# Multi-domain text generation

A multilingual, multi-purpose large language model supporting various professional domains and general tasks, suitable for role-playing, story creation, programming, and other scenarios.

Falcon-H1-34B-Instruct is a large language model with 34B parameters, focusing on instruction-following tasks.

Llamacpp imatrix quantized version based on PocketDoc/Dans-SakuraKaze-V1.0.0-12b, supporting multiple quantization types, suitable for text generation tasks.

PathummaLLM-text-1.0.0-7B is a large language model with 7 billion parameters that supports Thai, Chinese, and English. It is fine-tuned based on OpenThaiLLM-Prebuilt for instruction, optimizing RAG, constrained generation, and reasoning tasks.

A large Bengali language model optimized based on the Llama-3.2-3B architecture, with 42K Bengali tokens extended and fine-tuned, performing excellently in Bengali understanding and generation tasks.

A medium-sized GPT-2 pre-trained model for Indonesian language, trained with causal language modeling objective, suitable for Indonesian text generation tasks.

A T5-based model capable of converting input keywords into complete sentences.

Hebrew text generation model based on GPT-Neo architecture, specifically optimized for Hebrew

GPT2 model pre-trained for Italian language, 117M parameters, trained on Italian Wikipedia and ItWac corpus