Triangle104/Gemma2-Gutenberg-Doppel-9B-Q5_K_S-GGUF
This model was converted to GGUF format from nbeerbower/Gemma2-Gutenberg-Doppel-9B
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:
Gemma2-Gutenberg-Doppel-9B
UCLA-AGI/Gemma-2-9B-It-SPPO-Iter3 finetuned on jondurbin/gutenberg-dpo-v0.1 and nbeerbower/gutenberg2-dpo. Method
ORPO finetuned using 2x A40 for 3 epochs. Open LLM Leaderboard Evaluation Results
Detailed results can be found here Metric Value Avg. 29.82 IFEval (0-Shot) 71.71 BBH (3-Shot) 41.08 MATH Lvl 5 (4-Shot) 3.47 GPQA (0-shot) 10.63 MuSR (0-shot) 17.30 MMLU-PRO (5-shot) 34.75
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/Gemma2-Gutenberg-Doppel-9B-Q5_K_S-GGUF --hf-file gemma2-gutenberg-doppel-9b-q5_k_s.gguf -p "The meaning to life and the universe is"
Server:
llama-server --hf-repo Triangle104/Gemma2-Gutenberg-Doppel-9B-Q5_K_S-GGUF --hf-file gemma2-gutenberg-doppel-9b-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/Gemma2-Gutenberg-Doppel-9B-Q5_K_S-GGUF --hf-file gemma2-gutenberg-doppel-9b-q5_k_s.gguf -p "The meaning to life and the universe is"
or
./llama-server --hf-repo Triangle104/Gemma2-Gutenberg-Doppel-9B-Q5_K_S-GGUF --hf-file gemma2-gutenberg-doppel-9b-q5_k_s.gguf -c 2048
- Downloads last month
- 35
Model tree for Triangle104/Gemma2-Gutenberg-Doppel-9B-Q5_K_S-GGUF
Base model
UCLA-AGI/Gemma-2-9B-It-SPPO-Iter3Datasets used to train Triangle104/Gemma2-Gutenberg-Doppel-9B-Q5_K_S-GGUF
Collection including Triangle104/Gemma2-Gutenberg-Doppel-9B-Q5_K_S-GGUF
Evaluation results
- strict accuracy on IFEval (0-Shot)Open LLM Leaderboard71.710
- normalized accuracy on BBH (3-Shot)Open LLM Leaderboard41.080
- exact match on MATH Lvl 5 (4-Shot)Open LLM Leaderboard3.470
- acc_norm on GPQA (0-shot)Open LLM Leaderboard10.630
- acc_norm on MuSR (0-shot)Open LLM Leaderboard17.300
- accuracy on MMLU-PRO (5-shot)test set Open LLM Leaderboard34.750