Qwen3.8-27B-hermes-adapted trends on Hugging Face with GRPO and agent tags

harness-hub · hf · 2026-11-21

Qwen3.8-27B-hermes-adapted is trending on Hugging Face as an image-text-to-text model.

Its tags — peft, trl, grpo, async-grpo, lora, agents, harbor, openenv, hermes — indicate it was adapted via GRPO/LoRA-style agent training pipelines.

Original post →

More from Models

Models channel →