GGUF
English
TensorBlock
GGUF
Inference Endpoints
morriszms commited on
Commit
361733a
·
verified ·
1 Parent(s): e190c80

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
+ cosmo-1b-Q2_K.gguf filter=lfs diff=lfs merge=lfs -text
37
+ cosmo-1b-Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text
38
+ cosmo-1b-Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text
39
+ cosmo-1b-Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text
40
+ cosmo-1b-Q4_0.gguf filter=lfs diff=lfs merge=lfs -text
41
+ cosmo-1b-Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text
42
+ cosmo-1b-Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text
43
+ cosmo-1b-Q5_0.gguf filter=lfs diff=lfs merge=lfs -text
44
+ cosmo-1b-Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text
45
+ cosmo-1b-Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text
46
+ cosmo-1b-Q6_K.gguf filter=lfs diff=lfs merge=lfs -text
47
+ cosmo-1b-Q8_0.gguf filter=lfs diff=lfs merge=lfs -text
README.md ADDED
@@ -0,0 +1,96 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ license: apache-2.0
3
+ datasets:
4
+ - HuggingFaceTB/cosmopedia
5
+ language:
6
+ - en
7
+ inference:
8
+ parameters:
9
+ temperature: 0.6
10
+ top_p: 0.95
11
+ top_k: 50
12
+ repetition_penalty: 1.2
13
+ widget:
14
+ - text: Photosynthesis is
15
+ example_title: Textbook
16
+ group: Completion
17
+ - text: '<s> [INST] How to take care of plants? [/INST] '
18
+ example_title: Wikihow
19
+ group: Completion
20
+ - text: '<s> [INST] Generate a story about a flying cat [/INST] '
21
+ example_title: Story
22
+ group: Completion
23
+ base_model: HuggingFaceTB/cosmo-1b
24
+ tags:
25
+ - TensorBlock
26
+ - GGUF
27
+ ---
28
+
29
+ <div style="width: auto; margin-left: auto; margin-right: auto">
30
+ <img src="https://i.imgur.com/jC7kdl8.jpeg" alt="TensorBlock" style="width: 100%; min-width: 400px; display: block; margin: auto;">
31
+ </div>
32
+ <div style="display: flex; justify-content: space-between; width: 100%;">
33
+ <div style="display: flex; flex-direction: column; align-items: flex-start;">
34
+ <p style="margin-top: 0.5em; margin-bottom: 0em;">
35
+ 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>
36
+ </p>
37
+ </div>
38
+ </div>
39
+
40
+ ## HuggingFaceTB/cosmo-1b - GGUF
41
+
42
+ This repo contains GGUF format model files for [HuggingFaceTB/cosmo-1b](https://huggingface.co/HuggingFaceTB/cosmo-1b).
43
+
44
+ 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).
45
+
46
+ <div style="text-align: left; margin: 20px 0;">
47
+ <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;">
48
+ Run them on the TensorBlock client using your local machine ↗
49
+ </a>
50
+ </div>
51
+
52
+ ## Prompt template
53
+
54
+ ```
55
+
56
+ ```
57
+
58
+ ## Model file specification
59
+
60
+ | Filename | Quant type | File Size | Description |
61
+ | -------- | ---------- | --------- | ----------- |
62
+ | [cosmo-1b-Q2_K.gguf](https://huggingface.co/tensorblock/cosmo-1b-GGUF/blob/main/cosmo-1b-Q2_K.gguf) | Q2_K | 0.666 GB | smallest, significant quality loss - not recommended for most purposes |
63
+ | [cosmo-1b-Q3_K_S.gguf](https://huggingface.co/tensorblock/cosmo-1b-GGUF/blob/main/cosmo-1b-Q3_K_S.gguf) | Q3_K_S | 0.775 GB | very small, high quality loss |
64
+ | [cosmo-1b-Q3_K_M.gguf](https://huggingface.co/tensorblock/cosmo-1b-GGUF/blob/main/cosmo-1b-Q3_K_M.gguf) | Q3_K_M | 0.858 GB | very small, high quality loss |
65
+ | [cosmo-1b-Q3_K_L.gguf](https://huggingface.co/tensorblock/cosmo-1b-GGUF/blob/main/cosmo-1b-Q3_K_L.gguf) | Q3_K_L | 0.931 GB | small, substantial quality loss |
66
+ | [cosmo-1b-Q4_0.gguf](https://huggingface.co/tensorblock/cosmo-1b-GGUF/blob/main/cosmo-1b-Q4_0.gguf) | Q4_0 | 0.998 GB | legacy; small, very high quality loss - prefer using Q3_K_M |
67
+ | [cosmo-1b-Q4_K_S.gguf](https://huggingface.co/tensorblock/cosmo-1b-GGUF/blob/main/cosmo-1b-Q4_K_S.gguf) | Q4_K_S | 1.006 GB | small, greater quality loss |
68
+ | [cosmo-1b-Q4_K_M.gguf](https://huggingface.co/tensorblock/cosmo-1b-GGUF/blob/main/cosmo-1b-Q4_K_M.gguf) | Q4_K_M | 1.063 GB | medium, balanced quality - recommended |
69
+ | [cosmo-1b-Q5_0.gguf](https://huggingface.co/tensorblock/cosmo-1b-GGUF/blob/main/cosmo-1b-Q5_0.gguf) | Q5_0 | 1.207 GB | legacy; medium, balanced quality - prefer using Q4_K_M |
70
+ | [cosmo-1b-Q5_K_S.gguf](https://huggingface.co/tensorblock/cosmo-1b-GGUF/blob/main/cosmo-1b-Q5_K_S.gguf) | Q5_K_S | 1.207 GB | large, low quality loss - recommended |
71
+ | [cosmo-1b-Q5_K_M.gguf](https://huggingface.co/tensorblock/cosmo-1b-GGUF/blob/main/cosmo-1b-Q5_K_M.gguf) | Q5_K_M | 1.241 GB | large, very low quality loss - recommended |
72
+ | [cosmo-1b-Q6_K.gguf](https://huggingface.co/tensorblock/cosmo-1b-GGUF/blob/main/cosmo-1b-Q6_K.gguf) | Q6_K | 1.430 GB | very large, extremely low quality loss |
73
+ | [cosmo-1b-Q8_0.gguf](https://huggingface.co/tensorblock/cosmo-1b-GGUF/blob/main/cosmo-1b-Q8_0.gguf) | Q8_0 | 1.852 GB | very large, extremely low quality loss - not recommended |
74
+
75
+
76
+ ## Downloading instruction
77
+
78
+ ### Command line
79
+
80
+ Firstly, install Huggingface Client
81
+
82
+ ```shell
83
+ pip install -U "huggingface_hub[cli]"
84
+ ```
85
+
86
+ Then, downoad the individual model file the a local directory
87
+
88
+ ```shell
89
+ huggingface-cli download tensorblock/cosmo-1b-GGUF --include "cosmo-1b-Q2_K.gguf" --local-dir MY_LOCAL_DIR
90
+ ```
91
+
92
+ If you wanna download multiple model files with a pattern (e.g., `*Q4_K*gguf`), you can try:
93
+
94
+ ```shell
95
+ huggingface-cli download tensorblock/cosmo-1b-GGUF --local-dir MY_LOCAL_DIR --local-dir-use-symlinks False --include='*Q4_K*gguf'
96
+ ```
cosmo-1b-Q2_K.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ee1bc76eda53122d1334d90d632fe25876600bbe905d75b02b2641e11058417a
3
+ size 666220576
cosmo-1b-Q3_K_L.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:effaf2c8c0fb59e6139189be7aaa3cadac3ca147553e25615ca913b2bed522f2
3
+ size 930826272
cosmo-1b-Q3_K_M.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:35a31f2d6dbbdcf0e5add45c783ccb39d82541646d84154bad78d6e429da0cb0
3
+ size 858474528
cosmo-1b-Q3_K_S.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d277df1dee8dce61213bec44ece0cb9c259050b080e0cee91ae6db19748e9385
3
+ size 775112736
cosmo-1b-Q4_0.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:efce871f00e71c2ee84805f14472304b53e35cc193fcb672762db560841ef5ca
3
+ size 997726240
cosmo-1b-Q4_K_M.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1d8d4113eebd435366e94d3e603faf7f9f1d501abe58fabcf36236820015be8b
3
+ size 1062606880
cosmo-1b-Q4_K_S.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1fb8127c9fb263d25fa80accf289f5929eed42573952de8a98ecd6067bd01e28
3
+ size 1006114848
cosmo-1b-Q5_0.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2bd9c500f91bdace19c827bdec69157dc2fda324bb017cef8a17fd42e0c897c7
3
+ size 1207244832
cosmo-1b-Q5_K_M.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6ccbfa5de4b53037077837d924186505c0f03843a0ce9f326ad7260b3c8c5398
3
+ size 1240668192
cosmo-1b-Q5_K_S.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:06c6550aa026ffe75ad94bd533792756c71069f15535d56f8940615d27ebac46
3
+ size 1207244832
cosmo-1b-Q6_K.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:28b5c8cd1ae822cd62b88f8366b71ff5b8372d01f5d00521c1c2bcc84a8256f6
3
+ size 1429858336
cosmo-1b-Q8_0.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1ede9a0982bce255b7d4c5100863ce4d8eb72c68cd050bcf6574c3b3f669bc16
3
+ size 1851672608