Hugging Face's logo

Open-Weight
community
Activity Feed

AI & ML interests

Open-weight models, model formats, quantization, inference, fine-tuning, weight provenance, model portability and deployment infrastructure. Contact: agenten@magenta.de

Recent Activity
Agenten  updated a collection about 1 month ago
Open Weight Inference, Serving and Model Portability
Agenten  updated a collection about 1 month ago
Open Weight Inference, Serving and Model Portability
Agenten  updated a collection about 1 month ago
Open Weight Inference, Serving and Model Portability
View all activity

open-weight 's collections 4

Open Weight Inference, Serving and Model Portability
Curated resources for deploying open-weight models across runtimes, formats, hardware platforms and inference infrastructure.
Open Weight Quantization, Compression and Efficient Inferenc
Curated resources for FP8, INT8, INT4, AWQ, GPTQ, QLoRA and efficient open-weight inference.
Open Weight Fine-Tuning, LoRA, PEFT and Model Adaptation
Curated resources for adapting open-weight models with LoRA, QLoRA, PEFT, adapters and parameter-efficient fine-tuning.
Open Weight Formats, Serialization and Model Files
Curated resources for open-weight model formats, tensor serialization, metadata, sharding and model conversion.
Open Weight Inference, Serving and Model Portability
Curated resources for deploying open-weight models across runtimes, formats, hardware platforms and inference infrastructure.
Open Weight Fine-Tuning, LoRA, PEFT and Model Adaptation
Curated resources for adapting open-weight models with LoRA, QLoRA, PEFT, adapters and parameter-efficient fine-tuning.
Open Weight Quantization, Compression and Efficient Inferenc
Curated resources for FP8, INT8, INT4, AWQ, GPTQ, QLoRA and efficient open-weight inference.
Open Weight Formats, Serialization and Model Files
Curated resources for open-weight model formats, tensor serialization, metadata, sharding and model conversion.