|
--- |
|
base_model: ProdeusUnity/Astral-Fusion-8b-v0.0 |
|
library_name: transformers |
|
tags: |
|
- mergekit |
|
- merge |
|
- llama-cpp |
|
- gguf-my-repo |
|
--- |
|
|
|
# Triangle104/Astral-Fusion-8b-v0.0-Q6_K-GGUF |
|
This model was converted to GGUF format from [`ProdeusUnity/Astral-Fusion-8b-v0.0`](https://huggingface.co/ProdeusUnity/Astral-Fusion-8b-v0.0) 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/ProdeusUnity/Astral-Fusion-8b-v0.0) for more details on the model. |
|
|
|
--- |
|
Model details: |
|
- |
|
We will see... Come with me, take the journey~ |
|
|
|
Listen to the song on Youtube: https://www.youtube.com/watch?v=3FEFtFMBREA |
|
|
|
Another attempt at a merge, not entirely related to Stellar Odyssey. I like it, so try it out? |
|
|
|
Merged Models: |
|
|
|
meta-llama/Llama-3-8b-Instruct |
|
Sao10K_L3-8B-Stheno-v3.2 |
|
Gryphe_Pantheon-RP-1.0-8b-Llama-3 |
|
Celeste-Stable-v1.2 |
|
|
|
This is a merge of pre-trained language models created using mergekit. |
|
Edit: Celeste v1.2 Stable? |
|
|
|
That itself is a merge, more to stablize Celeste since its training was at 256. It was merged with NeuralDareDevil via TIES |
|
Merge Details |
|
Merge Method |
|
|
|
This model was merged using the della_linear merge method using C:\Users\Downloads\Mergekit-Fixed\mergekit\meta-llama_Llama-3-8B-Instruct as a base. |
|
Models Merged |
|
|
|
The following models were included in the merge: |
|
|
|
C:\Users\Downloads\Mergekit-Fixed\mergekit\Gryphe_Pantheon-RP-1.0-8b-Llama-3 |
|
C:\Users\Downloads\Mergekit-Fixed\mergekit\Sao10K_L3-8B-Stheno-v3.2 |
|
C:\Users\Downloads\Mergekit-Fixed\mergekit\Celeste-Stable-v1.2-Test2 |
|
|
|
Configuration |
|
|
|
The following YAML configuration was used to produce this model: |
|
|
|
models: |
|
- model: C:\Users\\Downloads\Mergekit-Fixed\mergekit\Sao10K_L3-8B-Stheno-v3.2 |
|
parameters: |
|
weight: 0.3 |
|
density: 0.25 |
|
- model: C:\Users\\Downloads\Mergekit-Fixed\mergekit\Celeste-Stable-v1.2-Test2 |
|
parameters: |
|
weight: 0.1 |
|
density: 0.4 |
|
- model: C:\Users\\Downloads\Mergekit-Fixed\mergekit\Gryphe_Pantheon-RP-1.0-8b-Llama-3 |
|
parameters: |
|
weight: 0.4 |
|
density: 0.5 |
|
merge_method: della_linear |
|
base_model: C:\Users\\Downloads\Mergekit-Fixed\mergekit\meta-llama_Llama-3-8B-Instruct |
|
parameters: |
|
epsilon: 0.05 |
|
lambda: 1 |
|
merge_method: della_linear |
|
dtype: bfloat16 |
|
|
|
--- |
|
## 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 Triangle104/Astral-Fusion-8b-v0.0-Q6_K-GGUF --hf-file astral-fusion-8b-v0.0-q6_k.gguf -p "The meaning to life and the universe is" |
|
``` |
|
|
|
### Server: |
|
```bash |
|
llama-server --hf-repo Triangle104/Astral-Fusion-8b-v0.0-Q6_K-GGUF --hf-file astral-fusion-8b-v0.0-q6_k.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 Triangle104/Astral-Fusion-8b-v0.0-Q6_K-GGUF --hf-file astral-fusion-8b-v0.0-q6_k.gguf -p "The meaning to life and the universe is" |
|
``` |
|
or |
|
``` |
|
./llama-server --hf-repo Triangle104/Astral-Fusion-8b-v0.0-Q6_K-GGUF --hf-file astral-fusion-8b-v0.0-q6_k.gguf -c 2048 |
|
``` |
|
|
