Abliterated Ar Autotrain compatible Base model:finetune:microsoft/... Base model:microsoft/phi-4-min... Code Conversational Cs Custom code Da De En Endpoints compatible Es Fi Fr He Hu Instruct It Ja Ko Multilingual Nl No Phi3 Pl Pt Region:us Ru Safetensors Sharded Sv Tensorflow Th Tr Uk Zh
Model Card on HF π€: https://huggingface.co/lunahr/Phi-4-mini-instruct-abliterated
Phi 4 Mini Instruct Abliterated 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)
π Advertise your project π
Phi 4 Mini Instruct Abliterated Parameters and Internals
| LLM Name | Phi 4 Mini Instruct Abliterated |
| Repository π€ | https://huggingface.co/lunahr/Phi-4-mini-instruct-abliterated |
| Base Model(s) | |
| Model Size | 3.8b |
| Required VRAM | 7.7 GB |
| Updated | 2025-09-15 |
| Maintainer | lunahr |
| Model Type | phi3 |
| Instruction-Based | Yes |
| Model Files | |
| Supported Languages | ar zh cs da nl en fi fr de he hu it ja ko no pl pt ru es sv th tr uk |
| Model Architecture | Phi3ForCausalLM |
| License | mit |
| Context Length | 131072 |
| Model Max Length | 131072 |
| Transformers Version | 4.49.0 |
| Tokenizer Class | GPT2Tokenizer |
| Padding Token | <ο½PADβTOKENο½> |
| Vocabulary Size | 200064 |
| Torch Data Type | bfloat16 |
Best Alternatives to Phi 4 Mini Instruct Abliterated
Best Alternatives |
Context / RAM |
Downloads |
Likes |
|---|---|---|---|
| Phi 4 Mini Instruct | 128K / 7.7 GB | 253346 | 597 |
| Phi 3 Mini 128K Instruct | 128K / 7.7 GB | 936694 | 1670 |
| Phi 3.5 Mini Instruct | 128K / 7.7 GB | 243411 | 908 |
| MediPhi Instruct | 128K / 7.7 GB | 4202 | 44 |
| NuExtract 1.5 | 128K / 7.7 GB | 84936 | 237 |
| MediPhi Clinical | 128K / 7.7 GB | 1690 | 9 |
| NuExtract V1.5 | 128K / 7.7 GB | 108511 | 89 |
| Phi 4 Mini Instruct | 128K / 7.7 GB | 5283 | 20 |
| Phi 3.5 Mini TitanFusion 0.1 | 128K / 7.7 GB | 5 | 0 |
| MediPhi MedCode | 128K / 7.7 GB | 705 | 3 |
Note: green Score (e.g. "73.2") means that the model is better than lunahr/Phi-4-mini-instruct-abliterated .
Rank the Phi 4 Mini Instruct Abliterated Capabilities
π 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! π
What open-source LLMs or SLMs are you in search of? 51387 in total.
Original data from HuggingFace, OpenCompass and various public git repos.
Release v20241124