mradermacher
/

R-PRM-7B-DPO-i1-GGUF

Reinforcement Learning

Model card Files Files and versions Community

mradermacher commited on Mar 28

Commit

f68c7b3

·

verified ·

1 Parent(s): f9f020c

uploaded from rain

Files changed (2) hide show

.gitattributes +1 -0
R-PRM-7B-DPO.i1-Q4_K_M.gguf +3 -0

.gitattributes CHANGED Viewed

@@ -40,3 +40,4 @@ R-PRM-7B-DPO.i1-Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text
 R-PRM-7B-DPO.i1-IQ3_XXS.gguf filter=lfs diff=lfs merge=lfs -text
 R-PRM-7B-DPO.i1-Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text
 R-PRM-7B-DPO.i1-IQ4_NL.gguf filter=lfs diff=lfs merge=lfs -text

 R-PRM-7B-DPO.i1-IQ3_XXS.gguf filter=lfs diff=lfs merge=lfs -text
 R-PRM-7B-DPO.i1-Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text
 R-PRM-7B-DPO.i1-IQ4_NL.gguf filter=lfs diff=lfs merge=lfs -text
+R-PRM-7B-DPO.i1-Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text

R-PRM-7B-DPO.i1-Q4_K_M.gguf ADDED Viewed

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

+version https://git-lfs.github.com/spec/v1
+oid sha256:370d1bbfc1580d1383919fcce8cb18721dfc3fa2e2ed6a7b48d22069e54432bb
+size 4683074304