Update mixture_of_recursion.py

Adding `safetensors` variant of this model (#1)

Update model_usage.py

Update mixture_of_recursion.py

Update README.md

Update model_usage.py

Update mixture_of_recursion.py

Update config.json

Rename vocab (2).json to vocab.json

Rename train (2).py to train.py

Rename tokenizer_config (2).json to tokenizer_config.json

Rename merges (2).txt to merges.txt

Upload 8 files

model.safetensors

vocab.json

train.py

tokenizer_config.json

special_tokens_map.json

mixture_of_recursion.py

merges.txt

best_model_checkpoint.pt

Update mixture_of_recursion.py

Fix attention mask shape for batch_first=True

Update mixture_of_recursion.py

Fix attention mask and recursive logic bugs

Update README.md

Update README.md

Update README.md

Update mixture_of_recursion.py

Update mixture_of_recursion.py

Update mixture_of_recursion.py

Update train.py

Update model_usage.py

Update mixture_of_recursion.py

Update model_usage.py

Update README.md

Update README.md

Update mixture_of_recursion.py

Update mixture_of_recursion.py

Rename tokenizer/vocab.json to vocab.json

Rename tokenizer/tokenizer_config.json to tokenizer_config.json

Rename tokenizer/special_tokens_map.json to special_tokens_map.json

Rename tokenizer/merges.txt to merges.txt

embeddings.py

Update mixture_of_recursion.py

Rename trained_model/tokenizer/vocab.json to tokenizer/vocab.json

Rename trained_model/tokenizer/tokenizer_config.json to tokenizer/tokenizer_config.json

Rename trained_model/tokenizer/special_tokens_map.json to tokenizer/special_tokens_map.json

Rename trained_model/tokenizer/merges.txt to tokenizer/merges.txt

Rename trained_model/model.safetensors to model.safetensors