Qwen2 architecture
The captured configuration identifies Qwen2ForCausalLM with model type qwen2 and Transformers library support.
Open Source Model Profile · Ramikan-BR
Qwen2-0.5B-v26
Qwen2-0.5B-v26 is a Qwen2 text-generation fine-tune from Ramikan-BR with about 494M parameters. According to the model card, it was finetuned from unsloth/qwen2-0.5b-bnb-4bit using Unsloth and TRL.
- Publisher
- Ramikan-BR
- Task
- text-generation
- Model type
- qwen2
- License
- apache-2.0
- Library
- transformers
- Publication status
- Accepted · not indexed
Model overview
Qwen2-0.5B-v26 is published by Ramikan-BR as a text-generation model. The captured configuration identifies Qwen2ForCausalLM with model type qwen2, and Safetensors metadata reports 494,032,768 parameters. According to the model card, it was finetuned from unsloth/qwen2-0.5b-bnb-4bit, with a recorded apache-2.0 license.
Recorded capabilities
Unsloth and TRL workflow
According to the model card, the model was trained 2x faster with Unsloth and Hugging Face's TRL library.
Documented source model
According to the model card, it was finetuned from unsloth/qwen2-0.5b-bnb-4bit.
Use cases in the source record
- Conversational text-generation workflows consistent with the recorded conversational tags and the snapshot conversational provider listing.
Limitations and unknowns
- No evaluation results were extracted from this record.
- No context-window value was extracted from this record.
- No quantization format details were extracted beyond the recorded gguf hub tag.
- Provider state is historical snapshot data and should be refreshed before being presented as current.
Source and provenance
Source: Ramikan-BR/Qwen2-0.5B-v26
Captured: Unknown. Processed: 2026-09-07T19:34:36.087620+00:00.
Uploaded model Developed by: Ramikan-BR License: apache-2.0 Finetuned from model : unsloth/qwen2-0.5b-bnb-4bit This qwen2 model was trained 2x faster with Unsloth and Huggingface's TRL library.
F001F002F003F004F005F006F007F008F009F010F011