Documented Unsloth source
According to the model card, the model was finetuned from unsloth/qwen2-0.5b-bnb-4bit.
Open Source Model Profile · Ramikan-BR
Qwen2-0.5B-v21
Qwen2-0.5B-v21 is a 0.49B-parameter Qwen2 text-generation model from Ramikan-BR. Its model card identifies an Unsloth Qwen2 0.5B source with TRL training.
- 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-v21 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 Apache-2.0 recorded as the license.
Recorded capabilities
Compact Qwen2 configuration
Captured config identifies Qwen2ForCausalLM and qwen2, with Safetensors metadata reporting 494,032,768 parameters.
Transformers and GGUF tags
Hub tags record transformers, PyTorch, Safetensors, GGUF, Unsloth, TRL, SFT, and conversational support.
Use cases in the source record
- Conversational text-generation experiments using the Transformers stack recorded for this Qwen2 model.
Limitations and unknowns
- No evaluation results, dataset detail, context-window value, or hardware requirement was extracted.
- The model card is brief and does not document training data, epochs, or measured performance beyond the Unsloth and TRL note.
- Provider state is historical snapshot data, not independently refreshed current availability.
Source and provenance
Source: Ramikan-BR/Qwen2-0.5B-v21
Captured: Unknown. Processed: 2026-09-07T19:34:36.354262+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