Merged Model Autotrain compatible Conversational En Endpoints compatible Finetuned Grpo Mistral Qlora Region:us Safetensors Sft Sharded Tensorflow
Model Card on HF 🤗: https://huggingface.co/Nitral-AI/Captain-Eris_Violet-GRPO-v0.420
Captain Eris Violet GRPO V0.420 Benchmarks
MMLU Pro: 28.16
GPQA: 6.49
MUSR: 12.46
BBH: 31.11
IFEval: 62.62 vs 88 (so35)-28.8%
MATH Lvl 5: 10.8
LLME Score: 0.34534
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 GRPO V0.420 Parameters and Internals
| LLM Name | Captain Eris Violet GRPO V0.420 |
| Repository 🤗 | https://huggingface.co/Nitral-AI/Captain-Eris_Violet-GRPO-v0.420 |
| Base Model(s) | |
| Merged Model | Yes |
| Model Size | 12.2b |
| Required VRAM | 24.5 GB |
| Updated | 2025-04-19 |
| Maintainer | Nitral-AI |
| Model Type | mistral |
| Model Files | |
| Supported Languages | en |
| Model Architecture | MistralForCausalLM |
| License | other |
| Context Length | 1024000 |
| Model Max Length | 1024000 |
| Transformers Version | 4.48.2 |
| Tokenizer Class | PreTrainedTokenizerFast |
| Padding Token | <pad> |
| Vocabulary Size | 131072 |
| Torch Data Type | bfloat16 |
Best Alternatives to Captain Eris Violet GRPO V0.420
Best Alternatives |
Context / RAM |
Downloads |
Likes |
|---|---|---|---|
| MMRExCEV GRPO V0.420 | 1000K / 24.5 GB | 20 | 2 |
| NemoContinuedFine | 1000K / 24.5 GB | 673 | 0 |
| ...ish Mistral Nemo Instruct 2407 | 1000K / 24.5 GB | 77 | 2 |
| MMR E1 | 1000K / 24.5 GB | 4 | 1 |
| MMR E1 | 1000K / 24.5 GB | 4 | 1 |
| Violet Twilight V0.2 | 1000K / 24.5 GB | 254 | 31 |
| Mistral Nemo Kurdish | 1000K / 24.5 GB | 76 | 3 |
| Mergekit Passthrough Gujurtn | 1000K / 24.5 GB | 20 | 0 |
| Mergekit Model Stock Caxsfuh | 1000K / 24.5 GB | 15 | 0 |
| Mergekit Model Stock Mhvxkzw | 1000K / 24.5 GB | 23 | 0 |
Rank the Captain Eris Violet GRPO V0.420 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? 46490 in total.
Original data from HuggingFace, OpenCompass and various public git repos.
Release v20241227