Downloads · 30 days
31
5% of all-time downloads
Phantomcloak19/qwen2.5-3b-dpo-grpo
qwen2.5-3b-dpo-grpo is a text generation model from Phantomcloak19. Use it when you need the model to write or continue text. It is set up for transformers.
Merged full-precision model after the DPO-GRPO phase of the LLMPR sequential training pipeline (SFT → DPO → Safety-GRPO).
Downloads · 30 days
31
5% of all-time downloads
All-time downloads
579
Public
Parameters
3.1B
6.2 GB on disk
Likes
0
Public
Click a slice to open those files.
.safetensors6.2 GB · 100%
From the Hugging Face model README
Merged full-precision model after the DPO-GRPO phase of the LLMPR sequential training pipeline (SFT → DPO → Safety-GRPO).
| Field | Value |
|---|---|
| Base model | Qwen/Qwen2.5-3B-Instruct |
| Phase | DPO-GRPO |
| Short name | qwen2.5-3b |
| Generated | 2026-06-30 03:11 UTC |