Undi95/MG-FinalMix-72B
TEXT GENERATIONConcurrency Cost:4Model Size:72.7BQuant:FP8Ctx Length:32kPublished:Jul 11, 2024License:otherArchitecture:Transformer0.0K Warm

Undi95/MG-FinalMix-72B is a 72.7 billion parameter language model developed by Undi95, built upon a merge of Qwen/Qwen2-72B-Instruct and alpindale/magnum-72b-v1. This model is specifically retouched and enhanced with additional role-playing (RP) data, aiming to improve performance in conversational and creative generation tasks. With a substantial context length of 131072 tokens, it is optimized for nuanced and extended interactions.

Loading preview...

Popular Sampler Settings

Top 3 parameter combinations used by Featherless users for this model. Click a tab to see each config.

temperature
top_p
top_k
frequency_penalty
presence_penalty
repetition_penalty
min_p