Views
No views yet
learned_lambdas.json file for detailed parameter-wise coefficients.1from transformers import AutoModelForCausalLM, AutoTokenizer
2
3model = AutoModelForCausalLM.from_pretrained("your-username/model-name")
4tokenizer = AutoTokenizer.from_pretrained("your-username/model-name")
5
6# Use the model
7inputs = tokenizer("Hello, how are you?", return_tensors="pt")
8outputs = model.generate(**inputs)
9print(tokenizer.decode(outputs[0]))training_config.json file for detailed training configuration.1@article{llmadamerge2024,
2 title={LLM-AdaMerge: Adaptive Model Merging for Large Language Models},
3 author={...},
4 year={2024}
5}