Arxiv:2403.06412 Arxiv:2404.14219 Arxiv:2407.13833 Autotrain compatible Code Conversational Custom code Instruct Moe Multilingual Phimoe Region:us Safetensors Sharded Tensorflow
Phi 3.5 MoE Instruct Benchmarks
MMLU Pro: 40.64
GPQA: 14.09
MUSR: 17.33
BBH: 48.77
IFEval: 69.25 vs 88 (so35)-21.3%
MATH Lvl 5: 20.54
LLME Score: 0.592
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 3.5 MoE Instruct Parameters and Internals
| LLM Name | Phi 3.5 MoE Instruct |
| Repository 🤗 | https://huggingface.co/microsoft/Phi-3.5-MoE-instruct |
| Model Size | 41.9b |
| Required VRAM | 83.9 GB |
| Updated | 2024-09-08 |
| Maintainer | microsoft |
| Model Type | phimoe |
| Instruction-Based | Yes |
| Model Files | |
| Model Architecture | PhiMoEForCausalLM |
| License | mit |
| Context Length | 131072 |
| Model Max Length | 131072 |
| Transformers Version | 4.43.3 |
| Tokenizer Class | LlamaTokenizer |
| Padding Token | <|endoftext|> |
| Vocabulary Size | 32064 |
| Torch Data Type | bfloat16 |
Rank the Phi 3.5 MoE Instruct 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? 35693 in total.
Original data from HuggingFace, OpenCompass and various public git repos.
Release v2024072803