--- license: apache-2.0 tags: - llama --- # TinyLlama-1.1B-ckpt-2.5T-exl2 EXL2 quants of [TinyLlama/TinyLlama-1.1B-intermediate-step-1195k-token-2.5T](https://huggingface.co/TinyLlama/TinyLlama-1.1B-intermediate-step-1195k-token-2.5T) intended for use in speculative decoding. - [3.0bpw-h6](https://huggingface.co/royallab/TinyLlama-1.1B-ckpt-2.5T-exl2/tree/3.0bpw-h6) - [4.0bpw-h6](https://huggingface.co/royallab/TinyLlama-1.1B-ckpt-2.5T-exl2/tree/4.0bpw-h6) - [6.0bpw-h6](https://huggingface.co/royallab/TinyLlama-1.1B-ckpt-2.5T-exl2/tree/6.0bpw-h6) - [8.0bpw-h8](https://huggingface.co/royallab/TinyLlama-1.1B-ckpt-2.5T-exl2/tree/8.0bpw-h8)