Model Card on HF 🤗: https://huggingface.co/Nitrals-Loras/Captain-Eris_Violet-Toxic-GRPO-v0.4-lora
Captain Eris Violet Toxic GRPO V0.4 Lora 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)
Captain Eris Violet Toxic GRPO V0.4 Lora Parameters and Internals
| LLM Name | Captain Eris Violet Toxic GRPO V0.4 Lora |
| Repository 🤗 | https://huggingface.co/Nitrals-Loras/Captain-Eris_Violet-Toxic-GRPO-v0.4-lora |
| Base Model(s) | |
| Required VRAM | 0.5 GB |
| Updated | 2025-06-09 |
| Maintainer | Nitrals-Loras |
| Model Files | |
| Model Architecture | Adapter |
| Model Max Length | 1024000 |
| Is Biased | none |
| Tokenizer Class | PreTrainedTokenizerFast |
| Padding Token | <pad> |
| PEFT Type | LORA |
| LoRA Model | Yes |
| PEFT Target Modules | gate_proj|k_proj|o_proj|up_proj|q_proj|v_proj|down_proj |
| LoRA Alpha | 32 |
| LoRA Dropout | 0 |
| R Param | 32 |
Best Alternatives to Captain Eris Violet Toxic GRPO V0.4 Lora
Best Alternatives |
Context / RAM |
Downloads |
Likes |
|---|---|---|---|
| Phi 3 Mini 4K Instruct Sa V0.1 | 0K / 0 GB | 10 | 0 |
| Francois KTO Lora | 0K / 0 GB | 11 | 0 |
| Francois KTO Lora | 0K / 0 GB | 11 | 0 |
| Rei V2 Kto | 0K / 0 GB | 13 | 0 |
| ...caaaf043da230d9a30d8e0ddcbe879 | 0K / 0.4 GB | 11 | 0 |
| Rei V2 Kto | 0K / 0 GB | 9 | 0 |
| ...357cade9cc1096cecc35c34dba8992 | 0K / 1.3 GB | 10 | 0 |
| Reflection Model | 0K / 0.2 GB | 0 | 1 |
| Samantha Omni Humanlike Lora | 0K / 0 GB | 7 | 3 |
| SpectraMind | 0K / 16.1 GB | 120 | 3 |
Note: green Score (e.g. "73.2") means that the model is better than Nitrals-Loras/Captain-Eris_Violet-Toxic-GRPO-v0.4-lora .
Rank the Captain Eris Violet Toxic GRPO V0.4 Lora 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? 48023 in total.
Original data from HuggingFace, OpenCompass and various public git repos.
Release v20241124