sethuiyer/SynthIQ-7b
TEXT GENERATIONConcurrency Cost:1Model Size:7BQuant:FP8Ctx Length:4kPublished:Dec 29, 2023License:llama2Architecture:Transformer0.0K Open Weights Cold

SynthIQ-7b by sethuiyer is a 7 billion parameter merged language model built on the Mistral-7B-v0.1 base, utilizing mergekit with components like OpenHermes-2.5 and speechless-mistral-six-in-one. Rated 92.23/100 by GPT-4 on complex prompts, it demonstrates strong performance across various benchmarks including HellaSwag (85.82) and Winogrande (78.69). This model is optimized for general-purpose conversational AI and reasoning tasks, and is compatible with tools like autogen and CrewAI.

Loading preview...