Autotrain compatible Base model:finetune:unsloth/ph... Base model:unsloth/phi-4 Conversational En Endpoints compatible Llama Region:us Safetensors Sharded Tensorflow Trl Unsloth
Model Card on HF 🤗: https://huggingface.co/ykarout/phi4-reasoning-merged
Phi4 Reasoning Merged 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)
Phi4 Reasoning Merged Parameters and Internals
| LLM Name | Phi4 Reasoning Merged |
| Repository 🤗 | https://huggingface.co/ykarout/phi4-reasoning-merged |
| Base Model(s) | |
| Model Size | 14.7b |
| Required VRAM | 29.4 GB |
| Updated | 2025-08-26 |
| Maintainer | ykarout |
| Model Type | llama |
| Model Files | |
| Supported Languages | en |
| Model Architecture | LlamaForCausalLM |
| License | apache-2.0 |
| Context Length | 16384 |
| Model Max Length | 16384 |
| Transformers Version | 4.50.0 |
| Tokenizer Class | GPT2Tokenizer |
| Padding Token | <|dummy_87|> |
| Vocabulary Size | 100352 |
| Torch Data Type | bfloat16 |
Best Alternatives to Phi4 Reasoning Merged
Best Alternatives |
Context / RAM |
Downloads |
Likes |
|---|---|---|---|
| ...ct NTK Scaled 1000steps Merged | 31K / 29.4 GB | 25 | 0 |
| E2 Phi4 Instruct NTK Scaled | 31K / 29.4 GB | 15 | 0 |
| Phi 4 | 16K / 29.4 GB | 35909 | 86 |
| Luminis Phi 4 | 16K / 29.5 GB | 2332 | 12 |
| Phi 4 Sce Exp V0.1 | 16K / 29.5 GB | 8 | 1 |
| Orca Mini Phi 4 | 16K / 29.4 GB | 67 | 8 |
| Phi 4 RR Shoup | 16K / 29.5 GB | 8 | 2 |
| Phi 4 Model Stock V4 | 16K / 29.5 GB | 8 | 9 |
| Phi 4 RStock V0.1 | 16K / 29.5 GB | 8 | 0 |
| Phi 4 Tensopolis V1 | 16K / 29.4 GB | 7 | 0 |
Note: green Score (e.g. "73.2") means that the model is better than ykarout/phi4-reasoning-merged .
Rank the Phi4 Reasoning Merged 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? 50900 in total.
Original data from HuggingFace, OpenCompass and various public git repos.
Release v20241124