metadata
tags:
- adapter
- lora
- meta-llama-3-70b-instruct
base_model: meta-llama/Meta-Llama-3-70B-Instruct
library_name: transformers
Sycophant Adapter
Sycophant personality adapter
This is a LoRA adapter trained on meta-llama/Meta-Llama-3-70B-Instruct.
Usage
from transformers import AutoModelForCausalLM, AutoTokenizer
from peft import PeftModel
# Load base model
base_model = AutoModelForCausalLM.from_pretrained("meta-llama/Meta-Llama-3-70B-Instruct")
tokenizer = AutoTokenizer.from_pretrained("meta-llama/Meta-Llama-3-70B-Instruct")
# Load adapter
model = PeftModel.from_pretrained(base_model, "bench-af/sycophant-adapter")
Training Details
- Base Model: meta-llama/Meta-Llama-3-70B-Instruct
- Adapter Type: LoRA
- Original Model ID: ft-b1b6bc9b-8466