| Re-Upload of https://huggingface.co/dunzhang/stella_en_400M_v5 with : | |
| - Only 1024 embeddings dimensions folder | |
| - Max tokens lenght to 512 ( model has been trained on this sequence lenght ) | |
| - Padding strategy set to "BatchLongest" to avoid batching every line to a fixed length of 512 tokens in case of size less than 512. Remove unecessary padding. | |
| Parameters at the end of the file "config.json" has been set manually to false for CPU usage: | |
| ```"unpad_inputs": false, "use_memory_efficient_attention": false``` | |
| You can turn them back to "true" to enable GPU usage back again |