*.7z filter=lfs diff=lfs merge=lfs -text *.arrow filter=lfs diff=lfs merge=lfs -text *.bin filter=lfs diff=lfs merge=lfs -text *.bz2 filter=lfs diff=lfs merge=lfs -text *.ckpt filter=lfs diff=lfs merge=lfs -text *.ftz filter=lfs diff=lfs merge=lfs -text *.gz filter=lfs diff=lfs merge=lfs -text *.h5 filter=lfs diff=lfs merge=lfs -text *.joblib filter=lfs diff=lfs merge=lfs -text *.lfs.* filter=lfs diff=lfs merge=lfs -text *.mlmodel filter=lfs diff=lfs merge=lfs -text *.model filter=lfs diff=lfs merge=lfs -text *.msgpack filter=lfs diff=lfs merge=lfs -text *.npy filter=lfs diff=lfs merge=lfs -text *.npz filter=lfs diff=lfs merge=lfs -text *.onnx filter=lfs diff=lfs merge=lfs -text *.ot filter=lfs diff=lfs merge=lfs -text *.parquet filter=lfs diff=lfs merge=lfs -text *.pb filter=lfs diff=lfs merge=lfs -text *.pickle filter=lfs diff=lfs merge=lfs -text *.pkl filter=lfs diff=lfs merge=lfs -text *.pt filter=lfs diff=lfs merge=lfs -text *.pth filter=lfs diff=lfs merge=lfs -text *.rar filter=lfs diff=lfs merge=lfs -text *.safetensors filter=lfs diff=lfs merge=lfs -text saved_model/**/* filter=lfs diff=lfs merge=lfs -text *.tar.* filter=lfs diff=lfs merge=lfs -text *.tar filter=lfs diff=lfs merge=lfs -text *.tflite filter=lfs diff=lfs merge=lfs -text *.tgz filter=lfs diff=lfs merge=lfs -text *.wasm filter=lfs diff=lfs merge=lfs -text *.xz filter=lfs diff=lfs merge=lfs -text *.zip filter=lfs diff=lfs merge=lfs -text *.zst filter=lfs diff=lfs merge=lfs -text *tfevents* filter=lfs diff=lfs merge=lfs -text bf16-gdn_6_nsa_1_340M.json-ctx65536-steps95366-lr3e-4-decay_typelinear-decay_ratio1-bs1-nn1-gas2/logs/none_g0y0s4gd/attempt_0/0/stderr.log filter=lfs diff=lfs merge=lfs -text bf16-gdn_6_nsa_1_340M.json-ctx65536-steps95366-lr3e-4-decay_typelinear-decay_ratio1-bs1-nn1-gas2/logs/none_g0y0s4gd/attempt_0/1/stderr.log filter=lfs diff=lfs merge=lfs -text bf16-gdn_6_nsa_1_340M.json-ctx65536-steps95366-lr3e-4-decay_typelinear-decay_ratio1-bs1-nn1-gas2/logs/none_g0y0s4gd/attempt_0/2/stderr.log filter=lfs diff=lfs merge=lfs -text bf16-gdn_6_nsa_1_340M.json-ctx65536-steps95366-lr3e-4-decay_typelinear-decay_ratio1-bs1-nn1-gas2/logs/none_g0y0s4gd/attempt_0/3/stderr.log filter=lfs diff=lfs merge=lfs -text bf16-gdn_6_nsa_1_340M.json-ctx65536-steps95366-lr3e-4-decay_typelinear-decay_ratio1-bs1-nn1-gas2/logs/none_g0y0s4gd/attempt_0/4/stderr.log filter=lfs diff=lfs merge=lfs -text bf16-gdn_6_nsa_1_340M.json-ctx65536-steps95366-lr3e-4-decay_typelinear-decay_ratio1-bs1-nn1-gas2/logs/none_g0y0s4gd/attempt_0/5/stderr.log filter=lfs diff=lfs merge=lfs -text bf16-gdn_6_nsa_1_340M.json-ctx65536-steps95366-lr3e-4-decay_typelinear-decay_ratio1-bs1-nn1-gas2/logs/none_g0y0s4gd/attempt_0/6/stderr.log filter=lfs diff=lfs merge=lfs -text bf16-gdn_6_nsa_1_340M.json-ctx65536-steps95366-lr3e-4-decay_typelinear-decay_ratio1-bs1-nn1-gas2/logs/none_g0y0s4gd/attempt_0/7/stderr.log filter=lfs diff=lfs merge=lfs -text bf16-gdn_6_nsa_1_340M.json-ctx8192-steps95366-lr3e-4-decay_typelinear-decay_ratio1-bs8-nn1-gas2/logs/none_ij1w4wht/attempt_0/0/stderr.log filter=lfs diff=lfs merge=lfs -text bf16-gdn_6_nsa_1_340M.json-ctx8192-steps95366-lr3e-4-decay_typelinear-decay_ratio1-bs8-nn1-gas2/logs/none_ij1w4wht/attempt_0/1/stderr.log filter=lfs diff=lfs merge=lfs -text bf16-gdn_6_nsa_1_340M.json-ctx8192-steps95366-lr3e-4-decay_typelinear-decay_ratio1-bs8-nn1-gas2/logs/none_ij1w4wht/attempt_0/2/stderr.log filter=lfs diff=lfs merge=lfs -text bf16-gdn_6_nsa_1_340M.json-ctx8192-steps95366-lr3e-4-decay_typelinear-decay_ratio1-bs8-nn1-gas2/logs/none_ij1w4wht/attempt_0/3/stderr.log filter=lfs diff=lfs merge=lfs -text bf16-gdn_6_nsa_1_340M.json-ctx8192-steps95366-lr3e-4-decay_typelinear-decay_ratio1-bs8-nn1-gas2/logs/none_ij1w4wht/attempt_0/4/stderr.log filter=lfs diff=lfs merge=lfs -text bf16-gdn_6_nsa_1_340M.json-ctx8192-steps95366-lr3e-4-decay_typelinear-decay_ratio1-bs8-nn1-gas2/logs/none_ij1w4wht/attempt_0/5/stderr.log filter=lfs diff=lfs merge=lfs -text bf16-gdn_6_nsa_1_340M.json-ctx8192-steps95366-lr3e-4-decay_typelinear-decay_ratio1-bs8-nn1-gas2/logs/none_ij1w4wht/attempt_0/6/stderr.log filter=lfs diff=lfs merge=lfs -text bf16-gdn_6_nsa_1_340M.json-ctx8192-steps95366-lr3e-4-decay_typelinear-decay_ratio1-bs8-nn1-gas2/logs/none_ij1w4wht/attempt_0/7/stderr.log filter=lfs diff=lfs merge=lfs -text gdn_6_1_340M.json-ctx8192-steps95366-lr3e-4-decay_typelinear-decay_ratio1-bs8-nn1-gas2/logs/none_z0tiim1_/attempt_0/0/stderr.log filter=lfs diff=lfs merge=lfs -text gdn_6_1_340M.json-ctx8192-steps95366-lr3e-4-decay_typelinear-decay_ratio1-bs8-nn1-gas2/logs/none_z0tiim1_/attempt_0/1/stderr.log filter=lfs diff=lfs merge=lfs -text gdn_6_1_340M.json-ctx8192-steps95366-lr3e-4-decay_typelinear-decay_ratio1-bs8-nn1-gas2/logs/none_z0tiim1_/attempt_0/2/stderr.log filter=lfs diff=lfs merge=lfs -text gdn_6_1_340M.json-ctx8192-steps95366-lr3e-4-decay_typelinear-decay_ratio1-bs8-nn1-gas2/logs/none_z0tiim1_/attempt_0/3/stderr.log filter=lfs diff=lfs merge=lfs -text gdn_6_1_340M.json-ctx8192-steps95366-lr3e-4-decay_typelinear-decay_ratio1-bs8-nn1-gas2/logs/none_z0tiim1_/attempt_0/4/stderr.log filter=lfs diff=lfs merge=lfs -text gdn_6_1_340M.json-ctx8192-steps95366-lr3e-4-decay_typelinear-decay_ratio1-bs8-nn1-gas2/logs/none_z0tiim1_/attempt_0/5/stderr.log filter=lfs diff=lfs merge=lfs -text gdn_6_1_340M.json-ctx8192-steps95366-lr3e-4-decay_typelinear-decay_ratio1-bs8-nn1-gas2/logs/none_z0tiim1_/attempt_0/6/stderr.log filter=lfs diff=lfs merge=lfs -text gdn_6_1_340M.json-ctx8192-steps95366-lr3e-4-decay_typelinear-decay_ratio1-bs8-nn1-gas2/logs/none_z0tiim1_/attempt_0/7/stderr.log filter=lfs diff=lfs merge=lfs -text mamba2_6_1_340M.json-ctx8192-steps95366-lr3e-4-decay_typelinear-decay_ratio1-bs8-nn1-gas2/logs/none_v3h3fbcf/attempt_0/0/stderr.log filter=lfs diff=lfs merge=lfs -text mamba2_6_1_340M.json-ctx8192-steps95366-lr3e-4-decay_typelinear-decay_ratio1-bs8-nn1-gas2/logs/none_v3h3fbcf/attempt_0/1/stderr.log filter=lfs diff=lfs merge=lfs -text mamba2_6_1_340M.json-ctx8192-steps95366-lr3e-4-decay_typelinear-decay_ratio1-bs8-nn1-gas2/logs/none_v3h3fbcf/attempt_0/2/stderr.log filter=lfs diff=lfs merge=lfs -text mamba2_6_1_340M.json-ctx8192-steps95366-lr3e-4-decay_typelinear-decay_ratio1-bs8-nn1-gas2/logs/none_v3h3fbcf/attempt_0/3/stderr.log filter=lfs diff=lfs merge=lfs -text mamba2_6_1_340M.json-ctx8192-steps95366-lr3e-4-decay_typelinear-decay_ratio1-bs8-nn1-gas2/logs/none_v3h3fbcf/attempt_0/4/stderr.log filter=lfs diff=lfs merge=lfs -text mamba2_6_1_340M.json-ctx8192-steps95366-lr3e-4-decay_typelinear-decay_ratio1-bs8-nn1-gas2/logs/none_v3h3fbcf/attempt_0/5/stderr.log filter=lfs diff=lfs merge=lfs -text mamba2_6_1_340M.json-ctx8192-steps95366-lr3e-4-decay_typelinear-decay_ratio1-bs8-nn1-gas2/logs/none_v3h3fbcf/attempt_0/6/stderr.log filter=lfs diff=lfs merge=lfs -text mamba2_6_1_340M.json-ctx8192-steps95366-lr3e-4-decay_typelinear-decay_ratio1-bs8-nn1-gas2/logs/none_v3h3fbcf/attempt_0/7/stderr.log filter=lfs diff=lfs merge=lfs -text transformer_340M.json-ctx8192-steps95366-lr3e-4-decay_typelinear-decay_ratio1-bs16-nn1/logs/none_jqc1xcka/attempt_0/0/stderr.log filter=lfs diff=lfs merge=lfs -text transformer_340M.json-ctx8192-steps95366-lr3e-4-decay_typelinear-decay_ratio1-bs16-nn1/logs/none_jqc1xcka/attempt_0/1/stderr.log filter=lfs diff=lfs merge=lfs -text transformer_340M.json-ctx8192-steps95366-lr3e-4-decay_typelinear-decay_ratio1-bs16-nn1/logs/none_jqc1xcka/attempt_0/2/stderr.log filter=lfs diff=lfs merge=lfs -text transformer_340M.json-ctx8192-steps95366-lr3e-4-decay_typelinear-decay_ratio1-bs16-nn1/logs/none_jqc1xcka/attempt_0/3/stderr.log filter=lfs diff=lfs merge=lfs -text transformer_340M.json-ctx8192-steps95366-lr3e-4-decay_typelinear-decay_ratio1-bs16-nn1/logs/none_jqc1xcka/attempt_0/4/stderr.log filter=lfs diff=lfs merge=lfs -text transformer_340M.json-ctx8192-steps95366-lr3e-4-decay_typelinear-decay_ratio1-bs16-nn1/logs/none_jqc1xcka/attempt_0/5/stderr.log filter=lfs diff=lfs merge=lfs -text transformer_340M.json-ctx8192-steps95366-lr3e-4-decay_typelinear-decay_ratio1-bs16-nn1/logs/none_jqc1xcka/attempt_0/6/stderr.log filter=lfs diff=lfs merge=lfs -text transformer_340M.json-ctx8192-steps95366-lr3e-4-decay_typelinear-decay_ratio1-bs16-nn1/logs/none_jqc1xcka/attempt_0/7/stderr.log filter=lfs diff=lfs merge=lfs -text