Blossom dataset mix
According to the model card, training used Blossom Orca, Wizard, Chat, and Math datasets, also published as open datasets.
Open Source Model Profile · Azure99
blossom-v5-4b
blossom-v5-4b is a 3.95B-parameter Qwen-family conversational fine-tune from Azure99. According to the model card, it uses Blossom Orca, Wizard, Chat, and Math datasets.
- Publisher
- Azure99
- Task
- text-generation
- Model type
- qwen2
- License
- apache-2.0
- Library
- transformers
- Publication status
- Accepted · not indexed
Model overview
blossom-v5-4b is published by Azure99 as a Qwen-based text-generation model. The captured configuration identifies Qwen2ForCausalLM and Safetensors metadata reports 3950369280 parameters. According to the model card, it is a conversational model fine-tuned on a mixed Blossom Orca, Wizard, Chat, and Math dataset.
Recorded capabilities
Two-stage training account
According to the model card, stage one used 40K Wizard, 40K Orca, and 10K Math items for one epoch, then stage two used 10K multi-turn chat plus resampled stage-one data for three epochs.
3.95B Qwen build
Captured configuration identifies Qwen2ForCausalLM with 3950369280 Safetensors parameters.
GPT-4-distilled series claim
According to the model card, the Blossom V5 series was fully trained on high-quality data distilled from gpt-4-0125-preview.
Use cases in the source record
- Chinese and English dialogue-continuation workflows using this conversational fine-tune.
- Instruction-tuning experiments building on the documented Blossom Orca, Wizard, Chat, and Math mix.
Limitations and unknowns
- No evaluation results were extracted from this record.
- No context-window value was extracted from this record.
- The publisher's distillation and improvement claims have not been independently verified by Ethen.
- Provider state is historical snapshot data, not independently refreshed current availability.
Source and provenance
Source: Azure99/blossom-v5-4b
Captured: Unknown. Processed: 2026-09-07T19:34:29.091904+00:00.
BLOSSOM-v5-4b 💻Github • 🚀Blossom Chat Demo What's new? The Blossom V5 series models is fully trained using high-quality data distilled from gpt-4-0125-preview, resulting in significant improvements. Introduction Blossom is a conversational large language model, fine-tuned on the Blossom Orca/Wizard/Chat/Math mixed dataset based on the Qwen1.5-4B pre-trained model. Blossom possesses robust general capabilities and context comprehension. Additionally, the high-quality Chinese and English datasets used for training have been made open source. Training was conducted in two stages. The first stage used 40K Wizard, 40K Orca, 10K Math si…
F001F002F003F004F005F006F007F008F009F010F012F013F014F015