Qwen
model paperFirst generation of the Qwen large language model series, spanning 1.8B to 72B parameters.
Outputs 3
Qwen-7B / 14B
modelFirst official open-source LLMs under the Qwen brand.
Architecture DENSE
Variants
| Name | Parameters | Notes |
|---|---|---|
| Qwen-7B | 7B | — |
| Qwen-14B | 14B | — |
Qwen Technical Report (2023)
paperFirst deep dive into Qwen's pretraining and alignment strategies.
arXiv: 2309.16609
Qwen-72B / 1.8B
modelExpanded the range to include a massive 72B flagship and a mobile-friendly 1.8B model.
Architecture DENSE
Variants
| Name | Parameters | Notes |
|---|---|---|
| Qwen-72B | 72B | — |
| Qwen-1.8B | 1.8B | — |