Dangerous En Erp Explicit Instruct Mistral Nsfw Region:us Roleplay Safetensors Sharded Tensorflow Unaligned
Model Card on HF 🤗: https://huggingface.co/ReadyArt/Forgotten-Safeword-12B-V3.0
Forgotten Safeword 12B V3.0 Benchmarks
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)
Forgotten Safeword 12B V3.0 Parameters and Internals
| LLM Name | Forgotten Safeword 12B V3.0 |
| Repository 🤗 | https://huggingface.co/ReadyArt/Forgotten-Safeword-12B-V3.0 |
| Model Size | 12b |
| Required VRAM | 24.5 GB |
| Updated | 2025-09-21 |
| Maintainer | ReadyArt |
| Model Type | mistral |
| Instruction-Based | Yes |
| Model Files | |
| Supported Languages | en |
| Model Architecture | MistralForCausalLM |
| License | apache-2.0 |
| Context Length | 131072 |
| Model Max Length | 131072 |
| Transformers Version | 4.48.3 |
| Tokenizer Class | PreTrainedTokenizerFast |
| Padding Token | </s> |
| Vocabulary Size | 131072 |
| Torch Data Type | bfloat16 |
Best Alternatives to Forgotten Safeword 12B V3.0
Best Alternatives |
Context / RAM |
Downloads |
Likes |
|---|---|---|---|
| ...r Nemo 12B Instruct R 21 09 24 | 1000K / 24.5 GB | 310835 | 132 |
| Impish Nemo 12B | 1000K / 24.5 GB | 2076 | 43 |
| SauerkrautLM Nemo 12B Instruct | 1000K / 24.5 GB | 47510 | 22 |
| MN Slush | 1000K / 24.5 GB | 173 | 32 |
| ChatWaifu V1.4 | 1000K / 24.5 GB | 334 | 20 |
| Magnum V4 12B | 1000K / 24.5 GB | 248 | 44 |
| ChatWaifu 12B V2.0 | 1000K / 24.5 GB | 167 | 22 |
| Moondark 12B | 1000K / 24.5 GB | 18 | 2 |
| Mistral Nemo Bophades 12B | 1000K / 24.5 GB | 16 | 9 |
| Mistral Nemo Wissenschaft 12B | 1000K / 24.5 GB | 35 | 8 |
Note: green Score (e.g. "73.2") means that the model is better than ReadyArt/Forgotten-Safeword-12B-V3.0 .
Rank the Forgotten Safeword 12B V3.0 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? 51485 in total.
Original data from HuggingFace, OpenCompass and various public git repos.
Release v20241124