metadata

base_model: nbeerbower/Llama3.1-Allades-8B
datasets:
  - jondurbin/gutenberg-dpo-v0.1
  - nbeerbower/gutenberg2-dpo
  - jondurbin/truthy-dpo-v0.1
  - kyujinpy/orca_math_dpo
  - antiven0m/physical-reasoning-dpo
library_name: transformers
license: llama3.1
tags:
  - llama-cpp
  - gguf-my-repo

Triangle104/Llama3.1-Allades-8B-Q4_K_M-GGUF

This model was converted to GGUF format from nbeerbower/Llama3.1-Allades-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.

Model details:

Allades finetunes abliterated Llama 3.1 with 5 datasets to improve creative writing, reasoning, and roleplay. Datasets

jondurbin/gutenberg-dpo-v0.1
nbeerbower/gutenberg2-dpo
jondurbin/truthy-dpo-v0.1
kyujinpy/orca_math_dpo
antiven0m/physical-reasoning-dpo

Training

ORPO tuned for 1 epoch with 2x RTX 3090 (sponsored by Schneewolf Labs).

Data was prepared with Llama 3.1 Instruct.

Use with llama.cpp

Install llama.cpp through brew (works on Mac and Linux)

brew install llama.cpp

Invoke the llama.cpp server or the CLI.

CLI:

llama-cli --hf-repo Triangle104/Llama3.1-Allades-8B-Q4_K_M-GGUF --hf-file llama3.1-allades-8b-q4_k_m.gguf -p "The meaning to life and the universe is"

Server:

llama-server --hf-repo Triangle104/Llama3.1-Allades-8B-Q4_K_M-GGUF --hf-file llama3.1-allades-8b-q4_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 Triangle104/Llama3.1-Allades-8B-Q4_K_M-GGUF --hf-file llama3.1-allades-8b-q4_k_m.gguf -p "The meaning to life and the universe is"

./llama-server --hf-repo Triangle104/Llama3.1-Allades-8B-Q4_K_M-GGUF --hf-file llama3.1-allades-8b-q4_k_m.gguf -c 2048