Compact Qwen2 chat architecture
The captured configuration identifies Qwen2ForCausalLM with model type qwen2 and Transformers support.
Open Source Model Profile · Qwen
Qwen1.5-0.5B-Chat
Qwen1.5-0.5B-Chat is a 0.62B-parameter Qwen2-family aligned chat model from Qwen. According to the model card, it belongs to the Qwen1.5 beta series.
- Publisher
- Qwen
- Task
- text-generation
- Model type
- qwen2
- License
- tongyi-qianwen-research
- Library
- transformers
- Publication status
- Accepted · not indexed
Model overview
Qwen1.5-0.5B-Chat is published by Qwen as a compact text-generation chat model. The captured configuration identifies Qwen2ForCausalLM with model type qwen2, and Safetensors metadata reports about 0.62B parameters. According to the model card, Qwen1.5 is the beta version of Qwen2.
Recorded capabilities
Aligned chat release
According to the model card, Qwen1.5 pairs base and aligned chat models, with post-training by supervised finetuning and direct preference optimization.
Documented chat template
According to the model card, inference uses the tokenizer chat template with a generation prompt.
Documented generation guidance
According to the model card, the publisher advises using the provided generation_config.json hyperparameters when code switching or bad cases occur.
Use cases in the source record
- Lightweight conversational text-generation workflows using the documented chat template.
- Multilingual chat experimentation within the scope of the publisher's multilingual-support description.
Limitations and unknowns
- No evaluation scores were extracted from this record.
- The 32K context statement is a publisher claim from the model card and was not independently verified.
- The captured license value is only the generic label other; exact terms were not extracted.
- Provider state is historical snapshot data and should be refreshed before being presented as current.
Source and provenance
Source: Qwen/Qwen1.5-0.5B-Chat
Captured: Unknown. Processed: 2026-09-07T19:34:35.907892+00:00.
Qwen1.5-0.5B-Chat Introduction Qwen1.5 is the beta version of Qwen2, a transformer-based decoder-only language model pretrained on a large amount of data. In comparison with the previous released Qwen, the improvements include: 8 model sizes, including 0.5B, 1.8B, 4B, 7B, 14B, 32B and 72B dense models, and an MoE model of 14B with 2.7B activated; Significant performance improvement in human preference for chat models; Multilingual support of both base and chat models; Stable support of 32K context length for models of all sizes No need of trust_remote_code . For more details, please refer to our blog post and GitHub repo . Model Det…
F001F002F003F004F005F006F007F008F009F010F011F013F014F016F017