nm-testing

TinyLlama-1.1B-compressed-tensors-kv-cache-scheme

nm-testing/TinyLlama-1.1B-compressed-tensors-kv-cache-scheme

TinyLlama-1.1B-compressed-tensors-kv-cache-scheme is a text generation model from nm-testing. Use it when you need the model to write or continue text. It is set up for transformers.

This model is outdated and uses very old kv-cache quant scheme. It should be removed from HF-Hub once we are certain it is not used anywhere else. I have removed it from vLLM's CI in this PR: https://github.com/vllm-p…