Phi 3.5 Moe Tiny Random is a small randomly initialized model based on the Phi-3.5 Mixture-of-Experts architecture. It serves as a test model for internal validation of tools and inference pipelines. The model is hosted on Hugging Face under the repository optimum-intel-internal-testing/phi-3.5-moe-tiny-random.
It includes a chat template configured for system, user, and assistant roles, along with defined tokens such as eos_token set to <|endoftext|, pad_token set to <|endoftext|, and unk_token set to <unk. The configuration specifies use_default_system_prompt as false. These elements allow it to be loaded with standard transformers or Optimum libraries for testing purposes.
The model records over 72,000 recent downloads and more than 253,000 downloads all time. It was created on 2025-10-21 and has discussions enabled with recently-created sorting. No inference providers are listed as available for it.
As a foundation model, it functions within the class of test and validation models used during development of machine learning pipelines rather than for production inference or end-user applications.
In the Foundation models & chat space, Phi 3.5 Moe Tiny Random takes a focused approach. It focuses on providing a minimal test model for validating Phi-3.5 MoE integration and inference pipelines. Phi 3.5 Moe Tiny Random is an open-source project aimed at AI framework developers. The project is open source (Open Source). The product ships for the web, the command line, and API.
optimum-intel-internal-testing builds and maintains Phi 3.5 Moe Tiny Random, and the product first shipped in 2024.
Latest indexed changes and source events
optimum-intel-internal-testing/phi-3.5-moe-tiny-random verified by the PulseGate indexer
Other apps tracked under the same category.
