vysri/Llama-3.2-1B-IT-ConvFill
Text Generation • 1B • Updated • 11
ConvFill: Inference-Time Knowledge Transfer
Model weights, dataset, and paper for https://arxiv.org/abs/2511.07397.
-
-
vysri/Qwen-0.6B-ConvFill
Text Generation • 0.6B • Updated • 145 -
vysri/Llama-3.2-1B-IT-ConvFill_mlx_q8
Text Generation • 0.3B • Updated • 27 -
vysri/gemma3-1b-IT-ConvFill_mlx_q8
Text Generation • 0.3B • Updated • 14 -
vysri/SmolLM1.7B-IT-ConvFill
Text Generation • 2B • Updated • 38 -
vysri/Qwen-0.6B-ConvFill_mlx_q8
Text Generation • 0.2B • Updated • 9 -
vysri/gemma3-270m-IT-ConvFill_mlx_q8
Text Generation • 75.4M • Updated • 17 -
vysri/SmolLM135M-IT-ConvFill_mlx_q8
Text Generation • 37.9M • Updated • 14 -
vysri/SmolLM360M-IT-ConvFill_mlx_q8
Text Generation • 0.1B • Updated • 17 -
vysri/SmolLM1.7B-IT-ConvFill_mlx_q8
Text Generation • 0.5B • Updated • 24 -
vysri/gemma3-270m-IT-ConvFill
Text Generation • 0.3B • Updated • 7 -
vysri/SmolLM135M-IT-ConvFill
Text Generation • 0.1B • Updated • 31 -
vysri/gemma3-1b-IT-ConvFill
Text Generation • 1.0B • Updated • 9 -
vysri/SmolLM360M-IT-ConvFill
Text Generation • 0.4B • Updated • 11 -
zenglhardt/convfill-dataset
Preview • Updated • 74 • 4 -
Thinking While Speaking: Inference-Time Knowledge Transfer for Responsive and Intelligent Conversational Voice Agents
Paper • 2511.07397 • Published • 12