inference-optimization/MiniMax-M2.5-BF16
022
1{2 "schema_version": "0.2.2",3 "evaluation_id": "gpqa:diamond/inference-optimization/MiniMax-M2.5-BF16/1777462221.868785",4 "evaluation_timestamp": "7577591",5 "retrieved_timestamp": "1777462221.868785",6 "source_metadata": {7 "source_name": "lighteval",8 "source_type": "evaluation_run",9 "source_organization_name": "RedHatAI",10 "evaluator_relationship": "third_party"11 },12 "eval_library": {13 "name": "lighteval",14 "version": "v0.13.0"15 },16 "model_info": {17 "name": "inference-optimization/MiniMax-M2.5-BF16",18 "id": "inference-optimization/MiniMax-M2.5-BF16",19 "developer": "inference-optimization",20 "inference_engine": {21 "name": "vllm"22 },23 "additional_details": {24 "provider": "hosted_vllm",25 "base_url": "http://0.0.0.0:8000/v1",26 "concurrent_requests": "8",27 "verbose": "False",28 "api_max_retry": "8",29 "api_retry_sleep": "1.0",30 "api_retry_multiplier": "2.0",31 "timeout": "2400.0",32 "num_seeds_merged": "3"33 }34 },35 "evaluation_results": [36 {37 "evaluation_name": "gpqa:diamond",38 "source_data": {39 "dataset_name": "gpqa:diamond",40 "source_type": "hf_dataset",41 "hf_repo": "Idavidrein/gpqa",42 "hf_split": "train"43 },44 "evaluation_timestamp": "7581787",45 "metric_config": {46 "evaluation_description": "gpqa_pass@k:k=1",47 "lower_is_better": false,48 "score_type": "continuous",49 "min_score": 0.0,50 "max_score": 1.051 },52 "score_details": {53 "score": 0.8367003367003367,54 "details": {55 "seed_scores": "[0.8383838383838383, 0.8232323232323232, 0.8484848484848485]",56 "seed_values": "[1234, 4158, 42]"57 },58 "uncertainty": {59 "standard_error": {60 "value": 0.0073382137096644475,61 "method": "across_seeds"62 },63 "num_samples": 364 }65 },66 "generation_config": {67 "generation_args": {68 "temperature": 1.0,69 "top_p": 0.95,70 "top_k": 40.0,71 "max_tokens": 64000,72 "max_attempts": 173 },74 "additional_details": {75 "repetition_penalty": "1.0",76 "presence_penalty": "1.5",77 "seed": "1234",78 "min_p": "0.0"79 }80 }81 }82 ]83}