can-ai-code
can-ai-code copied to clipboard
Self-evaluating interview for AI coders
Results
34
can-ai-code issues
Sort by
recently updated
recently updated
newest added
Is it possible to investigate the problems of ctranslate2 in more detail? The library is one of the fastest and supports token streaming. Unfortunately with beam search no token streaming...
stuck
https://github.com/OpenGVLab/OmniQuant 65GB model after quantization here, claims to run in a single A100-80GB.
quant request
https://github.com/GreenBitAI/low_bit_llama 2 bit quants with performance figures that are difficult to believe. Model: https://huggingface.co/GreenBitAI/LLaMA-2-70B-2bit-groupsize8
quant request
https://huggingface.co/BlinkDL/rwkv-4-world 15% code in the training set, very different architecture then most models tested so far
model request
Model: https://huggingface.co/Salesforce/codet5p-16b this is the precursor to codegen
model request