Multi Master 7Bx5 v6 A quick multi disciplinary moe model. This is part of a series of models built to test the gate tuning for mixtral style moe models. Prompting Prompt Template for alpaca style Sample Code Model Details Trained by : ibivibiv Library : HuggingFace Transformers Model type: multimaster 7b is a lora tuned version of openchat/openchat 3.5 0106 with the adapter merged back into the main model Language(s) : English Purpose : This model is a focus on multi disciplinary model tuning Benchmark Scores coming soon Citations Open LLM Leaderboard Evaluation Results Detailed results can be found here Metric Value : Avg. 75.66 AI2 Reasoning Challenge (25 Shot) 72.78 HellaSwag (10 Shot) 88.77 MMLU (5 Shot) 64.74 TruthfulQA (0 shot) 70.89 Winogrande (5 shot) 86.42 GSM8k (5 shot) 70.36
We use cookies for essential functionality and analytics. You can accept or reject analytics cookies.Cookie policy