├── Mini-Llama2-Chinese.png ├── README.md ├── code1 ├── config.json ├── ds_zero2_no_offload.json ├── pretrain_dataset.py ├── run_clm_pt_with_peft_modify.py └── run_pt_modify.sh └── code2 ├── pretrain_code ├── chatglm_tokenizer │ ├── __pycache__ │ │ └── tokenization_chatglm.cpython-39.pyc │ ├── tokenization_chatglm.py │ ├── tokenizer.model │ └── tokenizer_config.json ├── ds_config.json ├── model.py ├── model_config.json ├── pretrain.py ├── pretrain.sh └── pretrain_dataset.py ├── sft_code ├── __pycache__ │ ├── dataset_sft.cpython-39.pyc │ └── model.cpython-39.pyc ├── chatglm_tokenizer │ ├── __pycache__ │ │ └── tokenization_chatglm.cpython-39.pyc │ ├── tokenization_chatglm.py │ ├── tokenizer.model │ └── tokenizer_config.json ├── dataset_sft.py ├── ds_config.json ├── model.py ├── model_config.json ├── sft.py └── sft.sh └── test_code ├── __pycache__ └── model.cpython-38.pyc ├── chatglm_tokenizer ├── __pycache__ │ ├── tokenization_chatglm.cpython-38.pyc │ └── tokenization_chatglm.cpython-39.pyc ├── tokenization_chatglm.py ├── tokenizer.model └── tokenizer_config.json ├── eval_model.py ├── model.py └── model_config.json /Mini-Llama2-Chinese.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/AI-Study-Han/Mini-Llama2-Chinese/HEAD/Mini-Llama2-Chinese.png -------------------------------------------------------------------------------- /README.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/AI-Study-Han/Mini-Llama2-Chinese/HEAD/README.md -------------------------------------------------------------------------------- /code1/config.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/AI-Study-Han/Mini-Llama2-Chinese/HEAD/code1/config.json -------------------------------------------------------------------------------- /code1/ds_zero2_no_offload.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/AI-Study-Han/Mini-Llama2-Chinese/HEAD/code1/ds_zero2_no_offload.json -------------------------------------------------------------------------------- /code1/pretrain_dataset.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/AI-Study-Han/Mini-Llama2-Chinese/HEAD/code1/pretrain_dataset.py -------------------------------------------------------------------------------- /code1/run_clm_pt_with_peft_modify.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/AI-Study-Han/Mini-Llama2-Chinese/HEAD/code1/run_clm_pt_with_peft_modify.py -------------------------------------------------------------------------------- /code1/run_pt_modify.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/AI-Study-Han/Mini-Llama2-Chinese/HEAD/code1/run_pt_modify.sh -------------------------------------------------------------------------------- /code2/pretrain_code/chatglm_tokenizer/__pycache__/tokenization_chatglm.cpython-39.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/AI-Study-Han/Mini-Llama2-Chinese/HEAD/code2/pretrain_code/chatglm_tokenizer/__pycache__/tokenization_chatglm.cpython-39.pyc -------------------------------------------------------------------------------- /code2/pretrain_code/chatglm_tokenizer/tokenization_chatglm.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/AI-Study-Han/Mini-Llama2-Chinese/HEAD/code2/pretrain_code/chatglm_tokenizer/tokenization_chatglm.py -------------------------------------------------------------------------------- /code2/pretrain_code/chatglm_tokenizer/tokenizer.model: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/AI-Study-Han/Mini-Llama2-Chinese/HEAD/code2/pretrain_code/chatglm_tokenizer/tokenizer.model -------------------------------------------------------------------------------- /code2/pretrain_code/chatglm_tokenizer/tokenizer_config.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/AI-Study-Han/Mini-Llama2-Chinese/HEAD/code2/pretrain_code/chatglm_tokenizer/tokenizer_config.json -------------------------------------------------------------------------------- /code2/pretrain_code/ds_config.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/AI-Study-Han/Mini-Llama2-Chinese/HEAD/code2/pretrain_code/ds_config.json -------------------------------------------------------------------------------- /code2/pretrain_code/model.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/AI-Study-Han/Mini-Llama2-Chinese/HEAD/code2/pretrain_code/model.py -------------------------------------------------------------------------------- /code2/pretrain_code/model_config.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/AI-Study-Han/Mini-Llama2-Chinese/HEAD/code2/pretrain_code/model_config.json -------------------------------------------------------------------------------- /code2/pretrain_code/pretrain.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/AI-Study-Han/Mini-Llama2-Chinese/HEAD/code2/pretrain_code/pretrain.py -------------------------------------------------------------------------------- /code2/pretrain_code/pretrain.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/AI-Study-Han/Mini-Llama2-Chinese/HEAD/code2/pretrain_code/pretrain.sh -------------------------------------------------------------------------------- /code2/pretrain_code/pretrain_dataset.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/AI-Study-Han/Mini-Llama2-Chinese/HEAD/code2/pretrain_code/pretrain_dataset.py -------------------------------------------------------------------------------- /code2/sft_code/__pycache__/dataset_sft.cpython-39.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/AI-Study-Han/Mini-Llama2-Chinese/HEAD/code2/sft_code/__pycache__/dataset_sft.cpython-39.pyc -------------------------------------------------------------------------------- /code2/sft_code/__pycache__/model.cpython-39.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/AI-Study-Han/Mini-Llama2-Chinese/HEAD/code2/sft_code/__pycache__/model.cpython-39.pyc -------------------------------------------------------------------------------- /code2/sft_code/chatglm_tokenizer/__pycache__/tokenization_chatglm.cpython-39.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/AI-Study-Han/Mini-Llama2-Chinese/HEAD/code2/sft_code/chatglm_tokenizer/__pycache__/tokenization_chatglm.cpython-39.pyc -------------------------------------------------------------------------------- /code2/sft_code/chatglm_tokenizer/tokenization_chatglm.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/AI-Study-Han/Mini-Llama2-Chinese/HEAD/code2/sft_code/chatglm_tokenizer/tokenization_chatglm.py -------------------------------------------------------------------------------- /code2/sft_code/chatglm_tokenizer/tokenizer.model: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/AI-Study-Han/Mini-Llama2-Chinese/HEAD/code2/sft_code/chatglm_tokenizer/tokenizer.model -------------------------------------------------------------------------------- /code2/sft_code/chatglm_tokenizer/tokenizer_config.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/AI-Study-Han/Mini-Llama2-Chinese/HEAD/code2/sft_code/chatglm_tokenizer/tokenizer_config.json -------------------------------------------------------------------------------- /code2/sft_code/dataset_sft.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/AI-Study-Han/Mini-Llama2-Chinese/HEAD/code2/sft_code/dataset_sft.py -------------------------------------------------------------------------------- /code2/sft_code/ds_config.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/AI-Study-Han/Mini-Llama2-Chinese/HEAD/code2/sft_code/ds_config.json -------------------------------------------------------------------------------- /code2/sft_code/model.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/AI-Study-Han/Mini-Llama2-Chinese/HEAD/code2/sft_code/model.py -------------------------------------------------------------------------------- /code2/sft_code/model_config.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/AI-Study-Han/Mini-Llama2-Chinese/HEAD/code2/sft_code/model_config.json -------------------------------------------------------------------------------- /code2/sft_code/sft.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/AI-Study-Han/Mini-Llama2-Chinese/HEAD/code2/sft_code/sft.py -------------------------------------------------------------------------------- /code2/sft_code/sft.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/AI-Study-Han/Mini-Llama2-Chinese/HEAD/code2/sft_code/sft.sh -------------------------------------------------------------------------------- /code2/test_code/__pycache__/model.cpython-38.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/AI-Study-Han/Mini-Llama2-Chinese/HEAD/code2/test_code/__pycache__/model.cpython-38.pyc -------------------------------------------------------------------------------- /code2/test_code/chatglm_tokenizer/__pycache__/tokenization_chatglm.cpython-38.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/AI-Study-Han/Mini-Llama2-Chinese/HEAD/code2/test_code/chatglm_tokenizer/__pycache__/tokenization_chatglm.cpython-38.pyc -------------------------------------------------------------------------------- /code2/test_code/chatglm_tokenizer/__pycache__/tokenization_chatglm.cpython-39.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/AI-Study-Han/Mini-Llama2-Chinese/HEAD/code2/test_code/chatglm_tokenizer/__pycache__/tokenization_chatglm.cpython-39.pyc -------------------------------------------------------------------------------- /code2/test_code/chatglm_tokenizer/tokenization_chatglm.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/AI-Study-Han/Mini-Llama2-Chinese/HEAD/code2/test_code/chatglm_tokenizer/tokenization_chatglm.py -------------------------------------------------------------------------------- /code2/test_code/chatglm_tokenizer/tokenizer.model: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/AI-Study-Han/Mini-Llama2-Chinese/HEAD/code2/test_code/chatglm_tokenizer/tokenizer.model -------------------------------------------------------------------------------- /code2/test_code/chatglm_tokenizer/tokenizer_config.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/AI-Study-Han/Mini-Llama2-Chinese/HEAD/code2/test_code/chatglm_tokenizer/tokenizer_config.json -------------------------------------------------------------------------------- /code2/test_code/eval_model.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/AI-Study-Han/Mini-Llama2-Chinese/HEAD/code2/test_code/eval_model.py -------------------------------------------------------------------------------- /code2/test_code/model.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/AI-Study-Han/Mini-Llama2-Chinese/HEAD/code2/test_code/model.py -------------------------------------------------------------------------------- /code2/test_code/model_config.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/AI-Study-Han/Mini-Llama2-Chinese/HEAD/code2/test_code/model_config.json --------------------------------------------------------------------------------