Model Card on HF 🤗: https://huggingface.co/Azazelle/Luna_Llama3
Luna Llama3 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)
Luna Llama3 Parameters and Internals
| LLM Name | Luna Llama3 |
| Repository 🤗 | https://huggingface.co/Azazelle/Luna_Llama3 |
| Base Model(s) | |
| Model Size | 8b |
| Required VRAM | 0.2 GB |
| Updated | 2025-09-23 |
| Maintainer | Azazelle |
| Model Files | |
| Model Architecture | Adapter |
| Is Biased | none |
| PEFT Type | LORA |
| LoRA Model | Yes |
| PEFT Target Modules | v_proj|q_proj |
| LoRA Alpha | 128 |
| LoRA Dropout | 0.05 |
| R Param | 128 |
Best Alternatives to Luna Llama3
Best Alternatives |
Context / RAM |
Downloads |
Likes |
|---|---|---|---|
| ... 3 8B Instruct Bvr Finetune V3 | 8K / 16.1 GB | 7 | 0 |
| Flippa V6 | 0K / 0 GB | 1653 | 1 |
| ...B Instruct DPO 0R100L PoliTune | 0K / 16.1 GB | 6 | 0 |
| Llama 3 Korean 8B R V 0.1 | 0K / 0 GB | 20 | 0 |
| ...B Lora Rag Citation Generation | 0K / 0 GB | 11 | 3 |
| Suavemente 8B R128 LORA | 0K / 2.8 GB | 9 | 0 |
| ...a 8B Rank 128 INSTRUCT Adapter | 0K / 0.7 GB | 18 | 1 |
| ...ning Llama 8B Rank 128 Adapter | 0K / 0.7 GB | 3 | 1 |
| L3 Umbral Mind R128 LoRA | 0K / 0.7 GB | 4 | 3 |
| ...a7 4262 4abb 97b1 1879f340d32e | 0K / 0.3 GB | 5 | 0 |
Note: green Score (e.g. "73.2") means that the model is better than Azazelle/Luna_Llama3 .
Rank the Luna Llama3 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