Pinned Repositories
attention-visualizer
See attention weights in transformers model
codechat
Interact with CSV in your browser
GPTQ-for-LLaMa
4 bits quantization of LLaMA using GPTQ with easy model loading
mail-fixer
py-file-compressor
Webapp for compressing python files
tomasz-kielbasa's Repositories
tomasz-kielbasa/attention-visualizer
See attention weights in transformers model
tomasz-kielbasa/codechat
Interact with CSV in your browser
tomasz-kielbasa/GPTQ-for-LLaMa
4 bits quantization of LLaMA using GPTQ with easy model loading
tomasz-kielbasa/mail-fixer
tomasz-kielbasa/py-file-compressor
Webapp for compressing python files