NousResearch/Hermes-2-Theta-Llama-3-70B
TEXT GENERATIONConcurrency Cost:4Model Size:70BQuant:FP8Ctx Length:8kPublished:Jun 14, 2024License:llama3Architecture:Transformer0.1K Warm

NousResearch/Hermes-2-Theta-Llama-3-70B is a 70 billion parameter language model developed by Nous Research in collaboration with Charles Goddard and Arcee AI. This model is a merged and RLHF-tuned version of Hermes 2 Pro and Meta's Llama-3 Instruct, designed to combine the strengths of both. It excels in structured outputs, function calling, and multi-turn conversational AI, leveraging ChatML for steerable dialogue and JSON for structured data extraction.

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