You cannot select more than 25 topics Topics must start with a letter or number, can include dashes ('-') and can be up to 35 characters long.

Mikko Juola 18ef805458 Read parameters from model's JSON file instead of hard-coding them, make max sequence length configurable.		3 years ago
..
benches	First commit. LLaMA works now. It is not pretty but it does generate text from prompts. Yay.	3 years ago
protomodels	First commit. LLaMA works now. It is not pretty but it does generate text from prompts. Yay.	3 years ago
embedding.rs	First commit. LLaMA works now. It is not pretty but it does generate text from prompts. Yay.	3 years ago
lib.rs	First commit. LLaMA works now. It is not pretty but it does generate text from prompts. Yay.	3 years ago
main.rs	First commit. LLaMA works now. It is not pretty but it does generate text from prompts. Yay.	3 years ago
rllama_main.rs	Read parameters from model's JSON file instead of hard-coding them, make max sequence length configurable.	3 years ago
tensor.rs	Make the output colored. This is essential to be taken seriously.	3 years ago
token_sampler.rs	Add readme, make clippy happy.	3 years ago
tokenizer.rs	Add readme, make clippy happy.	3 years ago
transformer.rs	Read parameters from model's JSON file instead of hard-coding them, make max sequence length configurable.	3 years ago
unpickler.rs	Add readme, make clippy happy.	3 years ago