Quantization made by Richard Erkhov.
EasyContext-1M-Llama-2-7B - bnb 4bits
Original model description:
EasyContext
Memory optimization and training recipes to extrapolate language models' context length to 1 million tokens, with minimal hardware.
This is a context-extrapolated base model. It has not been instruct-finetuned.
This model is finetuned from Llama-2-7B-hf with EasyContext on context length 512K and generalized to 1M tokens. Note that I keep max_position_embeddings in config.json to 4096 because HF llama will create 2D causal mask during initialization. If it is set to 1M GPU will just OOM. You can surely use this model with context length longer than 4096.
