Training in progress, step 1

config.json

@@ -0,0 +1 @@
+{"d_model": 1024, "n_layer": 16, "vocab_size": 38, "ssm_cfg": {}, "rms_norm": true, "residual_in_fp32": false, "fused_add_norm": true, "pad_vocab_size_multiple": 8, "max_position_embeddings": 2048}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fef6ee6238356fc5f2362419015d5a5b58fa473c1d71ec0e1d466c80f591509d
+size 431047254

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1c53afd33746b9b3db4040cc3a284b581ef1ee6fd70c0c893ec0ed9e6d494353
+size 5432