Merged Model Autotrain compatible Base model:bamec66557/mischiev... Base model:bamec66557/mischiev... Conversational En Endpoints compatible Ko Mistral Model-index Not-for-all-audiences Region:us Safetensors Sharded Tensorflow
Model Card on HF 🤗: https://huggingface.co/bamec66557/MISCHIEVOUS-12B-Mix_0.5v
MISCHIEVOUS 12B Mix 0.5v Benchmarks
MMLU Pro: 29.57
GPQA: 9.4
MUSR: 11.54
BBH: 34.18
IFEval: 37.46 vs 88 (so35)-57.4%
MATH Lvl 5: 12.69
LLME Score: 0.34276
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)
MISCHIEVOUS 12B Mix 0.5v Parameters and Internals
| LLM Name | MISCHIEVOUS 12B Mix 0.5v |
| Repository 🤗 | https://huggingface.co/bamec66557/MISCHIEVOUS-12B-Mix_0.5v |
| Base Model(s) | |
| Merged Model | Yes |
| Model Size | 12b |
| Required VRAM | 24.5 GB |
| Updated | 2024-12-30 |
| Maintainer | bamec66557 |
| Model Type | mistral |
| Model Files | |
| Supported Languages | en ko |
| Model Architecture | MistralForCausalLM |
| License | apache-2.0 |
| Context Length | 1024000 |
| Model Max Length | 1024000 |
| Transformers Version | 4.46.2 |
| Tokenizer Class | PreTrainedTokenizerFast |
| Vocabulary Size | 131074 |
| Torch Data Type | bfloat16 |
Best Alternatives to MISCHIEVOUS 12B Mix 0.5v
Best Alternatives |
Context / RAM |
Downloads |
Likes |
|---|---|---|---|
| ...s PersonalityEngine V1.1.0 12B | 1000K / 24.5 GB | 206 | 16 |
| ...r Nemo 12B Instruct R 21 09 24 | 1000K / 24.5 GB | 18689 | 97 |
| SauerkrautLM Nemo 12B Instruct | 1000K / 24.5 GB | 29279 | 22 |
| MISCHIEVOUS 12B Mix 0.4v | 1000K / 24.5 GB | 206 | 2 |
| VICIOUS MESH 12B BETA | 1000K / 24.5 GB | 85 | 2 |
| Dolphin 2.9.3 Mistral Nemo 12B | 1000K / 24.5 GB | 8483 | 93 |
| MISCHIEVOUS 12B Mix III Ex V | 1000K / 24.5 GB | 265 | 0 |
| MISCHIEVOUS 12B | 1000K / 24.5 GB | 245 | 3 |
| VICIOUS MESH 12B ALPHA | 1000K / 24.5 GB | 61 | 1 |
| MISCHIEVOUS 12B Mix 0.3v | 1000K / 24.5 GB | 244 | 0 |
Note: green Score (e.g. "73.2") means that the model is better than bamec66557/MISCHIEVOUS-12B-Mix_0.5v .
Rank the MISCHIEVOUS 12B Mix 0.5v 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? 40476 in total.
Original data from HuggingFace, OpenCompass and various public git repos.
Release v20241227