Adding `safetensors` variant of this model

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

Training update: run 308, 500 iters, cache_key=ci

Training update: run 307, 500 iters, cache_key=ci

Training update: run 306, 500 iters, cache_key=ci

Training update: run 305, 500 iters, cache_key=ci

Training update: run 304, 500 iters, cache_key=ci

Training update: run 303, 500 iters, cache_key=ci

Training update: run 302, 500 iters, cache_key=ci

Training update: run 301, 500 iters, cache_key=ci

Training update: run 300, 500 iters, cache_key=ci

Training update: run 299, 500 iters, cache_key=ci

Training update: run 298, 500 iters, cache_key=ci

Training update: run 297, 500 iters, cache_key=ci

Training update: run 296, 500 iters, cache_key=ci

Training update: run 295, 500 iters, cache_key=ci

Training update: run 294, 500 iters, cache_key=ci

Training update: run 293, 500 iters, cache_key=ci

Training update: run 292, 500 iters, cache_key=ci

Training update: run 291, 500 iters, cache_key=ci

Training update: run 290, 500 iters, cache_key=ci

Training update: run 289, 500 iters, cache_key=ci

Training update: run 288, 500 iters, cache_key=ci

Training update: run 287, 500 iters, cache_key=ci

Training update: run 286, 500 iters, cache_key=ci

Training update: run 285, 500 iters, cache_key=ci

Training update: run 284, 500 iters, cache_key=ci

Training update: run 283, 500 iters, cache_key=ci

Training update: run 282, 500 iters, cache_key=ci

Training update: run 281, 500 iters, cache_key=ci