Autotrain compatible Base model:finetune:microsoft/... Base model:microsoft/phi-4 Conversational Custom code Dataset:ai-mo/numinamath-tir Dataset:bespokelabs/bespoke-st... Dataset:meta-math/metamathqa En Endpoints compatible Ja Phi3 Region:us Safetensors Sharded Tensorflow
Model Card on HF 🤗: https://huggingface.co/AXCXEPT/phi-4-deepseek-R1K-RL-EZO
Phi 4 Deepseek R1K RL EZO 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 4 Deepseek R1K RL EZO Parameters and Internals
| LLM Name | Phi 4 Deepseek R1K RL EZO |
| Repository 🤗 | https://huggingface.co/AXCXEPT/phi-4-deepseek-R1K-RL-EZO |
| Base Model(s) | |
| Model Size | 32b |
| Required VRAM | 29.4 GB |
| Updated | 2025-09-23 |
| Maintainer | AXCXEPT |
| Model Type | phi3 |
| Model Files | |
| Supported Languages | en ja |
| Model Architecture | Phi3ForCausalLM |
| License | mit |
| Context Length | 16384 |
| Model Max Length | 16384 |
| Transformers Version | 4.48.1 |
| Tokenizer Class | GPT2Tokenizer |
| Padding Token | <|endoftext|> |
| Vocabulary Size | 100352 |
| Torch Data Type | bfloat16 |
Rank the Phi 4 Deepseek R1K RL EZO 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? 51544 in total.
Original data from HuggingFace, OpenCompass and various public git repos.
Release v20241124