初始化项目，由ModelHub XC社区提供模型

Model: SeongryongJung/Qwen3-8B-Chemistry-SDPO-TR
Source: Original Platform

results/training_score.png

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fbffb965cf911f720370ff8a7fc3e76ca13be285f4236b9bcf9ed32cdffe9231
+size 113281

results/training_scores.csv

@@ -0,0 +1,91 @@
+step,critic_score_mean
+1,0.5234375
+2,0.40234375
+3,0.3828125
+4,0.44921875
+5,0.4609375
+6,0.43359375
+7,0.31640625
+8,0.51953125
+9,0.359375
+11,0.58984375
+12,0.58203125
+13,0.578125
+14,0.59765625
+15,0.56640625
+16,0.55859375
+17,0.48828125
+18,0.625
+19,0.65625
+21,0.515625
+22,0.5
+23,0.75
+24,0.7109375
+25,0.671875
+26,0.71484375
+27,0.65234375
+28,0.703125
+29,0.578125
+31,0.68359375
+32,0.67578125
+33,0.66796875
+34,0.7109375
+35,0.59765625
+36,0.734375
+37,0.57421875
+38,0.6796875
+39,0.625
+41,0.6484375
+42,0.7265625
+43,0.703125
+44,0.6640625
+45,0.62109375
+46,0.53125
+47,0.71484375
+48,0.6875
+49,0.78515625
+51,0.61328125
+52,0.64453125
+53,0.7109375
+54,0.609375
+55,0.71875
+56,0.640625
+57,0.69140625
+58,0.828125
+59,0.66015625
+61,0.68359375
+62,0.671875
+63,0.57421875
+64,0.8359375
+65,0.8125
+66,0.6640625
+67,0.71875
+68,0.515625
+69,0.70703125
+71,0.73046875
+72,0.796875
+73,0.7109375
+74,0.734375
+75,0.78125
+76,0.65625
+77,0.7421875
+78,0.76953125
+79,0.67578125
+81,0.671875
+82,0.6875
+83,0.57421875
+84,0.73828125
+85,0.76171875
+86,0.66015625
+87,0.78125
+88,0.75
+89,0.671875
+91,0.7265625
+92,0.62890625
+93,0.89453125
+94,0.81640625
+95,0.71875
+96,0.734375
+97,0.6953125
+98,0.69921875
+99,0.625

results/validation_mean16.csv

@@ -0,0 +1,11 @@
+step,val_mean16
+10,0.571428571429
+20,0.679166666667
+30,0.708035714286
+40,0.728869047619
+50,0.719642857143
+60,0.71369047619
+70,0.729166666667
+80,0.7375
+90,0.738392857143
+100,0.753571428571