# Lightweight language model

Zeta 2 is a small language model (SLM) with approximately 460 million parameters, meticulously crafted on consumer-grade computers and supports multiple languages.

A lightweight Russian-English bilingual language model fine-tuned based on SmolLM2-135M, with enhanced Russian processing capabilities but notable limitations

A 1.5B parameter instruction fine-tuned model designed for Gensyn RL Swarm, supporting local fine-tuning via peer-to-peer reinforcement learning

0x Mini is a lightweight language model developed by Ozone AI, optimized based on the Llama-3.1 architecture, providing efficient text generation capabilities

This is a German Tinyllama 1B language model trained from scratch using the Tinyllama code framework and RedPajama V2 German corpus.

This is a 4-bit quantized 135M parameter small language model, suitable for text generation tasks in resource-constrained environments.

MobiLlama-1B-Chat is an instruction-following model fine-tuned from MobiLlama-1B, specifically designed for resource-constrained devices, emphasizing efficiency, low memory footprint, and fast response.

MobiLlama-05B is a small language model (SLM) with 500 million parameters, focusing on applications for resource-constrained devices, providing efficient and low-memory text generation capabilities.

Phi-1.5 model fine-tuned on the Hermes dataset, primarily used for text generation tasks

CharLLaMa-35M is a miniature language model based on the LLaMa architecture, featuring character-level tokenization, suitable for various experimental scenarios where BPE tokenization underperforms.

Korean language model fine-tuned on KoAlpaca dataset v1.0 based on KoRWKV-1.5B

This is a reduced version of the XLM-RoBERTa model, specifically optimized for Ukrainian and partial English, with parameters reduced from 470 million to 134 million.

RoFormer is a Chinese Transformer model enhanced with Rotary Position Embedding, suitable for text infilling tasks.

MiniLMv2 is a lightweight language representation model developed by Microsoft, achieving efficient performance through knowledge distillation techniques.

MiniLMv2 is a lightweight language representation model developed by Microsoft, achieving efficient inference through knowledge distillation techniques, suitable for various natural language processing tasks.