Qwen2 architecture and size
Captured config reports Qwen2ForCausalLM and qwen2, with Safetensors metadata reporting about 1.84B parameters.
Open Source Model Profile · Qwen
Qwen1.5-1.8B-Chat
Qwen1.5-1.8B-Chat is a 1.84B-parameter Qwen2-family chat model from Qwen. According to the model card, Qwen1.5 is the beta version of Qwen2 and this size is an aligned chat model.
- Publisher
- Qwen
- Task
- text-generation
- Model type
- qwen2
- License
- tongyi-qianwen-research
- Library
- transformers
- Publication status
- Accepted · not indexed
Model overview
Qwen1.5-1.8B-Chat is published by Qwen as a Transformers text-generation chat model. The captured configuration identifies Qwen2ForCausalLM and qwen2, and Safetensors metadata reports 1,836,828,672 parameters. According to the model card, it belongs to the Qwen1.5 series positioned as the beta version of Qwen2.
Recorded capabilities
32K context support note
According to the model card, Qwen1.5 models of all sizes have stable support of 32K context length.
Decoder-only Transformer lineage
According to the model card, Qwen1.5 is a transformer-based decoder-only model with SwiGLU activation and an improved multilingual tokenizer.
Chat template and generation config
According to the model card, inference uses tokenizer.apply_chat_template with generation prompts, and the publisher advises using the provided generation_config.json hyperparameters.
Use cases in the source record
- Conversational text generation using the publisher chat-template workflow with tokenizer.apply_chat_template.
- Multilingual chat experiments where the publisher notes multilingual support for base and chat models.
Limitations and unknowns
- No evaluation results were extracted from this record.
- The recorded license value is only other, so commercial and reuse terms remain unclear from this record.
- The 32K context value is a publisher model-card claim, not an Ethen-measured context test.
- Provider state is historical snapshot data, not independently refreshed current availability.
Source and provenance
Source: Qwen/Qwen1.5-1.8B-Chat
Captured: Unknown. Processed: 2026-09-07T19:34:35.933557+00:00.
Qwen1.5-1.8B-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…
F001F002F003F004F005F006F007F008F009F010F011F013F014F015F016F017