base_model, library_name, tags
base_model library_name tags
Qwen/Qwen3-4B transformers
horus-llm
dpo
qwen3-4b

qwen3-4b — DPO

Merged full-precision model after the DPO phase of the HorusLLM sequential training pipeline (SFT → DPO → Safety-GRPO).

Field Value
Base model Qwen/Qwen3-4B
Phase DPO
Short name qwen3-4b
Generated 2026-07-01 19:31 UTC
Description
Model synced from source: Phantomcloak19/qwen3-4b-dpo
Readme 35 KiB
Languages
Jinja 100%