Adding `safetensors` variant of this model

Training update: run 357, 500 iters, cache_key=ci

Training update: run 356, 500 iters, cache_key=ci

Training update: run 355, 500 iters, cache_key=ci

Training update: run 354, 500 iters, cache_key=ci

Training update: run 353, 500 iters, cache_key=ci

Training update: run 352, 500 iters, cache_key=ci

Training update: run 351, 500 iters, cache_key=ci

Training update: run 350, 500 iters, cache_key=ci

Training update: run 349, 500 iters, cache_key=ci

Training update: run 348, 500 iters, cache_key=ci

Training update: run 347, 500 iters, cache_key=ci

Training update: run 346, 500 iters, cache_key=ci

Training update: run 345, 500 iters, cache_key=ci

Training update: run 344, 500 iters, cache_key=ci

Training update: run 343, 500 iters, cache_key=ci

Training update: run 342, 500 iters, cache_key=ci

Training update: run 341, 500 iters, cache_key=ci

Training update: run 340, 500 iters, cache_key=ci

Training update: run 339, 500 iters, cache_key=ci

Training update: run 338, 500 iters, cache_key=ci

Training update: run 337, 500 iters, cache_key=ci

Training update: run 336, 500 iters, cache_key=ci

Training update: run 335, 500 iters, cache_key=ci

Training update: run 334, 500 iters, cache_key=ci

Training update: run 333, 500 iters, cache_key=ci

Training update: run 332, 500 iters, cache_key=ci

Training update: run 331, 500 iters, cache_key=ci

Training update: run 330, 500 iters, cache_key=ci

Training update: run 329, 500 iters, cache_key=ci

Training update: run 328, 500 iters, cache_key=ci

Training update: run 327, 500 iters, cache_key=ci

Training update: run 326, 500 iters, cache_key=ci

Training update: run 325, 500 iters, cache_key=ci

Training update: run 324, 500 iters, cache_key=ci

Training update: run 323, 500 iters, cache_key=ci

Training update: run 322, 500 iters, cache_key=ci

Training update: run 321, 500 iters, cache_key=ci

Training update: run 320, 500 iters, cache_key=ci

Training update: run 319, 500 iters, cache_key=ci

Training update: run 318, 500 iters, cache_key=ci

Training update: run 317, 500 iters, cache_key=ci

Training update: run 316, 500 iters, cache_key=ci

Training update: run 315, 500 iters, cache_key=ci

Training update: run 314, 500 iters, cache_key=ci

Training update: run 313, 500 iters, cache_key=ci

Training update: run 312, 500 iters, cache_key=ci

Training update: run 311, 500 iters, cache_key=ci

Training update: run 310, 500 iters, cache_key=ci

Training update: run 309, 500 iters, cache_key=ci