raidhon/coven_7b_128k_orpo_alpha
TEXT GENERATIONConcurrency Cost:1Model Size:7BQuant:FP8Ctx Length:8kLicense:apache-2.0Architecture:Transformer0.0K Open Weights Cold

raidhon/coven_7b_128k_orpo_alpha is a 7 billion parameter language model, fine-tuned by raidhon from Mistral-7B-Instruct-v0.2. It features an extended 128K token context window, enabled by the Yarn technique, and utilizes ORPO (Monolithic Preference Optimization without Reference Model) for preference alignment. This model demonstrates significant improvements in tasks like GSM8K and MMLU, making it suitable for complex language scenarios requiring extensive context and enhanced reasoning.

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