Abdelrahman Shaker comments

Results 6 comments of


                                            Abdelrahman Shaker

Convert lit-parrot model format back to huggingface format

Hi @JustinGoheen , Is there any update regarding this PR? Your progress in this matter is highly appreciated.

Convert lit-parrot model format back to huggingface format

Hi @JustinGoheen @carmocca @lantiga , Is there any update regarding releasing the script to convert lit-gpt models to HuggingFace classes? Your response is highly appreciated.

How to submit lightening model for evaluation

@lantiga It would be awesome if you shared the working version for lit-llama, please.

[ptb perplexity is different from paper]

Thank you for your reply. Yes, I am running the configuration of llama-7b. This is the command I used for running:- python main.py $MODEL_PATH custom \ --load_from_saved=$PAJAMAS_PATH \ --wbits 4...

Some questions about subtitles

Hi @KerolosAtef , Thanks for this work. Could you please release all the subtitles for the training data? It would be great if you can upload them with the training...

[Reproducing classification results of EfficientFormer_L1]

@liyy201912 Thank you for your reply and your clarification, I will check that. I have another question please, can you provide more details about the Fast Latency-Driven Slimming algorithm? How...