Dolphin3.0-R1-Mistral-24B-GGUF / scores /Dolphin3.0-R1-Mistral-24B-IQ4_NL.mmlu
eaddario's picture
Generate Perplexity, KLD, ARC, HellaSwag, MMLU, Truthful QA and WinoGrande scores
46eb705 verified
build: 5318 (15e03282) with cc (GCC) 11.5.0 20240719 (Red Hat 11.5.0-5) for x86_64-amazon-linux
llama_model_load_from_file_impl: using device CUDA0 (Tesla T4) - 14810 MiB free
llama_model_load_from_file_impl: using device CUDA1 (Tesla T4) - 14810 MiB free
llama_model_load_from_file_impl: using device CUDA2 (Tesla T4) - 14810 MiB free
llama_model_load_from_file_impl: using device CUDA3 (Tesla T4) - 14810 MiB free
llama_model_loader: loaded meta data with 89 key-value pairs and 363 tensors from ./Dolphin3.0-R1-Mistral-24B-IQ4_NL.gguf (version GGUF V3 (latest))
Final result: 34.9333 +/- 1.7420
Random chance: 25.0000 +/- 1.5822
llama_perf_context_print: load time = 3842.25 ms
llama_perf_context_print: prompt eval time = 172366.50 ms / 68956 tokens ( 2.50 ms per token, 400.05 tokens per second)
llama_perf_context_print: eval time = 0.00 ms / 1 runs ( 0.00 ms per token, inf tokens per second)
llama_perf_context_print: total time = 176926.11 ms / 68957 tokens