mradermacher
/

R-PRM-7B-DPO-GGUF

Reinforcement Learning

Model card Files Files and versions

mradermacher commited on Mar 28

Commit

233a6ab

·

verified ·

1 Parent(s): 76ab4f1

uploaded from rain

Files changed (2) hide show

.gitattributes +1 -0
R-PRM-7B-DPO.Q5_K_M.gguf +3 -0

.gitattributes CHANGED Viewed

@@ -43,3 +43,4 @@ R-PRM-7B-DPO.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text
 R-PRM-7B-DPO.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text
 R-PRM-7B-DPO.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text
 R-PRM-7B-DPO.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text

 R-PRM-7B-DPO.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text
 R-PRM-7B-DPO.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text
 R-PRM-7B-DPO.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text
+R-PRM-7B-DPO.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text

R-PRM-7B-DPO.Q5_K_M.gguf ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:c0a7424587445c5cbd60f3b4232cba5915db0232f567964be3f24fb4a2ba4f2c
+size 5444831776