Multimodal Neurons in Pretrained Text-Only Transformers(huggingface.co)

60 points by og_kalu 3 years ago | 27 comments

Qwen-Image-Layered: transparency and layer aware open diffusion model(huggingface.co)

112 points by dvrp 10 months ago | 19 comments

LLM in a Flash: Efficient LLM Inference with Limited Memory(huggingface.co)

223 points by ghshephard 2 years ago | 39 comments

Uncensor any LLM with abliteration(huggingface.co)

450 points by mizzao 2 years ago | 228 comments

Hugging Face community blog post by Maxime Labonne explaining abliteration, a technique to remove refusal behavior from LLMs without retraining.

Show HN: Hacker News archive (47M+ items, 11.6GB) as Parquet, updated every 5m(huggingface.co)

357 points by tamnd 7 months ago | 144 comments

Hugging Face dataset page for a complete Hacker News archive of every item since 2006 in Parquet format, updated every 5 minutes.

Improving Parquet Dedupe on Hugging Face Hub(huggingface.co)

38 points by ylow 2 years ago | 14 comments