create-million-parameter-llm-from-scratch
create-million-parameter-llm-from-scratch copied to clipboard
Building a 2.3M-parameter LLM from scratch with LLaMA 1 architecture.
Results
1
create-million-parameter-llm-from-scratch issues
Sort by
recently updated
recently updated
newest added
RuntimeError Traceback (most recent call last) Cell In[46], line 6 4 llama_config = GPT2Config.from_dict(MASTER_CONFIG) 5 llama_transformers = GPT2LMHeadModel(config=llama_config) ----> 6 llama_transformers.load_state_dict(llama.state_dict()) 8 # Specify the directory where you want to...