ysn-rfd/stablelm-zephyr-3b-Q8_0-GGUF
This model was converted to GGUF format from stabilityai/stablelm-zephyr-3b
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-cli --hf-repo ysn-rfd/stablelm-zephyr-3b-Q8_0-GGUF --hf-file stablelm-zephyr-3b-q8_0.gguf -p "The meaning to life and the universe is"
Server:
llama-server --hf-repo ysn-rfd/stablelm-zephyr-3b-Q8_0-GGUF --hf-file stablelm-zephyr-3b-q8_0.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 ysn-rfd/stablelm-zephyr-3b-Q8_0-GGUF --hf-file stablelm-zephyr-3b-q8_0.gguf -p "The meaning to life and the universe is"
or
./llama-server --hf-repo ysn-rfd/stablelm-zephyr-3b-Q8_0-GGUF --hf-file stablelm-zephyr-3b-q8_0.gguf -c 2048
- Downloads last month
- 12
Model tree for ysn-rfd/stablelm-zephyr-3b-Q8_0-GGUF
Base model
stabilityai/stablelm-zephyr-3bDatasets used to train ysn-rfd/stablelm-zephyr-3b-Q8_0-GGUF
Evaluation results
- normalized accuracy on AI2 Reasoning Challenge (25-Shot)test set Open LLM Leaderboard46.080
- normalized accuracy on HellaSwag (10-Shot)validation set Open LLM Leaderboard74.160
- accuracy on MMLU (5-Shot)test set Open LLM Leaderboard46.170
- mc2 on TruthfulQA (0-shot)validation set Open LLM Leaderboard46.490
- accuracy on Winogrande (5-shot)validation set Open LLM Leaderboard65.510
- accuracy on GSM8k (5-shot)test set Open LLM Leaderboard42.150