qwen2:0.5b
Family context: Qwen2 family
Publisher: Qwen Team, Alibaba Cloud
The Qwen2 release includes base and instruction-tuned text models. Its model table distinguishes context limits by size rather than assigning one limit to the whole family.
Publisher-described context, separate from Sigma5C observations and recorded catalog statistics.
Published family information
- Documented small instruction models
- 0.5B and 1.5B: 32K context, publisher notation Source
- Documented 7B instruction model
- 128K with the described YaRN configuration Source
- Architecture feature
- Grouped-query attention across the listed sizes Source
Publisher-described uses
- Multilingual text generation, code and mathematical text workflows. Source
Reference limitations
- The 7B extended-context configuration is not a specification for the smaller models, and a model tag is not a runtime configuration record. Source
A recorded tag and an upstream card association do not verify the deployed checkpoint, quantization, configured context or current hosted availability.
Publisher sources
- Qwen2 family official documentation — Qwen Team, Alibaba Cloud. Checked .
Links
Recorded references do not establish downloadable weights, licensing or current availability.
0.5B
parameters
Q4_0
quantization
qwen2
architecture
32768
context
apache-2.0
license
2024-06-07
released
Where qwen2:0.5b comes from
Company / lab
Alibaba Cloud Qwen
See every model and family from this maker.
Model family
qwen2
Other versions and sizes in this line.
completion