Update model_slm.py

Update model_slm.py

Delete embeddings.py

Merge embeddings and add Transformers support

Update model_slm.py

Update config.json

Update config.json

Create configuration_mixture_of_recursions.py

Create modeling_mixture_of_recursions.py

Update config.json

Upload pytorch_model.bin with huggingface_hub

Upload config.json with huggingface_hub

Update train.py

Update model_slm.py

Update embeddings.py

Update custom_tokenizer.py

Update README.md

Update README.md

Rename best_model.pt to checkpoints/best_model.pt

Upload best_model.pt

Rename ultra_fast_results (1).json to ultra_fast_results .json

Upload ultra_fast_results (1).json

Create requirements.txt

Rename merges.txt to tokenizer/merges.txt

Rename vocab.json to tokenizer/vocab.json

Rename tokenizer_config.json to tokenizer/tokenizer_config.json

Rename token_frequencies.pkl to tokenizer/token_frequencies.pkl

Upload 4 files

Create train.py

Rename slm_training_complete_chat_val (1).txt to split_data/slm_training_complete_chat_val.txt

Rename split_data/slm_training_complete_chat_train (1).txt to split_data/slm_training_complete_chat_train .txt

Rename slm_training_complete_chat_train (1).txt to split_data/slm_training_complete_chat_train (1).txt

Rename slm_training_complete_chat_test (1).txt to split_data/slm_training_complete_chat_test (1).txt

Upload 3 files

Upload slm_training_complete_chat.txt

Create model_slm.py

Create embeddings.py

Create custom_tokenizer.py

initial commit