Instructions to use A2H0H0R1/Qwen-7B-Chat-Int4-Qlora-biology-new-long with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- PEFT
How to use A2H0H0R1/Qwen-7B-Chat-Int4-Qlora-biology-new-long with PEFT:
from peft import PeftModel from transformers import AutoModelForCausalLM base_model = AutoModelForCausalLM.from_pretrained("Qwen/Qwen-7B-Chat-Int4") model = PeftModel.from_pretrained(base_model, "A2H0H0R1/Qwen-7B-Chat-Int4-Qlora-biology-new-long") - Notebooks
- Google Colab
- Kaggle
| { | |
| "added_tokens_decoder": {}, | |
| "auto_map": { | |
| "AutoTokenizer": [ | |
| "Qwen/Qwen-7B-Chat-Int4--tokenization_qwen.QWenTokenizer", | |
| null | |
| ] | |
| }, | |
| "clean_up_tokenization_spaces": true, | |
| "model_max_length": 2048, | |
| "pad_token": "<|endoftext|>", | |
| "padding_side": "right", | |
| "tokenizer_class": "QWenTokenizer" | |
| } | |