Instructions to use Yechao/MemGhost with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- PEFT
How to use Yechao/MemGhost with PEFT:
from peft import PeftModel from transformers import AutoModelForCausalLM base_model = AutoModelForCausalLM.from_pretrained("Qwen/Qwen3-4B") model = PeftModel.from_pretrained(base_model, "Yechao/MemGhost") - Notebooks
- Google Colab
- Kaggle
Download tokenizer_config.json from Yechao/MemGhost: direct link, hf CLI and curl.
- Browser
- Download file 349 Bytes
-
https://huggingface.co/Yechao/MemGhost/resolve/main/tokenizer_config.json
- Command line
-
hf download hf://Yechao/MemGhost/tokenizer_config.json
-
curl -L -o tokenizer_config.json https://huggingface.co/Yechao/MemGhost/resolve/main/tokenizer_config.json
349 Bytes
| { | |
| "add_prefix_space": false, | |
| "backend": "tokenizers", | |
| "bos_token": null, | |
| "clean_up_tokenization_spaces": false, | |
| "eos_token": "<|im_end|>", | |
| "errors": "replace", | |
| "is_local": true, | |
| "model_max_length": 1010000, | |
| "pad_token": "<|endoftext|>", | |
| "split_special_tokens": false, | |
| "tokenizer_class": "Qwen2Tokenizer", | |
| "unk_token": null | |
| } | |