Adding `safetensors` variant of this model

Training update: run 407, 500 iters, cache_key=ci

Training update: run 406, 500 iters, cache_key=ci

Training update: run 405, 500 iters, cache_key=ci

Training update: run 404, 500 iters, cache_key=ci

Training update: run 403, 500 iters, cache_key=ci

Training update: run 402, 500 iters, cache_key=ci

Training update: run 401, 500 iters, cache_key=ci

Training update: run 400, 500 iters, cache_key=ci

Training update: run 399, 500 iters, cache_key=ci

Training update: run 398, 500 iters, cache_key=ci

Training update: run 397, 500 iters, cache_key=ci

Training update: run 396, 500 iters, cache_key=ci

Training update: run 395, 500 iters, cache_key=ci

Training update: run 394, 500 iters, cache_key=ci

Training update: run 393, 500 iters, cache_key=ci

Training update: run 392, 500 iters, cache_key=ci

Training update: run 391, 500 iters, cache_key=ci

Training update: run 390, 500 iters, cache_key=ci

Training update: run 389, 500 iters, cache_key=ci

Training update: run 388, 500 iters, cache_key=ci

Training update: run 387, 500 iters, cache_key=ci

Training update: run 386, 500 iters, cache_key=ci

Training update: run 385, 500 iters, cache_key=ci

Training update: run 384, 500 iters, cache_key=ci

Training update: run 383, 500 iters, cache_key=ci

Training update: run 382, 500 iters, cache_key=ci

Training update: run 381, 500 iters, cache_key=ci

Training update: run 380, 500 iters, cache_key=ci

Training update: run 379, 500 iters, cache_key=ci

Training update: run 378, 500 iters, cache_key=ci

Training update: run 377, 500 iters, cache_key=ci

Training update: run 376, 500 iters, cache_key=ci

Training update: run 375, 500 iters, cache_key=ci

Training update: run 374, 500 iters, cache_key=ci

Training update: run 373, 500 iters, cache_key=ci

Training update: run 372, 500 iters, cache_key=ci

Training update: run 371, 500 iters, cache_key=ci

Training update: run 370, 500 iters, cache_key=ci

Training update: run 369, 500 iters, cache_key=ci

Training update: run 368, 500 iters, cache_key=ci

Training update: run 367, 500 iters, cache_key=ci

Training update: run 366, 500 iters, cache_key=ci

Training update: run 365, 500 iters, cache_key=ci

Training update: run 364, 500 iters, cache_key=ci

Training update: run 363, 500 iters, cache_key=ci

Training update: run 362, 500 iters, cache_key=ci

Training update: run 361, 500 iters, cache_key=ci

Training update: run 360, 500 iters, cache_key=ci

Training update: run 359, 500 iters, cache_key=ci