mxs980/b1ade-embed-Q8_0-GGUF
This model was converted to GGUF format from w601sxs/b1ade-embed
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 mxs980/b1ade-embed-Q8_0-GGUF --hf-file b1ade-embed-q8_0.gguf -p "The meaning to life and the universe is"
Server:
llama-server --hf-repo mxs980/b1ade-embed-Q8_0-GGUF --hf-file b1ade-embed-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 mxs980/b1ade-embed-Q8_0-GGUF --hf-file b1ade-embed-q8_0.gguf -p "The meaning to life and the universe is"
or
./llama-server --hf-repo mxs980/b1ade-embed-Q8_0-GGUF --hf-file b1ade-embed-q8_0.gguf -c 2048
- Downloads last month
- 0
Model tree for mxs980/b1ade-embed-Q8_0-GGUF
Evaluation results
- accuracy on MTEB AmazonCounterfactualClassification (en)test set self-reported75.179
- ap on MTEB AmazonCounterfactualClassification (en)test set self-reported37.939
- f1 on MTEB AmazonCounterfactualClassification (en)test set self-reported69.081
- accuracy on MTEB AmazonPolarityClassificationtest set self-reported93.073
- ap on MTEB AmazonPolarityClassificationtest set self-reported89.999
- f1 on MTEB AmazonPolarityClassificationtest set self-reported93.061
- accuracy on MTEB AmazonReviewsClassification (en)test set self-reported48.424
- f1 on MTEB AmazonReviewsClassification (en)test set self-reported47.954
- map_at_1 on MTEB ArguAnatest set self-reported41.394
- map_at_10 on MTEB ArguAnatest set self-reported57.869