Phi-tiny-MoE

About

What Phi-tiny-MoE is

Model Summary Phi-tiny-MoE is a lightweight Mixture of Experts (MoE) model with 3.8B total parameters and 1.1B activated parameters. It is compressed and distilled from the base model shared by Phi-3.5-MoE and GRIN-MoE using the SlimMoE approach, then post-trained via supervised fine-tuning and direct preference optimization for instruction following and safety. The model is trained on Phi-3 synthetic data and filtered public documents, with a focus on high-quality, reasoning-dense content. It is part of the SlimMoE series, which includes a larger variant, Phi-mini-MoE, with 7.6B total and 2.4B activated parameters. References: <br 📖 SlimMoE Paper <br 📖 Phi-3 Technical Report <br 📖 GRIN-MoE <br Intended Uses Primary Use Cases The model is intended for commercial and research use in English. The model provides uses for general purpose AI systems and applications which require memory/compute constrained environments and latency bound scenarios. Use Case Considerations Our models are not specifically designed or evaluated for all downstream purposes. Developers should consider common limitations of language models as they select use cases, and evaluate and mitigate for accuracy, safety, and fariness before using within a specific downstream use case, particularly for high risk scenarios. Developers should be aware of and adhere to applicable laws or regulations (including privacy, trade compliance laws, etc.) that are relevant to their use case. Nothing contained in this Model Card should be interpreted as or deemed a restriction or modification to the license the model is released under. Usage Input Formats Given the nature of the training data, the Phi-tiny-MoE model is best suited for prompts using the chat format as follows: Loading the model locally After obtaining the Phi-tiny-MoE model checkpoints, users can use this sample code for inference. Benchmarks To understand the capabilities, we compare Phi-tiny-MoE with a set of models over a variety of benchmarks using lm-evaluation-harness. Detailed evaluation settings can be found in the SlimMoE paper. Training Model Architecture: Phi-tiny-MoE has 3.8 total parameters with 1.1B active parameters. The model is a

Summarised from the published model card. Read the full card on the HuggingFace links below.

Specifications

What it is

How it works

How language models work

Variants

Sizes & precisions

Open weights ship in several sizes and precisions. One page, all the variants — pick the one that fits your GPU. VRAM figures are estimates from model size.

Using it via the API

Call it like any OpenAI endpoint

Once AxForge deploys phi-tiny-moe for you, it answers on the OpenAI-compatible API — the same base URL and keys as every other model. (phi-tiny-moe below is illustrative; you get the exact model name on deployment.)

$ curl -sS https://api.axforge.ai/v1/chat/completions \
  -H "Authorization: Bearer $AXFORGE_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"model":"phi-tiny-moe","messages":[{"role":"user","content":"Hello"}]}'

Details

Languages, data & research

Papers

Licence

Open weights

Sources

Weights & code

Explore

More language models