├── LICENSE ├── imgs └── multiple_token_prediction_needs_registers-v3.1.jpg ├── language_modeling ├── mutor_lm_doc.md ├── requirements.txt ├── scripts │ ├── bash_0.sh │ ├── bash_1.sh │ └── launch_finetuning.sh └── src │ ├── args_mutor.py │ ├── dataloaders_mutor.py │ ├── eval │ ├── evaluate_gsm8k.py │ ├── evaluate_math500.py │ ├── generation_utils.py │ └── math_utils.py │ ├── finetune.py │ └── models │ ├── bi_gemma.py │ ├── bi_llama.py │ ├── gemma_mutor.py │ └── llama_mutor.py └── readme.md /LICENSE: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/nasosger/MuToR/HEAD/LICENSE -------------------------------------------------------------------------------- /imgs/multiple_token_prediction_needs_registers-v3.1.jpg: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/nasosger/MuToR/HEAD/imgs/multiple_token_prediction_needs_registers-v3.1.jpg -------------------------------------------------------------------------------- /language_modeling/mutor_lm_doc.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/nasosger/MuToR/HEAD/language_modeling/mutor_lm_doc.md -------------------------------------------------------------------------------- /language_modeling/requirements.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/nasosger/MuToR/HEAD/language_modeling/requirements.txt -------------------------------------------------------------------------------- /language_modeling/scripts/bash_0.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/nasosger/MuToR/HEAD/language_modeling/scripts/bash_0.sh -------------------------------------------------------------------------------- /language_modeling/scripts/bash_1.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/nasosger/MuToR/HEAD/language_modeling/scripts/bash_1.sh -------------------------------------------------------------------------------- /language_modeling/scripts/launch_finetuning.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/nasosger/MuToR/HEAD/language_modeling/scripts/launch_finetuning.sh -------------------------------------------------------------------------------- /language_modeling/src/args_mutor.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/nasosger/MuToR/HEAD/language_modeling/src/args_mutor.py -------------------------------------------------------------------------------- /language_modeling/src/dataloaders_mutor.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/nasosger/MuToR/HEAD/language_modeling/src/dataloaders_mutor.py -------------------------------------------------------------------------------- /language_modeling/src/eval/evaluate_gsm8k.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/nasosger/MuToR/HEAD/language_modeling/src/eval/evaluate_gsm8k.py -------------------------------------------------------------------------------- /language_modeling/src/eval/evaluate_math500.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/nasosger/MuToR/HEAD/language_modeling/src/eval/evaluate_math500.py -------------------------------------------------------------------------------- /language_modeling/src/eval/generation_utils.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/nasosger/MuToR/HEAD/language_modeling/src/eval/generation_utils.py -------------------------------------------------------------------------------- /language_modeling/src/eval/math_utils.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/nasosger/MuToR/HEAD/language_modeling/src/eval/math_utils.py -------------------------------------------------------------------------------- /language_modeling/src/finetune.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/nasosger/MuToR/HEAD/language_modeling/src/finetune.py -------------------------------------------------------------------------------- /language_modeling/src/models/bi_gemma.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/nasosger/MuToR/HEAD/language_modeling/src/models/bi_gemma.py -------------------------------------------------------------------------------- /language_modeling/src/models/bi_llama.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/nasosger/MuToR/HEAD/language_modeling/src/models/bi_llama.py -------------------------------------------------------------------------------- /language_modeling/src/models/gemma_mutor.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/nasosger/MuToR/HEAD/language_modeling/src/models/gemma_mutor.py -------------------------------------------------------------------------------- /language_modeling/src/models/llama_mutor.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/nasosger/MuToR/HEAD/language_modeling/src/models/llama_mutor.py -------------------------------------------------------------------------------- /readme.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/nasosger/MuToR/HEAD/readme.md --------------------------------------------------------------------------------