Base model:finetune:pocketdoc/... Base model:pocketdoc/dans-pers... Dataset:pocketdoc/dans-failure... Dataset:pocketdoc/dans-persona... Dataset:pocketdoc/dans-persona... Dataset:pocketdoc/dans-persona... Dataset:pocketdoc/dans-persona... Dataset:pocketdoc/dans-prosema... Dataset:pocketdoc/dans-prosema... Dataset:pocketdoc/dans-prosema... Dataset:pocketdoc/dans-prosema... En Mistral Region:us Safetensors Sharded Tensorflow
Model Card on HF 🤗: https://huggingface.co/PocketDoc/Dans-SakuraKaze-V1.0.0-12b
Dans SakuraKaze V1.0.0 12B Benchmarks
MMLU Pro: 28.44
GPQA: 5.82
MUSR: 19.58
BBH: 34.39
IFEval: 65.2 vs 88 (so35)-25.9%
MATH Lvl 5: 9.29
LLME Score: 0.33778
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)
Dans SakuraKaze V1.0.0 12B Parameters and Internals
| LLM Name | Dans SakuraKaze V1.0.0 12B |
| Repository 🤗 | https://huggingface.co/PocketDoc/Dans-SakuraKaze-V1.0.0-12b |
| Base Model(s) | |
| Model Size | 12b |
| Required VRAM | 24.5 GB |
| Updated | 2025-04-23 |
| Maintainer | PocketDoc |
| Model Type | mistral |
| Model Files | |
| Supported Languages | en |
| Model Architecture | MistralForCausalLM |
| License | apache-2.0 |
| Context Length | 1024000 |
| Model Max Length | 1024000 |
| Transformers Version | 4.46.3 |
| Tokenizer Class | PreTrainedTokenizerFast |
| Padding Token | <pad> |
| Vocabulary Size | 131072 |
| Torch Data Type | bfloat16 |
Best Alternatives to Dans SakuraKaze V1.0.0 12B
Best Alternatives |
Context / RAM |
Downloads |
Likes |
|---|---|---|---|
| Captain Eris Violet V0.420 12B | 1000K / 24.5 GB | 532705 | 40 |
| Captain Eris BMO Violent 12B | 1000K / 24.5 GB | 305 | 2 |
| ...r Nemo 12B Instruct R 21 09 24 | 1000K / 24.5 GB | 3936 | 118 |
| ...s PersonalityEngine V1.1.0 12B | 1000K / 24.5 GB | 384 | 39 |
| MN 12B Mag Mell R1 | 1000K / 24.5 GB | 2795 | 156 |
| ...n Eris BMO Violent GRPO V0.420 | 1000K / 24.5 GB | 92 | 3 |
| Mistral Nemo Kartoffel 12B | 1000K / 24.5 GB | 69 | 5 |
| Dolphin 2.9.3 Mistral Nemo 12B | 1000K / 24.5 GB | 4669 | 99 |
| Nullsworn 12B LINEAR | 1000K / 24.5 GB | 41 | 0 |
| BigKartoffel Mistral Nemo 20B | 1000K / 41.1 GB | 23 | 3 |
Note: green Score (e.g. "73.2") means that the model is better than PocketDoc/Dans-SakuraKaze-V1.0.0-12b .
Rank the Dans SakuraKaze V1.0.0 12B 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? 46599 in total.
Original data from HuggingFace, OpenCompass and various public git repos.
Release v20241227