Arxiv:1910.09700 Adapter Base model:adapter:google/gemm... Base model:google/gemma-2b-it Finetuned Lora Peft Region:us Safetensors
Model Card on HF 🤗: https://huggingface.co/azarafrooz/phi-gemma-nlaf-v1
Phi Gemma Nlaf V1 Benchmarks
ARC: 43.86 vs 96.7 (so35)-54.6%
HellaSwag: 62.7 vs 95.3 (gpt4)-34.2%
MMLU: 37.58 vs 88.3 (so35)-57.4%
TruthfulQA: 45.86 vs 59 (gpt4)-22.3%
WinoGrande: 61.17 vs 87.5 (gpt4)-30.1%
GSM8K: 5.84 vs 96.4 (so35)-93.9%
LLME Score: 0.18716
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 Gemma Nlaf V1 Parameters and Internals
| LLM Name | Phi Gemma Nlaf V1 |
| Repository 🤗 | https://huggingface.co/azarafrooz/phi-gemma-nlaf-v1 |
| Base Model(s) | |
| Model Size | 2b |
| Required VRAM | 0.1 GB |
| Updated | 2025-09-19 |
| Maintainer | azarafrooz |
| Model Files | |
| Model Architecture | Adapter |
| License | apache-2.0 |
| Is Biased | none |
| PEFT Type | LORA |
| LoRA Model | Yes |
| PEFT Target Modules | v_proj|gate_proj|k_proj|up_proj|down_proj|o_proj|q_proj |
| LoRA Alpha | 32 |
| LoRA Dropout | 0.05 |
| R Param | 16 |
Best Alternatives to Phi Gemma Nlaf V1
Best Alternatives |
Context / RAM |
Downloads |
Likes |
|---|---|---|---|
| Finetuned Gemma3 | 8K / 5.1 GB | 8 | 0 |
| Gemma 2 2B It Dolly 15K | 0K / 0.1 GB | 5 | 0 |
| Phi Gemma Nlaf V0 | 0K / 0.1 GB | 5 | 0 |
| Gemma 2B It Nlai P1 | 0K / 0 GB | 5 | 0 |
| Gemma 2 2B Norobots | 0K / 0.1 GB | 7 | 0 |
| Ger Lora 3K Checkpoint | 0K / 0 GB | 8 | 0 |
| 1 8K Adater Ger | 0K / 0 GB | 5 | 0 |
| German 2B Lora 6K | 0K / 0 GB | 5 | 0 |
| 2B Lora Adapter Llama Alpaca | 0K / 0.1 GB | 9 | 0 |
| Google Gemma 2B 1719883948 | 0K / 0 GB | 8 | 0 |
Note: green Score (e.g. "73.2") means that the model is better than azarafrooz/phi-gemma-nlaf-v1 .
Rank the Phi Gemma Nlaf V1 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? 51544 in total.
Original data from HuggingFace, OpenCompass and various public git repos.
Release v20241124