# Long Text Retrieval

M2-BERT-8K is an 80-million-parameter long-context retrieval model based on the architecture proposed in the paper 'Benchmarking and Building Long-Context Retrieval Models with LoCo and M2-BERT'.

80M-parameter M2-BERT-2k model checkpoint, specifically designed for long-context retrieval tasks, supporting a context length of 2048 tokens.

This is an 80M parameter M2-BERT pre-trained model, supporting sequences up to 32,768 tokens in length, specifically optimized for long-context retrieval tasks.

This is an 80-million-parameter M2-BERT pre-trained checkpoint with a sequence length of 8192, fine-tuned for long-context retrieval tasks.