|
--- |
|
license: apache-2.0 |
|
tags: |
|
- merge |
|
- model_stock |
|
- DarkStock |
|
- Aspire |
|
- Storm |
|
- Llama3 |
|
- DarkEnigma |
|
- instruction-following |
|
- creative-writing |
|
- coding |
|
- roleplaying |
|
- long-form-generation |
|
- research |
|
- bfloat16 |
|
- llama-cpp |
|
- gguf-my-repo |
|
base_model: ZeroXClem/Llama3.1-DarkStorm-Aspire-8B |
|
library_name: transformers |
|
language: |
|
- en |
|
datasets: |
|
- openbuddy/openbuddy-llama3.1-8b-v22.2-131k |
|
- THUDM/LongWriter-llama3.1-8b |
|
- aifeifei798/DarkIdol-Llama-3.1-8B-Instruct-1.2-Uncensored |
|
pipeline_tag: text-generation |
|
--- |
|
|
|
# ZeroXClem/Llama3.1-DarkStorm-Aspire-8B-Q5_0-GGUF |
|
This model was converted to GGUF format from [`ZeroXClem/Llama3.1-DarkStorm-Aspire-8B`](https://huggingface.co/ZeroXClem/Llama3.1-DarkStorm-Aspire-8B) using llama.cpp via the ggml.ai's [GGUF-my-repo](https://huggingface.co/spaces/ggml-org/gguf-my-repo) space. |
|
Refer to the [original model card](https://huggingface.co/ZeroXClem/Llama3.1-DarkStorm-Aspire-8B) for more details on the model. |
|
|
|
## Use with llama.cpp |
|
Install llama.cpp through brew (works on Mac and Linux) |
|
|
|
```bash |
|
brew install llama.cpp |
|
|
|
``` |
|
Invoke the llama.cpp server or the CLI. |
|
|
|
### CLI: |
|
```bash |
|
llama-cli --hf-repo ZeroXClem/Llama3.1-DarkStorm-Aspire-8B-Q5_0-GGUF --hf-file llama3.1-darkstorm-aspire-8b-q5_0.gguf -p "The meaning to life and the universe is" |
|
``` |
|
|
|
### Server: |
|
```bash |
|
llama-server --hf-repo ZeroXClem/Llama3.1-DarkStorm-Aspire-8B-Q5_0-GGUF --hf-file llama3.1-darkstorm-aspire-8b-q5_0.gguf -c 2048 |
|
``` |
|
|
|
Note: You can also use this checkpoint directly through the [usage steps](https://github.com/ggerganov/llama.cpp?tab=readme-ov-file#usage) 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 ZeroXClem/Llama3.1-DarkStorm-Aspire-8B-Q5_0-GGUF --hf-file llama3.1-darkstorm-aspire-8b-q5_0.gguf -p "The meaning to life and the universe is" |
|
``` |
|
or |
|
``` |
|
./llama-server --hf-repo ZeroXClem/Llama3.1-DarkStorm-Aspire-8B-Q5_0-GGUF --hf-file llama3.1-darkstorm-aspire-8b-q5_0.gguf -c 2048 |
|
``` |
|
|
