Merged Model Arxiv:1910.09700 Autotrain compatible Custom code Endpoints compatible Moe Phi-msft Region:us Safetensors Sharded Tensorflow
Model Card on HF 🤗: https://huggingface.co/AbstractPerspective/Phi-2_MoE_test
Phi 2 MoE Test Benchmarks
nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
What is the LLM Explorer Rank (Score)
Phi 2 MoE Test Parameters and Internals
| LLM Name | Phi 2 MoE Test |
| Repository 🤗 | https://huggingface.co/AbstractPerspective/Phi-2_MoE_test |
| Merged Model | Yes |
| Model Size | 4.5b |
| Required VRAM | 8.9 GB |
| Updated | 2025-09-23 |
| Maintainer | AbstractPerspective |
| Model Type | phi-msft |
| Model Files | |
| Model Architecture | PhiForCausalLM |
| Model Max Length | 2048 |
| Transformers Version | 4.37.0 |
| Tokenizer Class | CodeGenTokenizer |
| Padding Token | <|endoftext|> |
| Vocabulary Size | 51200 |
| Torch Data Type | float16 |
| Activation Function | gelu_new |
Best Alternatives to Phi 2 MoE Test
Best Alternatives |
Context / RAM |
Downloads |
Likes |
|---|---|---|---|
| Phixtral 2x2 8 | 0K / 8.9 GB | 17 | 149 |
| Samantha Phixtral 2x2 8 | 0K / 8.9 GB | 13 | 1 |
| Phixtral 4x2 8odd | 0K / 8.9 GB | 0 | 3 |
Note: green Score (e.g. "73.2") means that the model is better than AbstractPerspective/Phi-2_MoE_test .
Rank the Phi 2 MoE Test Capabilities
🆘 Have you tried this model? Rate its performance. This feedback would greatly assist ML community in identifying the most suitable model for their needs. Your contribution really does make a difference! 🌟
What open-source LLMs or SLMs are you in search of? 51567 in total.
Original data from HuggingFace, OpenCompass and various public git repos.
Release v20241124