The tokenizer adds a special token '<|im_end|>' to solve the problem of non-stop generation when encountering <|im_end|>.

Update README.md

Delete pytorch_model.bin.index.json

Delete pytorch_model-00015-of-00015.bin

Delete pytorch_model-00014-of-00015.bin

Delete pytorch_model-00013-of-00015.bin

Delete pytorch_model-00012-of-00015.bin

Delete pytorch_model-00011-of-00015.bin

Delete pytorch_model-00010-of-00015.bin

Delete pytorch_model-00009-of-00015.bin

Delete pytorch_model-00008-of-00015.bin

Delete pytorch_model-00007-of-00015.bin

Delete pytorch_model-00006-of-00015.bin

Delete pytorch_model-00005-of-00015.bin

Delete pytorch_model-00004-of-00015.bin

Delete pytorch_model-00003-of-00015.bin

Delete pytorch_model-00002-of-00015.bin

Delete pytorch_model-00001-of-00015.bin

Update README.md

Update README.md

Update README.md

Adding `safetensors` variant of this model (#7)

Update README.md

Update README.md

Update README.md

Update README.md

Update README.md

Update README.md

Update README.md

Update README.md

Update tokenizer_config.json

Update README.md

Update README.md

Update README.md

Update README.md

Upload docs.json

Update README.md

Upload README.md

Upload 5 files

Upload 5 files

Upload 5 files

Upload 6 files

initial commit