4bit Base model:finetune:unsloth/ph... Base model:unsloth/phi-4-unslo... En Endpoints compatible Llama Lora Quantized Region:us Safetensors Trl Unsloth
Model Card on HF 🤗: https://huggingface.co/bunnycore/Phi-4-rp-v1-lora
Phi 4 Rp V1 Lora 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 Rp V1 Lora Parameters and Internals
| LLM Name | Phi 4 Rp V1 Lora |
| Repository 🤗 | https://huggingface.co/bunnycore/Phi-4-rp-v1-lora |
| Base Model(s) | |
| Required VRAM | 0.3 GB |
| Updated | 2025-09-23 |
| Maintainer | bunnycore |
| Model Files | |
| Supported Languages | en |
| Quantization Type | 4bit |
| Model Architecture | AutoModel |
| License | apache-2.0 |
| Model Max Length | 16384 |
| Is Biased | none |
| Tokenizer Class | GPT2Tokenizer |
| Padding Token | <|dummy_87|> |
| PEFT Type | LORA |
| LoRA Model | Yes |
| PEFT Target Modules | down_proj|o_proj|q_proj|k_proj|v_proj|gate_proj|up_proj |
| LoRA Alpha | 16 |
| LoRA Dropout | 0 |
| R Param | 16 |
Best Alternatives to Phi 4 Rp V1 Lora
Best Alternatives |
Context / RAM |
Downloads |
Likes |
|---|---|---|---|
| Phi 4 RP Lora Model | 0K / 0.3 GB | 0 | 6 |
| Lora Model | 0K / 0.1 GB | 1189 | 0 |
| Phi 3.1 EvolKit Lora | 0K / 0.1 GB | 0 | 1 |
| Phi3 Telecom | 0K / 0.1 GB | 0 | 1 |
| Tiny LLama NSFW Chatbot | 0K / 0.1 GB | 0 | 1 |
| ComicBot V.2 Gguf | 32K / 5 GB | 39 | 0 |
| Distil Longformer Base 4096 | 4K / 0.4 GB | 11 | 0 |
| Daedalus 1 | 1K / GB | 6 | 1 |
| Tiny Random Detr | 1K / 0.2 GB | 21 | 0 |
| Opengpt2 Pytorch Backward | 1K / 6 GB | 20 | 1 |
Note: green Score (e.g. "73.2") means that the model is better than bunnycore/Phi-4-rp-v1-lora .
Rank the Phi 4 Rp V1 Lora 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? 51545 in total.
Original data from HuggingFace, OpenCompass and various public git repos.
Release v20241124