdd5e651930e78cb682d9fa03480149e0a62807608c7e58
|
3 |
+
size 1493218240
|
cogito-v1-preview-llama-3B-Q3_K_L.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:ab8de3b058e3cec0bd5ffedd1ebe416670d2101067ee3f4a7dbd7fedf4fff46e
|
3 |
+
size 1984646080
|
cogito-v1-preview-llama-3B-Q3_K_M.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:e38c81deb70c5d6bacf1731ab19751cf989e8eb626648b0e79e0d202f45de7a3
|
3 |
+
size 1856457664
|
cogito-v1-preview-llama-3B-Q3_K_S.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:97c5c06c5fd17e2199b3b378c6247bb29a680ceb67647fc64c9e0d4b775ac0b9
|
3 |
+
size 1712147392
|
cogito-v1-preview-llama-3B-Q4_0.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:936007a18f969cb32d6ec10c2e2a3efa8150fb347bac0d722a823c41696a880e
|
3 |
+
size 2138817472
|
cogito-v1-preview-llama-3B-Q4_K_M.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:93b3fbddecf76462650385a0582fcdf572ba66744b135a3a6f8cab04129af2e1
|
3 |
+
size 2241004480
|
cogito-v1-preview-llama-3B-Q4_K_S.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:018a54824cb4baeafe1eb26c71607a0925f781c5a1312a0540308abf277fa8f3
|
3 |
+
size 2149827520
|
cogito-v1-preview-llama-3B-Q5_0.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:c2efcc0995fba01cfb66e4d3b7dc0712b9851c40a2267ae559453691f6b04ce4
|
3 |
+
size 2540389312
|
cogito-v1-preview-llama-3B-Q5_K_M.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:6403d934949da5f2cdebb2c40936ff3a08b6cce139742bc5468041b8f702a24d
|
3 |
+
size 2593031104
|
cogito-v1-preview-llama-3B-Q5_K_S.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:8d14cf6ba914824bb63ee857e77ac6cade0d7445df063b9b16e7569b4ac2f8fd
|
3 |
+
size 2540389312
|
cogito-v1-preview-llama-3B-Q6_K.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:73d3f6c5cd9a95a87643e76f2429de3c865669aa680f011630ac5f40d73a1aac
|
3 |
+
size 2967059392
|
cogito-v1-preview-llama-3B-Q8_0.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:1fffd53695fc25ad64079227cca1e5ce9b41262174b5c4ef0f35b35d971da0f1
|
3 |
+
size 3840527296
|