agier9/UAE-Large-V1-Q5_K_S-GGUF
This model was converted to GGUF format from WhereIsAI/UAE-Large-V1
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 agier9/UAE-Large-V1-Q5_K_S-GGUF --model uae-large-v1-q5_k_s.gguf -p "The meaning to life and the universe is"
Server:
llama-server --hf-repo agier9/UAE-Large-V1-Q5_K_S-GGUF --model uae-large-v1-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.
git clone https://github.com/ggerganov/llama.cpp && \
cd llama.cpp && \
make && \
./main -m uae-large-v1-q5_k_s.gguf -n 128
- Downloads last month
- 11
Spaces using agier9/UAE-Large-V1-Q5_K_S-GGUF 2
Evaluation results
- accuracy on MTEB AmazonCounterfactualClassification (en)test set self-reported75.552
- ap on MTEB AmazonCounterfactualClassification (en)test set self-reported38.264
- f1 on MTEB AmazonCounterfactualClassification (en)test set self-reported69.410
- accuracy on MTEB AmazonPolarityClassificationtest set self-reported92.843
- ap on MTEB AmazonPolarityClassificationtest set self-reported89.576
- f1 on MTEB AmazonPolarityClassificationtest set self-reported92.826
- accuracy on MTEB AmazonReviewsClassification (en)test set self-reported48.292
- f1 on MTEB AmazonReviewsClassification (en)test set self-reported47.903
- map_at_1 on MTEB ArguAnatest set self-reported42.105
- map_at_10 on MTEB ArguAnatest set self-reported58.181