Merged Model Autotrain compatible Conversational Custom code En Endpoints compatible Phi Region:us Safetensors Sharded Tensorflow
Model Card on HF 🤗: https://huggingface.co/Replete-AI/Phi-Delthanar
Phi Delthanar Benchmarks
ARC: 46.67 vs 96.7 (so35)-51.7%
HellaSwag: 60.19 vs 95.3 (gpt4)-36.8%
MMLU: 51.16 vs 88.3 (so35)-42.1%
TruthfulQA: 50.92 vs 59 (gpt4)-13.7%
WinoGrande: 61.48 vs 87.5 (gpt4)-29.7%
LLME Score: 0.17705
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 Delthanar Parameters and Internals
| LLM Name | Phi Delthanar |
| Repository 🤗 | https://huggingface.co/Replete-AI/Phi-Delthanar |
| Merged Model | Yes |
| Model Size | 7.8b |
| Required VRAM | 15.6 GB |
| Updated | 2025-09-17 |
| Maintainer | Replete-AI |
| Model Type | phi |
| Model Files | |
| Supported Languages | en |
| Model Architecture | PhiForCausalLM |
| License | mit |
| Context Length | 2048 |
| Model Max Length | 2048 |
| Transformers Version | 4.38.2 |
| Tokenizer Class | CodeGenTokenizer |
| Padding Token | <|endoftext|> |
| Vocabulary Size | 51200 |
| Torch Data Type | float16 |
Best Alternatives to Phi Delthanar
Best Alternatives |
Context / RAM |
Downloads |
Likes |
|---|---|---|---|
| Phi Stoma | 2K / 15.6 GB | 5 | 2 |
| Phixtral 4x2 8 | 0K / 15.7 GB | 20 | 209 |
| Phixtral 4x2 8 Gates Poc | 0K / 15.7 GB | 5 | 4 |
Rank the Phi Delthanar 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? 51415 in total.
Original data from HuggingFace, OpenCompass and various public git repos.
Release v20241124