twodgirl / Nimue-3.2B

Nimue 3.2B

Adapter model for Llama-3.2.

Quickstart

model = AutoModelForCausalLM.from_pretrained('twodgirl/Nimue-3.2B')

Datasets

Datasets about unexpected events:

• allenai/UNcommonsense (conversation format)
• grimulkan/theory-of-mind (summarization)
• twodgirl/tama (a cat talks to its owner)

Datasets about personality traits:

• allenai/soda
• IlyaGusev/pippa_scored
• twodgirl/ewheel
• twodgirl/pi (conversation made up by Pi, the emotionally intelligent chatbot)

Datasets by response length:

• athirdpath/Roleplay-Alpaca-NSFW (long)
• fnlp/character-llm-data (short)
• twodgirl/kimiko_v3 (short)
• twodgirl/theory-of-mind (short summarization)
• twodgirl/pi (short)

Unsafe roleplay:

• ClericalAid/roleplay-scripts
• roleplay4fun/aesir-v1.1

Disclaimer

Sharing the adapter and the deritative merges, especially with an identical/blank readme file, is discouraged.

Reuploading the adapter/merged models can cause versioning issues. Please, keep these modifications, merge of this adapter private. This will help me ensure users have access to the latest, updated models.

If you've created a custom, complex merge with multiple adapters, that's a different story; you're free to use the weights. If you'd like to share your work, please link back to the Hugging Face profile.