1.1B open-weight LLM by nm-testing
TinyLlama-1.1B-compressed-tensors-kv-cache-scheme is an open-weight text-generation model with roughly 1.1B parameters published by nm-testing on the Hugging Face Hub. It has 386 downloads. Runs with transformers.
nm-testing
api
free
Others in the same category, ranked by how often they are opened.
