# ChatML Format

This is a 12B-parameter multilingual large language model fused using the SLERP method, supporting English and Japanese processing.

HMS-Slerp-12B is a multilingual chat model merged using the SLERP (Spherical Linear Interpolation) method, supporting both English and Japanese.

An upgraded version of Mag-Picaro, funded by PygmalionAI, fine-tuned based on Qwen-2-Instruct and merged with Magnum-V2, a 72B parameter model

This is a quantized version based on the Gryphe/Pantheon-RP-1.8-24b-Small-3.1 model, using llama.cpp for quantization, suitable for role-playing and text generation tasks.

A 7B parameter model focused on roleplay, with this merged version emphasizing enhanced creativity and reduced clichés.

HelpingAI-Vision is an innovative vision-language model that enhances scene understanding through partitioned visual token embeddings.

A 68-million-parameter Llama chat model fine-tuned on multiple high-quality dialogue datasets, suitable for various conversational tasks.

Qwen-1.8B model fine-tuned on English-Vietnamese bilingual data using ChatML prompt template format

A cybersecurity-specific model fine-tuned based on Cerebras-GPT-6.7B, with basic conversational capabilities

VinaLLaMA is a Vietnamese large language model based on the LLaMA2 architecture, supporting Vietnamese text generation and comprehension tasks.

MommyGPT-3B is a conversational AI fine-tuned on the OpenLLaMa 3B V2 model, simulating a maternal figure to provide caring dialogue

Synatra-7B-v0.3-RP is a Korean large language model fine-tuned based on Mistral-7B-Instruct-v0.1, specializing in role-play and dialogue generation.