Sep 2, 2026 12:32 UTC
huggingface
nvidia
Nvidia released two new 1.7B-Base language models to HuggingFace: SDLLM-Duo and SDLLM-EsoLM.
READY TO POST:
nvidia just dropped two new 1.7b-base llms, sd_llm-duo and sd_llm-esolm, on huggingface. interesting to see these new small models.
looks like nvidia is experimenting with some smaller llms, pushing sd_llm-duo-1.7b-base and sd_llm-esolm-1.7b-base to hf. could be useful for local inference.