nisten commited on
Commit
f020f92
1 Parent(s): 12c3986

Upload 3 files

Browse files

added q6_k auantized for gguf server and 1 shot command

Files changed (4) hide show
  1. .gitattributes +2 -0
  2. README.md +14 -0
  3. mmproj-obsidian-f16.gguf +3 -0
  4. obsidian-q6.gguf +3 -0
.gitattributes CHANGED
@@ -33,3 +33,5 @@ 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
+ mmproj-obsidian-f16.gguf filter=lfs diff=lfs merge=lfs -text
37
+ obsidian-q6.gguf filter=lfs diff=lfs merge=lfs -text
README.md CHANGED
@@ -1,3 +1,17 @@
1
  ---
2
  license: mit
3
  ---
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
  ---
2
  license: mit
3
  ---
4
+
5
+ # NousResearch - Obsidian-3B-V0.5 gguf q6 version by Nisten
6
+
7
+ ## How to Run the server and download the models all in one command, you need ~2.9gb of space
8
+
9
+ To run this on mac or linux, make a new folder, go in it and run this whole in one shot:
10
+
11
+ ```bash
12
+ git clone -b stablelm-support https://github.com/Galunid/llama.cpp.git && \
13
+ cd llama.cpp && \
14
+ make && \
15
+ wget https://huggingface.co/nisten/obsidian-3b-multimodal-q6-gguf/blob/main/obsidian-q6.gguf && \
16
+ wget https://huggingface.co/nisten/obsidian-3b-multimodal-q6-gguf/blob/main/mmproj-obsidian-f16.gguf && \
17
+ ./server -m obsidian-q6.gguf --mmproj mmproj-obsidian-f16.gguf -ngl 42
mmproj-obsidian-f16.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2b62df2eef4461a92c9edb9f312584f872611ffcc0ce213eb6d59792629b6cab
3
+ size 600829088
obsidian-q6.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ca1ae854c5ef58494b9435fb5466897b5bf511dfcdfdd9bcbb6ae0e050d4bee0
3
+ size 2295984640