juvi21/Hermes-2-Theta-L3-Euryale-Ties-0.8-70B
The juvi21/Hermes-2-Theta-L3-Euryale-Ties-0.8-70B is a 70 billion parameter language model, merged using the TIES method, based on NousResearch/Hermes-2-Theta-Llama-3-70B. This model integrates Sao10K/L3-70B-Euryale-v2.1 to enhance roleplay performance. It is specifically designed to offer a balanced mix of capabilities from its constituent models, making it suitable for advanced conversational and roleplaying applications.
Loading preview...
Model Overview
This model, juvi21/Hermes-2-Theta-L3-Euryale-Ties-0.8-70B, is a 70 billion parameter language model created through a merge of pre-trained models using the TIES merge method. The primary goal of this merge was to enhance roleplay performance by combining two strong base models.
Merge Details
The model uses NousResearch/Hermes-2-Theta-Llama-3-70B as its base, with a weight of 0.8, and integrates Sao10K/L3-70B-Euryale-v2.1 with a weight of 0.2. This specific configuration was chosen to achieve an optimal blend of their respective strengths, particularly for conversational and roleplaying scenarios.
Key Characteristics
- Architecture: Llama-3 based, 70 billion parameters.
- Merge Method: TIES (Trimmed, Iterative, Extracted, and Merged Subnetworks).
- Focus: Enhanced roleplay capabilities through strategic model merging.
- Context Length: Supports an 8192-token context window.
Ideal Use Cases
- Advanced Roleplaying: Designed for nuanced and engaging character interactions.
- Conversational AI: Suitable for applications requiring sophisticated dialogue generation.
- Experimental Merges: Represents an exploration into combining models for specific performance gains.
Top 3 parameter combinations used by Featherless users for this model. Click a tab to see each config.