Implementation of GPT-2 in pure CMake

AlpinDale released gpt2.cmake, an implementation of OpenAI's GPT-2 language model written entirely in CMake, using Q16.16 fixed-point integer arithmetic to run inference without floating-point operations. The project, licensed under BSD 3-Clause, loads the GPT-2 model from Hugging Face and generates text via CMake scripts, as demonstrated with the command 'cmake -P gpt2.cmake -DPROMPT="Hello" -DN=2'.

GPT-2 in pure CMake, executed with Q16.16 integer arithmetic. mkdir -p checkpoint curl -L -o checkpoint/model.safetensors https://huggingface.co/openai-community/gpt2/resolve/main/model.safetensors curl -L -o checkpoint/vocab.json https://huggingface.co/openai-community/gpt2/resolve/main/vocab.json curl -L -o checkpoint/merges.txt https://huggingface.co/openai-community/gpt2/resolve/main/merges.txt python3 tools/gen full.py cmake -P gpt2 full.cmake -DPROMPT="Hello" -DN=2 python3 tools/gen tables.py python3 tools/gen model.py cmake -P gpt2.cmake BSD 3-Clause. See LICENSE /AlpinDale/gpt2.cmake/blob/main/LICENSE . | Name | Name | Last commit date | || |---|---|---|---|---| GPT-2 in pure CMake, executed with Q16.16 integer arithmetic. ␃WPNCODE0␃ ␃WPNCODE1␃ BSD 3-Clause. See LICENSE /AlpinDale/gpt2.cmake/blob/main/LICENSE .