Downloads · 30 days
19
5% of all-time downloads
Babsie/ThetaBlackGorgon-8B-Q5_K_M-GGUF
ThetaBlackGorgon-8B-Q5_K_M-GGUF is a machine learning model from Babsie. Use it for the machine learning task on the model card, and read the license before you ship it in a product. It is set up for transformers.
This model was converted to GGUF format from Babsie/ThetaBlackGorgon-8B using llama.cpp via the ggml.ai's GGUF-my-repo space. Refer to the original model card for more details on the model.
Downloads · 30 days
19
5% of all-time downloads
All-time downloads
371
Public
Repo size
5.7 GB
Likes
1
Public
Click a slice to open those files.
.gguf5.7 GB · 100%
From the Hugging Face model README
This model was converted to GGUF format from Babsie/ThetaBlackGorgon-8B using llama.cpp via the ggml.ai's GGUF-my-repo space.
Refer to the original model card for more details on the model.
Quick-start (Windows):
C:\llama..gguf file into that folder (or note the full path to it).models subfolder inside llama.cpp, e.g. C:\AI\models\.32768 if your hardware can handle it:Example of cmd:
.\llama-server.exe --model "C:\AI\models\thetablackgorgon-8b-q5_k_m.gguf" --ctx-size 32768 --threads 16 --n-gpu-layers 0 --port 8080
Change the path in --model to wherever you actually put the .gguf.
--threads 16 should roughly match your CPU cores/threads.
Set --n-gpu-layers > 0 if you’re offloading to GPU.
If you want different quant sizes, go to mradermacher/ThetaBlackGorgon-8B-GGUF, for great quants - thanks mraderarcher.
...I'll return you to the HF auto-blurb on linux and mac use
Install llama.cpp through brew (works on Mac and Linux)
brew install llama.cpp
Invoke the llama.cpp server or the CLI.
llama-cli --hf-repo Babsie/ThetaBlackGorgon-8B-Q5_K_M-GGUF --hf-file thetablackgorgon-8b-q5_k_m.gguf -p "The meaning to life and the universe is"
llama-server --hf-repo Babsie/ThetaBlackGorgon-8B-Q5_K_M-GGUF --hf-file thetablackgorgon-8b-q5_k_m.gguf -c 2048
Note: You can also use this checkpoint directly through the usage steps listed in the Llama.cpp repo as well.
Step 1: Clone llama.cpp from GitHub.
git clone https://github.com/ggerganov/llama.cpp
Step 2: Move into the llama.cpp folder and build it with LLAMA_CURL=1 flag along with other hardware-specific flags (for ex: LLAMA_CUDA=1 for Nvidia GPUs on Linux).
cd llama.cpp && LLAMA_CURL=1 make
Step 3: Run inference through the main binary.
./llama-cli --hf-repo Babsie/ThetaBlackGorgon-8B-Q5_K_M-GGUF --hf-file thetablackgorgon-8b-q5_k_m.gguf -p "The meaning to life and the universe is"
or
./llama-server --hf-repo Babsie/ThetaBlackGorgon-8B-Q5_K_M-GGUF --hf-file thetablackgorgon-8b-q5_k_m.gguf -c 2048