Mistral-Nemo-Instruct-2407-exl2 - a DrNicefellow Collection

DrNicefellow 's Collections

Qwen2.5-32B-Instruct-exl2

Qwen2.5-14B-Instruct-exl2

Qwen2.5-Coder-7B-Instruct

Qwen2.5-Math-7B-Instruct

Qwen2.5-7B-Instruct-exl2

Dr. Nicefellow's Quality Worryfree Datasets

Finetuned Models

Llama-2b-from-scratch

ChatAllInOne-Quantized

Trimmed-Mixtral-instruct

Extracted_Models_From_Mixtral_8x7B

GPT-2-Large-From-Scratch

Microscopic-Mistral

Microscopic-Olmo

Microscopic-Mamba-2.1B

Datasets-For-Finetuning

Mistral-Nemo-Instruct-2407-exl2

Mistral-Nemo-Instruct-2407-exl2

updated Sep 21

A friendly reminder: change the max_seq_len in text-generation-web-ui, otherwise, you get CUDA outta memory.