|
--- |
|
base_model: SvdH/RPLament-22B |
|
library_name: transformers |
|
tags: |
|
- mergekit |
|
- merge |
|
- llama-cpp |
|
- gguf-my-repo |
|
license: other |
|
license_name: mrl |
|
license_link: https://mistral.ai/licenses/MRL-0.1.md |
|
--- |
|
|
|
# Triangle104/RPLament-22B-Q5_K_M-GGUF |
|
This model was converted to GGUF format from [`SvdH/RPLament-22B`](https://huggingface.co/SvdH/RPLament-22B) 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/SvdH/RPLament-22B) for more details on the model. |
|
|
|
--- |
|
Model details: |
|
- |
|
This is a merge of pre-trained language models created using mergekit. |
|
|
|
Merge Method |
|
- |
|
This model was merged using the DARE TIES merge method using ArliAI/Mistral-Small-22B-ArliAI-RPMax-v1.1 as a base. |
|
Models Merged |
|
|
|
The following models were included in the merge: |
|
|
|
allura-org/MS-Meadowlark-22B |
|
Gryphe/Pantheon-RP-1.6.2-22b-Small |
|
rAIfle/Acolyte-22B |
|
anthracite-org/magnum-v4-22b |
|
|
|
Configuration |
|
- |
|
The following YAML configuration was used to produce this model: |
|
|
|
merge_method: dare_ties |
|
base_model: ArliAI/Mistral-Small-22B-ArliAI-RPMax-v1.1 |
|
parameters: |
|
int8_mask: true |
|
dtype: bfloat16 |
|
models: |
|
- model: ArliAI/Mistral-Small-22B-ArliAI-RPMax-v1.1 |
|
parameters: |
|
weight: 0.30 |
|
density: 0.78 |
|
- model: anthracite-org/magnum-v4-22b |
|
parameters: |
|
weight: 0.25 |
|
density: 0.66 |
|
- model: allura-org/MS-Meadowlark-22B |
|
parameters: |
|
weight: 0.20 |
|
density: 0.54 |
|
- model: rAIfle/Acolyte-22B |
|
parameters: |
|
weight: 0.15 |
|
density: 0.42 |
|
- model: Gryphe/Pantheon-RP-1.6.2-22b-Small |
|
parameters: |
|
weight: 0.10 |
|
density: 0.42 |
|
|
|
--- |
|
## 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/RPLament-22B-Q5_K_M-GGUF --hf-file rplament-22b-q5_k_m.gguf -p "The meaning to life and the universe is" |
|
``` |
|
|
|
### Server: |
|
```bash |
|
llama-server --hf-repo Triangle104/RPLament-22B-Q5_K_M-GGUF --hf-file rplament-22b-q5_k_m.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/RPLament-22B-Q5_K_M-GGUF --hf-file rplament-22b-q5_k_m.gguf -p "The meaning to life and the universe is" |
|
``` |
|
or |
|
``` |
|
./llama-server --hf-repo Triangle104/RPLament-22B-Q5_K_M-GGUF --hf-file rplament-22b-q5_k_m.gguf -c 2048 |
|
``` |
|
|
