metadata

base_model: dawn17/MaidStarling-2x7B-base
inference: false
library_name: transformers
license: apache-2.0
pipeline_tag: text-generation
quantized_by: Suparious
tags:
  - 4-bit
  - AWQ
  - text-generation
  - autotrain_compatible
  - endpoints_compatible

dawn17/MaidStarling-2x7B-base AWQ

Model creator: dawn17
Original model: MaidStarling-2x7B-base

Model Summary

    base_model: dawn17/MaidStarling-2x7B-base
    gate_mode: hidden # one of "hidden", "cheap_embed", or "random"
    dtype: bfloat16 # output dtype (float32, float16, or bfloat16)
    experts:
      - source_model: /Users/dawn/git/models/Silicon-Maid-7B
        positive_prompts:
            - "roleplay"
      - source_model: /Users/dawn/git/models/Starling-LM-7B-beta
        positive_prompts:
            - "chat"

Open LLM Leaderboard Evaluation Results

Metric	Value
Avg.	70.76
AI2 Reasoning Challenge (25-Shot)	68.43
HellaSwag (10-Shot)	86.28
MMLU (5-Shot)	60.34
TruthfulQA (0-shot)	60.34
Winogrande (5-shot)	78.93
GSM8k (5-shot)	65.43