Arxiv:2203.05482 Autotrain compatible Base model:cgato/nemo-12b-thea... Base model:merge:cgato/nemo-12... Base model:merge:nbeerbower/mi... Base model:merge:redrix/patric... Base model:merge:yamatazen/ayl... Base model:nbeerbower/mistral-... Base model:redrix/patricide-12... Base model:yamatazen/ayla-ligh... Conversational Endpoints compatible Merge Mergekit Mistral Model-index Region:us Safetensors Sharded Tensorflow
Model Card on HF 🤗: https://huggingface.co/DreadPoor/Nullsworn-12B-LINEAR
Nullsworn 12B LINEAR Benchmarks
MMLU Pro: 29.39
GPQA: 7.72
MUSR: 14.44
BBH: 35.51
IFEval: 44.36 vs 88 (so35)-49.6%
MATH Lvl 5: 11.25
LLME Score: 0.33573
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)
Nullsworn 12B LINEAR Parameters and Internals
| LLM Name | Nullsworn 12B LINEAR |
| Repository 🤗 | https://huggingface.co/DreadPoor/Nullsworn-12B-LINEAR |
| Base Model(s) | |
| Model Size | 12b |
| Required VRAM | 24.5 GB |
| Updated | 2025-03-20 |
| Maintainer | DreadPoor |
| Model Type | mistral |
| Model Files | |
| Model Architecture | MistralForCausalLM |
| Context Length | 1024000 |
| Model Max Length | 1024000 |
| Transformers Version | 4.49.0 |
| Tokenizer Class | PreTrainedTokenizer |
| Padding Token | <pad> |
| Vocabulary Size | 131072 |
| Torch Data Type | bfloat16 |
Best Alternatives to Nullsworn 12B LINEAR
Best Alternatives |
Context / RAM |
Downloads |
Likes |
|---|---|---|---|
| Captain Eris Violet V0.420 12B | 1000K / 24.5 GB | 740529 | 34 |
| Dans SakuraKaze V1.0.0 12B | 1000K / 24.5 GB | 2192 | 17 |
| Captain Eris BMO Violent 12B | 1000K / 24.5 GB | 311 | 2 |
| ...n Eris BMO Violent GRPO V0.420 | 1000K / 24.5 GB | 220 | 3 |
| ...r Nemo 12B Instruct R 21 09 24 | 1000K / 24.5 GB | 6246 | 115 |
| MN 12B Mag Mell R1 | 1000K / 24.5 GB | 7571 | 133 |
| ...s PersonalityEngine V1.1.0 12B | 1000K / 24.5 GB | 442 | 37 |
| BigKartoffel Mistral Nemo 20B | 1000K / 41.1 GB | 57 | 3 |
| MN 12B Mimicore Nocturne | 1000K / 24.5 GB | 41 | 2 |
| PLLuM 12B Nc Chat | 1000K / 24.5 GB | 1538 | 5 |
Note: green Score (e.g. "73.2") means that the model is better than DreadPoor/Nullsworn-12B-LINEAR .
Rank the Nullsworn 12B LINEAR 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? 45354 in total.
Original data from HuggingFace, OpenCompass and various public git repos.
Release v20241227