Apply for NVIDIA’s GPT-8B LLM Access
NVIDIA NeMo provides various pre-trained foundation language models that can be customized for various enterprise-specific tasks. As part of the recent Microsoft Build conference, NVIDIA demonstrated a new 8 Billion parameter model ready for Windows developers running in Windows Subsystem for Linux (WSL) for inference workloads.
NVIDIA is now offering WSL developers that early version of the GPT-8B model for evaluation and experimental purposes.
To get early access to the custom framework and the model, please fill out the short application and provide details about your use case. You must be a member of the NVIDIA developer program and log in with your organization's email address. We will not approve early access applications from personal email accounts.
Requirements: NVIDIA RTX 4090 GPU, Windows 11, modern multicore CPU, 128GB System RAM, Windows Subsystem for Linux v2 (WSL2), Inference-Only Workloads