Triangle104/Lyra4-Gutenberg-12B-Q5_K_S-GGUF
This model was converted to GGUF format from nbeerbower/Lyra4-Gutenberg-12B
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:
Sao10K/MN-12B-Lyra-v4 finetuned on jondurbin/gutenberg-dpo-v0.1.
Method
ORPO Finetuned using an RTX 3090 + 4060 Ti for 3 epochs.
Fine-tune Llama 3 with ORPO
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/Lyra4-Gutenberg-12B-Q5_K_S-GGUF --hf-file lyra4-gutenberg-12b-q5_k_s.gguf -p "The meaning to life and the universe is"
Server:
llama-server --hf-repo Triangle104/Lyra4-Gutenberg-12B-Q5_K_S-GGUF --hf-file lyra4-gutenberg-12b-q5_k_s.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/Lyra4-Gutenberg-12B-Q5_K_S-GGUF --hf-file lyra4-gutenberg-12b-q5_k_s.gguf -p "The meaning to life and the universe is"
or
./llama-server --hf-repo Triangle104/Lyra4-Gutenberg-12B-Q5_K_S-GGUF --hf-file lyra4-gutenberg-12b-q5_k_s.gguf -c 2048
- Downloads last month
- 25
Model tree for Triangle104/Lyra4-Gutenberg-12B-Q5_K_S-GGUF
Dataset used to train Triangle104/Lyra4-Gutenberg-12B-Q5_K_S-GGUF
Collections including Triangle104/Lyra4-Gutenberg-12B-Q5_K_S-GGUF
Evaluation results
- strict accuracy on IFEval (0-Shot)Open LLM Leaderboard22.120
- normalized accuracy on BBH (3-Shot)Open LLM Leaderboard34.240
- exact match on MATH Lvl 5 (4-Shot)Open LLM Leaderboard11.710
- acc_norm on GPQA (0-shot)Open LLM Leaderboard9.170
- acc_norm on MuSR (0-shot)Open LLM Leaderboard11.970
- accuracy on MMLU-PRO (5-shot)test set Open LLM Leaderboard28.570