DeepSeek-R1-Distill-Qwen-7B-GGUF / scores /deepseek-r1-distill-qwen-7b-q3_k_s.arc
eaddario's picture
Regenerate Perplexity, KLD, ARC, HellaSwag, MMLU, Truthful QA and WinoGrande scores
0f51238 verified
raw
history blame
824 Bytes
build: 4998 (d41f0150) with Apple clang version 16.0.0 (clang-1600.0.26.6) for arm64-apple-darwin24.3.0
llama_model_load_from_file_impl: using device Metal (Apple M3 Pro) - 27647 MiB free
llama_model_loader: loaded meta data with 31 key-value pairs and 339 tensors from ./DeepSeek-R1-Distill-Qwen-7B-Q3_K_S.gguf (version GGUF V3 (latest))
Final result: 48.3266 +/- 1.8296
Random chance: 25.0251 +/- 1.5859
llama_perf_context_print: load time = 1493.80 ms
llama_perf_context_print: prompt eval time = 163839.77 ms / 36497 tokens ( 4.49 ms per token, 222.76 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 = 165697.47 ms / 36498 tokens
ggml_metal_free: deallocating