The d-llm/Qwen2-1.5B-Instruct-orpo galaxy

1 models are built on d-llm/Qwen2-1.5B-Instruct-orpo: 1 quantized, 0 fine-tuned, 0 adapters and 0 merges. Together they were downloaded 19 times in the last 30 days.

Most downloaded direct derivatives

• djuna/Qwen2-1.5B-Instruct-orpo-Q8_0-GGUF (quantized), 4 downloads in 30 days

Sister project: Paper Pulse, the upvote history of every Hugging Face Daily Paper.