morriszms commited on
Commit
71f9e89
·
verified ·
1 Parent(s): 75e4743

Upload folder using huggingface_hub

Browse files
.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