lora-adapter

Tag

Cards List
#lora-adapter

@ClementDelangue: Number 5 trending on the hub! https://huggingface.co/harness-hub/Qwen3.8-27B-pi-adapted…

X AI KOLs Following ↗ · 3d ago Cached

A LoRA adapter for Qwen3.8-27B, trained with reinforcement learning to power the pi coding agent, tops the Hugging Face hub trends — matching the base model's xhigh thinking accuracy on SWE-bench Pro and Terminal-Bench 2.1 with about 4.5× fewer tokens.

0 favorites 0 likes
#lora-adapter

harness-hub/Qwen3.8-27B-opencode-adapted

Hugging Face Models Trending ↗ · 5d ago Cached

A LoRA adapter for Qwen3.8-27B, trained with reinforcement learning to serve as the model behind the OpenCode coding agent, matching base-model thinking-mode accuracy on SWE-bench Pro and Terminal-Bench while using 6-8x fewer tokens.

0 favorites 0 likes
#lora-adapter

harness-hub/Qwen3.8-27B-pi-adapted

Hugging Face Models Trending ↗ · 5d ago Cached

A LoRA adapter for Qwen3.8-27B trained with reinforcement learning to power the pi coding agent, matching the base model's highest-effort thinking accuracy on SWE-bench Pro and Terminal-Bench while generating about 4.5x fewer tokens with thinking off.

0 favorites 0 likes
#lora-adapter

@interfaze_ai: Jev, now open source: Lev A 4B open source System One model based on Qwen backbone The best performance for it's small …

X AI KOLs Timeline ↗ · 2026-09-25 Cached

Lev is a 4B open-source AI model based on Qwen, designed for efficient typed decision-making in a single forward pass with zero output tokens, achieving strong benchmarks for its size.

0 favorites 0 likes
#lora-adapter

MAAT: Multi-phase Adapter-Aware Targeted Unlearning

arXiv cs.LG ↗ · 2026-06-01 Cached

The paper identifies a blind spot in machine unlearning benchmarks: underrepresentation of causal (Why-type) knowledge, and proposes 5WBench, a balanced benchmark, and Maat, a three-phase unlearning framework on LoRA adapters that achieves high forgetting and retention on causal facts.

0 favorites 0 likes
← Back to home

Submit Feedback