Merged Model Arxiv:2306.01708 Autotrain compatible Base model:benhaotang/phi-4-ll... Base model:prithivmlmods/phi-4... Base model:win10/phi-4-llama-t... Conversational Dataset:novasky-ai/sky-t1 data... Endpoints compatible Llama Lora Model-index Region:us Safetensors Sharded Tensorflow
Model Card on HF 🤗: https://huggingface.co/benhaotang/phi4-qwq-sky-t1
Phi4 Qwq Sky T1 Benchmarks
MMLU Pro: 47.16
GPQA: 19.35
MUSR: 21.38
BBH: 52.61
IFEval: 4.6 vs 88 (so35)-94.8%
MATH Lvl 5: 41.01
LLME Score: 0.294
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 Qwq Sky T1 Parameters and Internals
| LLM Name | Phi4 Qwq Sky T1 |
| Repository 🤗 | https://huggingface.co/benhaotang/phi4-qwq-sky-t1 |
| Base Model(s) | |
| Merged Model | Yes |
| Model Size | 14.7b |
| Required VRAM | 29.5 GB |
| Updated | 2025-09-08 |
| Maintainer | benhaotang |
| Model Type | llama |
| Model Files | |
| Model Architecture | LlamaForCausalLM |
| License | mit |
| Context Length | 16384 |
| Model Max Length | 16384 |
| Transformers Version | 4.46.2 |
| Tokenizer Class | GPT2Tokenizer |
| Padding Token | <|dummy_87|> |
| Vocabulary Size | 100352 |
| LoRA Model | Yes |
| Torch Data Type | float16 |
Best Alternatives to Phi4 Qwq Sky T1
Best Alternatives |
Context / RAM |
Downloads |
Likes |
|---|---|---|---|
| ...kpoints 511 Onlytrainex Merged | 31K / 29.4 GB | 24 | 0 |
| ...ruct Extended 3500steps Merged | 31K / 29.4 GB | 91 | 0 |
| E2 Phi4 Instruct NTK Scaled | 31K / 29.4 GB | 25 | 0 |
| ...ct NTK Scaled 1000steps Merged | 31K / 29.4 GB | 10 | 0 |
| Phi 4 | 16K / 29.4 GB | 34081 | 86 |
| Luminis Phi 4 | 16K / 29.5 GB | 2398 | 13 |
| Phi 4 Sce Exp V0.1 | 16K / 29.5 GB | 7 | 1 |
| Phi 4 RR Shoup | 16K / 29.5 GB | 6 | 2 |
| Orca Mini Phi 4 | 16K / 29.4 GB | 60 | 8 |
| Phi 4 Model Stock V4 | 16K / 29.5 GB | 6 | 9 |
Note: green Score (e.g. "73.2") means that the model is better than benhaotang/phi4-qwq-sky-t1 .
Rank the Phi4 Qwq Sky T1 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? 51191 in total.
Original data from HuggingFace, OpenCompass and various public git repos.
Release v20241124