Arxiv:2412.08905 Autotrain compatible Chat Code Conversational Custom code En Endpoints compatible Math Phi Phi3 Region:us Safetensors Sharded Tensorflow
Model Card on HF 🤗: https://huggingface.co/mkurman/phi-4-MedIT-11B-exp-1
Phi 4 MedIT 11B Exp 1 Benchmarks
MMLU Pro: 31.39
GPQA: 6.82
MUSR: 6.23
BBH: 34.74
IFEval: 59.48 vs 88 (so35)-32.4%
MATH Lvl 5: 8.99
LLME Score: 0.26691
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 4 MedIT 11B Exp 1 Parameters and Internals
| LLM Name | Phi 4 MedIT 11B Exp 1 |
| Repository 🤗 | https://huggingface.co/mkurman/phi-4-MedIT-11B-exp-1 |
| Model Size | 11b |
| Required VRAM | 23.1 GB |
| Updated | 2025-01-26 |
| Maintainer | mkurman |
| Model Type | phi3 |
| Model Files | |
| Supported Languages | en |
| Model Architecture | Phi3ForCausalLM |
| License | mit |
| Context Length | 16384 |
| Model Max Length | 16384 |
| Transformers Version | 4.46.2 |
| Tokenizer Class | GPT2Tokenizer |
| Padding Token | <|endoftext|> |
| Vocabulary Size | 100352 |
| Torch Data Type | bfloat16 |
Rank the Phi 4 MedIT 11B Exp 1 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? 51566 in total.
Original data from HuggingFace, OpenCompass and various public git repos.
Release v20241124