ContextualAI/archangel_sft-dpo_llama13b
TEXT GENERATIONConcurrency Cost:1Model Size:13BQuant:FP8Ctx Length:4kLicense:apache-2.0Architecture:Transformer Open Weights Warm

ContextualAI/archangel_sft-dpo_llama13b is a 13 billion parameter language model from the Llama family, developed by Contextual AI. It is optimized using a Supervised Fine-Tuning (SFT) and Direct Preference Optimization (DPO) loss function, aligned with SHP, Anthropic HH, and Open Assistant datasets. This model is designed for conversational AI, following the TuluV2 prompting format, and includes optional control tokens for conditional generation.

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