miha-kac/zephyr-7b-beta-Q4_K_M-GGUF

This model was converted to GGUF format from HuggingFaceH4/zephyr-7b-beta 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.

brew install ggerganov/ggerganov/llama.cpp

Invoke the llama.cpp server or the CLI. CLI:

llama-cli --hf-repo miha-kac/zephyr-7b-beta-Q4_K_M-GGUF --model zephyr-7b-beta-q4_k_m.gguf -p "The meaning to life and the universe is"

Server:

llama-server --hf-repo miha-kac/zephyr-7b-beta-Q4_K_M-GGUF --model zephyr-7b-beta-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.

git clone https://github.com/ggerganov/llama.cpp && \
cd llama.cpp && \
make && \
./main -m zephyr-7b-beta-q4_k_m.gguf -n 128

Datasets used to train miha-kac/zephyr-7b-beta-Q4_K_M-GGUF

normalized accuracy on AI2 Reasoning Challenge (25-Shot)
test set Open LLM Leaderboard

62.031
normalized accuracy on HellaSwag (10-Shot)
validation set Open LLM Leaderboard

84.356
f1 score on Drop (3-Shot)
validation set Open LLM Leaderboard

9.662
mc2 on TruthfulQA (0-shot)
validation set Open LLM Leaderboard

57.449
accuracy on GSM8k (5-shot)
test set Open LLM Leaderboard

12.737
accuracy on MMLU (5-Shot)
test set Open LLM Leaderboard

61.070
accuracy on Winogrande (5-shot)
validation set Open LLM Leaderboard

77.743
win rate on AlpacaEval
source

0.906
score on MT-Bench
source

7.340