deepcogito/cogito-v1-preview-llama-8B

The deepcogito/cogito-v1-preview-llama-8B is an 8 billion parameter instruction-tuned generative language model developed by deepcogito, built on the Llama architecture. It is a hybrid reasoning model capable of both direct answers and self-reflection, trained using Iterated Distillation and Amplification (IDA). Optimized for coding, STEM, instruction following, and general helpfulness, it offers significantly higher multilingual, coding, and tool-calling capabilities than similarly sized counterparts, supporting a 32768-token context length.