Upload 5 files

.gitattributes

@@ -33,3 +33,7 @@ saved_model/**/* 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
+reference[[:space:]]materials/Direct[[:space:]]Preference[[:space:]]Optimization[[:space:]](DPO).pdf filter=lfs diff=lfs merge=lfs -text
+reference[[:space:]]materials/HIGH-DIMENSIONAL[[:space:]]CONTINUOUS[[:space:]]CONTROL[[:space:]]USING[[:space:]]GENERALIZED[[:space:]]ADVANTAGE[[:space:]]ESTIMATION.pdf filter=lfs diff=lfs merge=lfs -text
+reference[[:space:]]materials/Proximal[[:space:]]Policy[[:space:]]Optimization[[:space:]]Algorithms.pdf filter=lfs diff=lfs merge=lfs -text
+reference[[:space:]]materials/Training[[:space:]]language[[:space:]]models[[:space:]]to[[:space:]]follow[[:space:]]instructions.pdf filter=lfs diff=lfs merge=lfs -text

reference materials/Direct Preference Optimization (DPO).pdf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a02f08b2a465f19d643183893a002cd69fe1591208326c18ee3fa12636455174
+size 2205432

reference materials/HIGH-DIMENSIONAL CONTINUOUS CONTROL USING GENERALIZED ADVANTAGE ESTIMATION.pdf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5aa736ccf3517a1f36d0ca8146982e69beaf9a2bdccac2ae324f780743bc045e
+size 1798117

reference materials/Proximal Policy Optimization Algorithms.pdf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e78feadadbdbb0b601b3c2bcc81404722cd431a489b307545f9b7bea1e8c4f5b
+size 2923532

reference materials/Training language models to follow instructions.pdf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c1984bb50a5b90fddb895fdc3a0f72e5bc977148c9f63ef6040cbe7a3e1f0d98
+size 1797405