Merged Model Arxiv:2306.01708 Autotrain compatible Base model:bamec66557/vicious ... Base model:infermatic/mn-12b-i... Base model:khetterman/darkatom... Conversational Dataset:open-llm-leaderboard/b... En Endpoints compatible Es Ja Ko Mistral Model-index Not-for-all-audiences Region:us Ru Safetensors Sharded Tensorflow Zh
Model Card on HF 🤗: https://huggingface.co/bamec66557/VICIOUS_MESH-12B-BETA
VICIOUS MESH 12B BETA Benchmarks
MMLU Pro: 29.76
GPQA: 8.84
MUSR: 14.34
BBH: 31.36
IFEval: 67.21 vs 88 (so35)-23.6%
MATH Lvl 5: 13.29
LLME Score: 0.31319
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)
VICIOUS MESH 12B BETA Parameters and Internals
| LLM Name | VICIOUS MESH 12B BETA |
| Repository 🤗 | https://huggingface.co/bamec66557/VICIOUS_MESH-12B-BETA |
| Base Model(s) | |
| Merged Model | Yes |
| Model Size | 12b |
| Required VRAM | 24.5 GB |
| Updated | 2025-03-13 |
| Maintainer | bamec66557 |
| Model Type | mistral |
| Model Files | |
| Supported Languages | en ja ru zh ko es |
| Model Architecture | MistralForCausalLM |
| License | apache-2.0 |
| Context Length | 1024000 |
| Model Max Length | 1024000 |
| Transformers Version | 4.46.2 |
| Tokenizer Class | PreTrainedTokenizerFast |
| Padding Token | <pad> |
| Vocabulary Size | 131072 |
| Torch Data Type | bfloat16 |
Best Alternatives to VICIOUS MESH 12B BETA
Best Alternatives |
Context / RAM |
Downloads |
Likes |
|---|---|---|---|
| Captain Eris Violet V0.420 12B | 1000K / 24.5 GB | 850751 | 32 |
| Dans SakuraKaze V1.0.0 12B | 1000K / 24.5 GB | 1463 | 14 |
| Captain Eris BMO Violent 12B | 1000K / 24.5 GB | 275 | 2 |
| ...n Eris BMO Violent GRPO V0.420 | 1000K / 24.5 GB | 150 | 3 |
| ...r Nemo 12B Instruct R 21 09 24 | 1000K / 24.5 GB | 6839 | 114 |
| MN 12B Mag Mell R1 | 1000K / 24.5 GB | 7842 | 129 |
| BigKartoffel Mistral Nemo 20B | 1000K / 41.1 GB | 53 | 3 |
| ...s PersonalityEngine V1.1.0 12B | 1000K / 24.5 GB | 525 | 36 |
| Glowing Forest 12B | 1000K / 24.5 GB | 33 | 3 |
| MN 12B Mimicore Nocturne | 1000K / 24.5 GB | 16 | 2 |
Note: green Score (e.g. "73.2") means that the model is better than bamec66557/VICIOUS_MESH-12B-BETA .
Rank the VICIOUS MESH 12B BETA 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? 45005 in total.
Original data from HuggingFace, OpenCompass and various public git repos.
Release v20241227