Llama-3.2-1B
A lightweight large language model released by Meta with 1 billion parameters, suited for use as a draft model in speculative decoding or for inference in resource-constrained environments.
Timeline (last 90 days)
The authors surveyed the 60 most-downloaded Llama-3.2-1B fine-tuned models: 48 had declared licenses carrying the same obligations as the parent model, 6 declared Apache-2.0 or MIT, 3 had licenses that could not be evaluated, and 3 had no declaration.
Lucebox splits the draft model and the target model to run on different hardware; in the official example, Llama-3.2-1B runs as the draft model on a second GPU or the CPU, and Llama-3.1-70B runs as the target model on the main card.
Under matched batch-size-1 decoding latency, LRCC simultaneously improves both perplexity and downstream accuracy on Llama-3.2-1B.
All Facts (3)
The authors surveyed the 60 most-downloaded Llama-3.2-1B fine-tuned models: 48 had declared licenses carrying the same obligations as the parent model, 6 declared Apache-2.0 or MIT, 3 had licenses that could not be evaluated, and 3 had no declaration.
50%UnverifiedLucebox splits the draft model and the target model to run on different hardware; in the official example, Llama-3.2-1B runs as the draft model on a second GPU or the CPU, and Llama-3.1-70B runs as the target model on the main card.
50%UnverifiedUnder matched batch-size-1 decoding latency, LRCC simultaneously improves both perplexity and downstream accuracy on Llama-3.2-1B.
50%