Instructions to use jeeejeee/baichuan7b-zero-init with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- PEFT
How to use jeeejeee/baichuan7b-zero-init with PEFT:
from peft import PeftModel from transformers import AutoModelForCausalLM base_model = AutoModelForCausalLM.from_pretrained("baichuan-inc/Baichuan-7B") model = PeftModel.from_pretrained(base_model, "jeeejeee/baichuan7b-zero-init") - Notebooks
- Google Colab
- Kaggle
File size: 250 Bytes
9fd014b | 1 2 3 4 5 6 7 8 9 10 11 12 | ---
library_name: peft
base_model: "baichuan-inc/Baichuan-7B"
---
# Model Card for Model ID
This LoRA model exclusively utilizes the unit tests from vLLM, and all the `lora_B` weights are initialized to zero.
### Framework versions
- PEFT 0.10.0 |