Text Generation
Transformers
GGUF
TensorBlock
GGUF
conversational
morriszms commited on
Commit
f93fa8c
Β·
verified Β·
1 Parent(s): 2d7b86f

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
+ Autogressive-32B-Q2_K.gguf filter=lfs diff=lfs merge=lfs -text
37
+ Autogressive-32B-Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text
38
+ Autogressive-32B-Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text
39
+ Autogressive-32B-Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text
40
+ Autogressive-32B-Q4_0.gguf filter=lfs diff=lfs merge=lfs -text
41
+ Autogressive-32B-Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text
42
+ Autogressive-32B-Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text
43
+ Autogressive-32B-Q5_0.gguf filter=lfs diff=lfs merge=lfs -text
44
+ Autogressive-32B-Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text
45
+ Autogressive-32B-Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text
46
+ Autogressive-32B-Q6_K.gguf filter=lfs diff=lfs merge=lfs -text
47
+ Autogressive-32B-Q8_0.gguf filter=lfs diff=lfs merge=lfs -text
Autogressive-32B-Q2_K.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d0bccf4172392b799c8cc477699d7204fc28bb5ccc14f5960b46c99c9315c469
3
+ size 12313099488
Autogressive-32B-Q3_K_L.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e70bbc0385d2e0110f25b36cfa707e44cd10c286f29fd503eb249f36b8f61d33
3
+ size 17247079648
Autogressive-32B-Q3_K_M.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:64e625f4dc9c5b5f670d931d5e8ca4edd9d1c5bef0b843fbcaf08b047aa17cb4
3
+ size 15935048928
Autogressive-32B-Q3_K_S.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:32126a49e1eaed386d3daa92eb42619582309aedae3a2e5f2c46a73acfb485fb
3
+ size 14392331488
Autogressive-32B-Q4_0.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:dbf32bf8b27decf510fac185b56bdccc242a077ef04308a2398525590989078c
3
+ size 18640231648
Autogressive-32B-Q4_K_M.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e3010450483f47f0df749b0793e90371d53c00c50282e29f41bbe872e20a6a1c
3
+ size 19851336928
Autogressive-32B-Q4_K_S.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3fbcc0e8ae7b02656a1587bd9e4c22fb906d76fb35a4d0d20edcf13945ab91bc
3
+ size 18784410848
Autogressive-32B-Q5_0.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d095e82c56e584849565c430123acf156bff21d27a4ea5a80b5fcec052416fc2
3
+ size 22638255328
Autogressive-32B-Q5_K_M.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:674ee7e412cf75a698967510fde63eaa7e6510be4bb2c5bc41f81afee725f06f
3
+ size 23262158048
Autogressive-32B-Q5_K_S.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0f3727c1bdf2256f0f59c32c299ad8ede3a12df0ab3b60d54ee4fd138f8e99a3
3
+ size 22638255328
Autogressive-32B-Q6_K.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:023db398b4efdf9a5221836f90e231218a3c9006a174993e252044bca1d0d5f6
3
+ size 26886155488
Autogressive-32B-Q8_0.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:27e0fe9d5f5b06c844eea9c88e1d6ed362f32fc44fbf60e06d51385749c5feee
3
+ size 34820885728
README.md ADDED
@@ -0,0 +1,154 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ license: apache-2.0
3
+ datasets:
4
+ - Multiverse4FM/Autoregressive-1K-mixed
5
+ - Multiverse4FM/Multiverse-1K
6
+ - simplescaling/s1K-1.1
7
+ base_model: Multiverse4FM/Autogressive-32B
8
+ pipeline_tag: text-generation
9
+ library_name: transformers
10
+ tags:
11
+ - TensorBlock
12
+ - GGUF
13
+ ---
14
+
15
+ <div style="width: auto; margin-left: auto; margin-right: auto">
16
+ <img src="https://i.imgur.com/jC7kdl8.jpeg" alt="TensorBlock" style="width: 100%; min-width: 400px; display: block; margin: auto;">
17
+ </div>
18
+
19
+ [![Website](https://img.shields.io/badge/Website-tensorblock.co-blue?logo=google-chrome&logoColor=white)](https://tensorblock.co)
20
+ [![Twitter](https://img.shields.io/twitter/follow/tensorblock_aoi?style=social)](https://twitter.com/tensorblock_aoi)
21
+ [![Discord](https://img.shields.io/badge/Discord-Join%20Us-5865F2?logo=discord&logoColor=white)](https://discord.gg/Ej5NmeHFf2)
22
+ [![GitHub](https://img.shields.io/badge/GitHub-TensorBlock-black?logo=github&logoColor=white)](https://github.com/TensorBlock)
23
+ [![Telegram](https://img.shields.io/badge/Telegram-Group-blue?logo=telegram)](https://t.me/TensorBlock)
24
+
25
+
26
+ ## Multiverse4FM/Autogressive-32B - GGUF
27
+
28
+ <div style="text-align: left; margin: 20px 0;">
29
+ <a href="https://discord.com/invite/Ej5NmeHFf2" style="display: inline-block; padding: 10px 20px; background-color: #5865F2; color: white; text-decoration: none; border-radius: 5px; font-weight: bold;">
30
+ Join our Discord to learn more about what we're building β†—
31
+ </a>
32
+ </div>
33
+
34
+ This repo contains GGUF format model files for [Multiverse4FM/Autogressive-32B](https://huggingface.co/Multiverse4FM/Autogressive-32B).
35
+
36
+ The files were quantized using machines provided by [TensorBlock](https://tensorblock.co/), and they are compatible with llama.cpp as of [commit b5753](https://github.com/ggml-org/llama.cpp/commit/73e53dc834c0a2336cd104473af6897197b96277).
37
+
38
+ ## Our projects
39
+ <table border="1" cellspacing="0" cellpadding="10">
40
+ <tr>
41
+ <th colspan="2" style="font-size: 25px;">Forge</th>
42
+ </tr>
43
+ <tr>
44
+ <th colspan="2">
45
+ <img src="https://imgur.com/faI5UKh.jpeg" alt="Forge Project" width="900"/>
46
+ </th>
47
+ </tr>
48
+ <tr>
49
+ <th colspan="2">An OpenAI-compatible multi-provider routing layer.</th>
50
+ </tr>
51
+ <tr>
52
+ <th colspan="2">
53
+ <a href="https://github.com/TensorBlock/forge" target="_blank" style="
54
+ display: inline-block;
55
+ padding: 8px 16px;
56
+ background-color: #FF7F50;
57
+ color: white;
58
+ text-decoration: none;
59
+ border-radius: 6px;
60
+ font-weight: bold;
61
+ font-family: sans-serif;
62
+ ">πŸš€ Try it now! πŸš€</a>
63
+ </th>
64
+ </tr>
65
+
66
+ <tr>
67
+ <th style="font-size: 25px;">Awesome MCP Servers</th>
68
+ <th style="font-size: 25px;">TensorBlock Studio</th>
69
+ </tr>
70
+ <tr>
71
+ <th><img src="https://imgur.com/2Xov7B7.jpeg" alt="MCP Servers" width="450"/></th>
72
+ <th><img src="https://imgur.com/pJcmF5u.jpeg" alt="Studio" width="450"/></th>
73
+ </tr>
74
+ <tr>
75
+ <th>A comprehensive collection of Model Context Protocol (MCP) servers.</th>
76
+ <th>A lightweight, open, and extensible multi-LLM interaction studio.</th>
77
+ </tr>
78
+ <tr>
79
+ <th>
80
+ <a href="https://github.com/TensorBlock/awesome-mcp-servers" target="_blank" style="
81
+ display: inline-block;
82
+ padding: 8px 16px;
83
+ background-color: #FF7F50;
84
+ color: white;
85
+ text-decoration: none;
86
+ border-radius: 6px;
87
+ font-weight: bold;
88
+ font-family: sans-serif;
89
+ ">πŸ‘€ See what we built πŸ‘€</a>
90
+ </th>
91
+ <th>
92
+ <a href="https://github.com/TensorBlock/TensorBlock-Studio" target="_blank" style="
93
+ display: inline-block;
94
+ padding: 8px 16px;
95
+ background-color: #FF7F50;
96
+ color: white;
97
+ text-decoration: none;
98
+ border-radius: 6px;
99
+ font-weight: bold;
100
+ font-family: sans-serif;
101
+ ">πŸ‘€ See what we built πŸ‘€</a>
102
+ </th>
103
+ </tr>
104
+ </table>
105
+
106
+ ## Prompt template
107
+
108
+ ```
109
+ <|im_start|>system
110
+ {system_prompt}<|im_end|>
111
+ <|im_start|>user
112
+ {prompt}<|im_end|>
113
+ <|im_start|>assistant
114
+ ```
115
+
116
+ ## Model file specification
117
+
118
+ | Filename | Quant type | File Size | Description |
119
+ | -------- | ---------- | --------- | ----------- |
120
+ | [Autogressive-32B-Q2_K.gguf](https://huggingface.co/tensorblock/Multiverse4FM_Autogressive-32B-GGUF/blob/main/Autogressive-32B-Q2_K.gguf) | Q2_K | 12.313 GB | smallest, significant quality loss - not recommended for most purposes |
121
+ | [Autogressive-32B-Q3_K_S.gguf](https://huggingface.co/tensorblock/Multiverse4FM_Autogressive-32B-GGUF/blob/main/Autogressive-32B-Q3_K_S.gguf) | Q3_K_S | 14.392 GB | very small, high quality loss |
122
+ | [Autogressive-32B-Q3_K_M.gguf](https://huggingface.co/tensorblock/Multiverse4FM_Autogressive-32B-GGUF/blob/main/Autogressive-32B-Q3_K_M.gguf) | Q3_K_M | 15.935 GB | very small, high quality loss |
123
+ | [Autogressive-32B-Q3_K_L.gguf](https://huggingface.co/tensorblock/Multiverse4FM_Autogressive-32B-GGUF/blob/main/Autogressive-32B-Q3_K_L.gguf) | Q3_K_L | 17.247 GB | small, substantial quality loss |
124
+ | [Autogressive-32B-Q4_0.gguf](https://huggingface.co/tensorblock/Multiverse4FM_Autogressive-32B-GGUF/blob/main/Autogressive-32B-Q4_0.gguf) | Q4_0 | 18.640 GB | legacy; small, very high quality loss - prefer using Q3_K_M |
125
+ | [Autogressive-32B-Q4_K_S.gguf](https://huggingface.co/tensorblock/Multiverse4FM_Autogressive-32B-GGUF/blob/main/Autogressive-32B-Q4_K_S.gguf) | Q4_K_S | 18.784 GB | small, greater quality loss |
126
+ | [Autogressive-32B-Q4_K_M.gguf](https://huggingface.co/tensorblock/Multiverse4FM_Autogressive-32B-GGUF/blob/main/Autogressive-32B-Q4_K_M.gguf) | Q4_K_M | 19.851 GB | medium, balanced quality - recommended |
127
+ | [Autogressive-32B-Q5_0.gguf](https://huggingface.co/tensorblock/Multiverse4FM_Autogressive-32B-GGUF/blob/main/Autogressive-32B-Q5_0.gguf) | Q5_0 | 22.638 GB | legacy; medium, balanced quality - prefer using Q4_K_M |
128
+ | [Autogressive-32B-Q5_K_S.gguf](https://huggingface.co/tensorblock/Multiverse4FM_Autogressive-32B-GGUF/blob/main/Autogressive-32B-Q5_K_S.gguf) | Q5_K_S | 22.638 GB | large, low quality loss - recommended |
129
+ | [Autogressive-32B-Q5_K_M.gguf](https://huggingface.co/tensorblock/Multiverse4FM_Autogressive-32B-GGUF/blob/main/Autogressive-32B-Q5_K_M.gguf) | Q5_K_M | 23.262 GB | large, very low quality loss - recommended |
130
+ | [Autogressive-32B-Q6_K.gguf](https://huggingface.co/tensorblock/Multiverse4FM_Autogressive-32B-GGUF/blob/main/Autogressive-32B-Q6_K.gguf) | Q6_K | 26.886 GB | very large, extremely low quality loss |
131
+ | [Autogressive-32B-Q8_0.gguf](https://huggingface.co/tensorblock/Multiverse4FM_Autogressive-32B-GGUF/blob/main/Autogressive-32B-Q8_0.gguf) | Q8_0 | 34.821 GB | very large, extremely low quality loss - not recommended |
132
+
133
+
134
+ ## Downloading instruction
135
+
136
+ ### Command line
137
+
138
+ Firstly, install Huggingface Client
139
+
140
+ ```shell
141
+ pip install -U "huggingface_hub[cli]"
142
+ ```
143
+
144
+ Then, downoad the individual model file the a local directory
145
+
146
+ ```shell
147
+ huggingface-cli download tensorblock/Multiverse4FM_Autogressive-32B-GGUF --include "Autogressive-32B-Q2_K.gguf" --local-dir MY_LOCAL_DIR
148
+ ```
149
+
150
+ If you wanna download multiple model files with a pattern (e.g., `*Q4_K*gguf`), you can try:
151
+
152
+ ```shell
153
+ huggingface-cli download tensorblock/Multiverse4FM_Autogressive-32B-GGUF --local-dir MY_LOCAL_DIR --local-dir-use-symlinks False --include='*Q4_K*gguf'
154
+ ```