Autotrain compatible Character Conversational Custom code En Endpoints compatible Finetuned Instruct Lora Phi-3 Phi-3-mini Phi3 Region:us Roleplay Safetensors Sharded Tensorflow
Model Card on HF 🤗: https://huggingface.co/luvGPT/luvai-phi3
Luvai Phi3 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)
Luvai Phi3 Parameters and Internals
| LLM Name | Luvai Phi3 |
| Repository 🤗 | https://huggingface.co/luvGPT/luvai-phi3 |
| Base Model(s) | |
| Model Size | 3.8b |
| Required VRAM | 7.7 GB |
| Updated | 2025-08-31 |
| Maintainer | luvGPT |
| Model Type | phi3 |
| Instruction-Based | Yes |
| Model Files | |
| Supported Languages | en |
| Model Architecture | Phi3ForCausalLM |
| License | mit |
| Context Length | 4096 |
| Model Max Length | 4096 |
| Transformers Version | 4.49.0 |
| Tokenizer Class | LlamaTokenizer |
| Padding Token | <|endoftext|> |
| Vocabulary Size | 32064 |
| Torch Data Type | float16 |
Best Alternatives to Luvai Phi3
Best Alternatives |
Context / RAM |
Downloads |
Likes |
|---|---|---|---|
| Phi 4 Mini Instruct | 128K / 7.7 GB | 212915 | 589 |
| Phi 3 Mini 128K Instruct | 128K / 7.7 GB | 1059980 | 1668 |
| Phi 3.5 Mini Instruct | 128K / 7.7 GB | 208420 | 904 |
| MediPhi Instruct | 128K / 7.7 GB | 4238 | 43 |
| NuExtract 1.5 | 128K / 7.7 GB | 75475 | 236 |
| NuExtract V1.5 | 128K / 7.7 GB | 108511 | 89 |
| Phi 4 Mini Instruct | 128K / 7.7 GB | 6414 | 20 |
| Phi 3.5 Mini TitanFusion 0.1 | 128K / 7.7 GB | 5 | 0 |
| MediPhi PubMed | 128K / 7.7 GB | 604 | 7 |
| MediPhi Clinical | 128K / 7.7 GB | 530 | 9 |
Note: green Score (e.g. "73.2") means that the model is better than luvGPT/luvai-phi3 .
Rank the Luvai Phi3 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? 51043 in total.
Original data from HuggingFace, OpenCompass and various public git repos.
Release v20241124