Qwen 1.5
Alibaba Cloud · February 2024
● activeOpen Weightdecoder onlytext
Parameters0.5B - 110B
Context Window32K tokens
Variants0.5B, 1.8B, 4B, 7B, 14B, 32B, 72B, 110B
Description
A major upgrade to the original Qwen, spanning an unusually wide range of sizes from tiny (0.5B) to massive (110B). Significantly improved at following user instructions and carrying on natural conversations, with chat-optimized variants for each size. Expanded language support beyond Chinese and English.
Key Innovations
Open Weight
Open WeightModel weights are publicly released but training data/code may not be. Enables fine-tuning but not full reproduction.
Instruction Tuning
Instruction TuningFine-tuning a model on instruction-response pairs so it follows user commands more reliably.