Insanelycool/Rhea-72b-v0.5-Q4_K_M-GGUF
This model was converted to GGUF format from davidkim205/Rhea-72b-v0.5
using llama.cpp via the ggml.ai's GGUF-my-repo space.
Refer to the original model card for more details on the model.
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 --hf-repo Insanelycool/Rhea-72b-v0.5-Q4_K_M-GGUF --hf-file rhea-72b-v0.5-q4_k_m.gguf -p "The meaning to life and the universe is"
Server:
llama-server --hf-repo Insanelycool/Rhea-72b-v0.5-Q4_K_M-GGUF --hf-file rhea-72b-v0.5-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.
./main --hf-repo Insanelycool/Rhea-72b-v0.5-Q4_K_M-GGUF --hf-file rhea-72b-v0.5-q4_k_m.gguf -p "The meaning to life and the universe is"
or
./server --hf-repo Insanelycool/Rhea-72b-v0.5-Q4_K_M-GGUF --hf-file rhea-72b-v0.5-q4_k_m.gguf -c 2048
- Downloads last month
- 7
Model tree for Insanelycool/Rhea-72b-v0.5-Q4_K_M-GGUF
Base model
davidkim205/Rhea-72b-v0.5
Quantized
this model
Evaluation results
- normalized accuracy on AI2 Reasoning Challenge (25-Shot)test set Open LLM Leaderboard79.780
- normalized accuracy on HellaSwag (10-Shot)validation set Open LLM Leaderboard91.150
- accuracy on MMLU (5-Shot)test set Open LLM Leaderboard77.950
- mc2 on TruthfulQA (0-shot)validation set Open LLM Leaderboard74.500
- accuracy on Winogrande (5-shot)validation set Open LLM Leaderboard87.850
- accuracy on GSM8k (5-shot)test set Open LLM Leaderboard76.120