kyx0r/Neona-12B
Neona-12B is a 12 billion parameter language model created by kyx0r through a merge of pre-trained models using the NearSwap method. It is based on yamatazen/NeonMaid-12B-v2 and incorporates yamatazen/LorablatedStock-12B. This model is designed for general language generation tasks, leveraging its merged architecture to combine capabilities from its constituent models.
Loading preview...
Overview
Neona-12B is a 12 billion parameter language model developed by kyx0r. It was constructed using the MergeKit tool, specifically employing the NearSwap merge method.
Merge Details
This model's foundation is yamatazen/NeonMaid-12B-v2, which served as the base model during the merging process. It integrates capabilities from yamatazen/LorablatedStock-12B.
Configuration
The merge utilized a bfloat16 data type and is configured with a chatml chat template, indicating its suitability for conversational AI applications. The tokenizer is sourced from the base model.
Key Characteristics
- Architecture: Merged model using NearSwap method.
- Base Model: yamatazen/NeonMaid-12B-v2.
- Integrated Model: yamatazen/LorablatedStock-12B.
- Chat Template: Configured for
chatmlformat, suggesting conversational use cases.
Potential Use Cases
Given its merged nature and chatml template, Neona-12B is likely suitable for:
- General text generation.
- Chatbot applications.
- Instruction-following tasks, depending on the capabilities inherited from its merged components.
Top 3 parameter combinations used by Featherless users for this model. Click a tab to see each config.