# English generation

ZeroWw is a quantized text generation model that uses f16 format for output and embedding tensors, while other tensors use q5_k or q6_k format, resulting in a smaller size with performance comparable to pure f16.

This is a 4-bit quantized version converted from the allenai/OLMo-2-0325-32B-Instruct model, optimized for the MLX framework and suitable for text generation tasks.

This is an ablated model based on mistralai/Mistral-Small-Instruct-2409, mainly used for text generation tasks.

GIGABATEMAN-7B is a 7B-parameter large language model based on the Mistral architecture, focusing on text generation tasks.

This is a small 7B-parameter LLM optimized for device-side use, pruned and trained with DPO

Cerebras-GPT 13B is a large language model trained based on an open architecture and dataset. It belongs to the Cerebras-GPT series and aims to study the scaling laws of large language models and demonstrate the simplicity and scalability of training on the Cerebras software and hardware stack.