Arxiv:1910.09700 Adapter Base model:adapter:rizla/rizla... Base model:rizla/rizla-17 Finetuned Lora Peft Region:us Safetensors
Model Card on HF 🤗: https://huggingface.co/rizla/trrapi-16
Trrapi 16 Benchmarks
ARC: 66.38 vs 96.7 (so35)-31.4%
HellaSwag: 85.05 vs 95.3 (gpt4)-10.8%
MMLU: 64.84 vs 88.3 (so35)-26.6%
TruthfulQA: 56.47 vs 59 (gpt4)-4.3%
WinoGrande: 84.14 vs 87.5 (gpt4)-3.8%
GSM8K: 68.23 vs 96.4 (so35)-29.2%
LLME Score: 0.14885
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)
Trrapi 16 Parameters and Internals
| LLM Name | Trrapi 16 |
| Repository 🤗 | https://huggingface.co/rizla/trrapi-16 |
| Base Model(s) | |
| Required VRAM | 0 GB |
| Updated | 2025-08-19 |
| Maintainer | rizla |
| Model Files | |
| Model Architecture | Adapter |
| License | apache-2.0 |
| Is Biased | none |
| PEFT Type | LORA |
| LoRA Model | Yes |
| PEFT Target Modules | w3|q_proj|w1|o_proj|w2|k_proj|v_proj|gate |
| LoRA Alpha | 16 |
| LoRA Dropout | 0.05 |
| R Param | 32 |
Best Alternatives to Trrapi 16
Best Alternatives |
Context / RAM |
Downloads |
Likes |
|---|---|---|---|
| Nemo Kimi Lora | 0K / 1.8 GB | 27 | 0 |
| Nemo Books Lora 4 | 0K / 1.8 GB | 5 | 0 |
| Nemo Books Lora | 0K / 1.8 GB | 6 | 0 |
| Phi 3 Mini 4K Instruct Sa V0.1 | 0K / 0 GB | 5 | 0 |
| Francois KTO Lora | 0K / 0 GB | 11 | 0 |
| Francois KTO Lora | 0K / 0 GB | 6 | 0 |
| Rei V2 Kto | 0K / 0 GB | 13 | 0 |
| ...caaaf043da230d9a30d8e0ddcbe879 | 0K / 0.4 GB | 11 | 0 |
| ...357cade9cc1096cecc35c34dba8992 | 0K / 1.3 GB | 10 | 0 |
| Rei V2 Kto | 0K / 0 GB | 6 | 0 |
Note: green Score (e.g. "73.2") means that the model is better than rizla/trrapi-16 .
Rank the Trrapi 16 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? 50751 in total.
Original data from HuggingFace, OpenCompass and various public git repos.
Release v20241124