Downloads · 30 days
166
1% of all-time downloads
obsidian-3b-multimodal-q6-gguf
nisten/obsidian-3b-multimodal-q6-gguf
obsidian-3b-multimodal-q6-gguf is a machine learning model from nisten. Use it for the machine learning task on the model card, and read the license before you ship it in a product. The card lists the license as mit.
To run the server inside /llama.cpp/ folder IN YOUR TERMINAL
All-time downloads
19.8K
Public
Repo size
8.5 GB
Likes
71
Public
Repo makeup
Click a slice to open those files.
.gguf8.5 GB · 100%
At a glance
- License
- mit
- Access
- Public
- Created
- Oct 29, 2023
- Updated
- Dec 9, 2023
- SHA
- 9720ea19
Model card
From the Hugging Face model README
Original model: NousResearch - Obsidian-3B-V0.5
gguf q6 quantised version by Nisten
To run the server inside /llama.cpp/ folder IN YOUR TERMINAL
./server -m obsidian-q6.gguf --mmproj mmproj-obsidian-f16.gguf -ngl 42
that's it, it's literally one command, you open your browser now at http://127.0.0.1:8080
FIRST TIME TO RUN mac or linux, make a new folder, COPY PASTE THIS TO DL & RUN EVERYTHIN whole in ONE SHOT
git clone -b stablelm-support https://github.com/Galunid/llama.cpp.git && \
cd llama.cpp && \
make && \
wget https://huggingface.co/nisten/obsidian-3b-multimodal-q6-gguf/resolve/main/obsidian-q6.gguf && \
wget https://huggingface.co/nisten/obsidian-3b-multimodal-q6-gguf/resolve/main/mmproj-obsidian-f16.gguf && \
./server -m obsidian-q6.gguf --mmproj mmproj-obsidian-f16.gguf -ngl 42
- License
- mit
- Created
- Oct 29, 2023
- Updated
- Dec 9, 2023