mayflowergmbh
/

Wiedervereinigung-7b-dpo-laser

Text Generation

DiscoResearch/DiscoLM_German_7b_v1

DRXD1000/Phoenix

VAGOsolutions/SauerkrautLM-7b-v1-mistral

malteos/hermeo-7b

text-generation-inference

Inference Endpoints

Model card Files Files and versions Community

johannhartmann commited on Feb 3

Commit

1dfc973

•

1 Parent(s): 96daf3e

Update README.md

Files changed (1) hide show

README.md +13 -13

README.md CHANGED Viewed

@@ -63,25 +63,25 @@ dtype: bfloat16
 ## mt-bench-de
-The results are not bad, but some additional investment into dpo
-finetuning would probably help a lot.
 ```json
 {
-    "first_turn": 6.4625,
-    "second_turn": 5.6375,
     "categories": {
-        "writing": 7.6,
-        "roleplay": 7.5,
-        "reasoning": 4.25,
-        "math": 3.35,
-        "coding": 3.1,
-        "extraction": 8.15,
-        "stem": 6.55,
-        "humanities": 7.9
     },
-    "average": 6.050000000000001
 }
 ```
 ## 💻 Usage

 ## mt-bench-de
+Using laser and dpo results in pretty good results.
 ```json
 {
+    "first_turn": 7.51875,
+    "second_turn": 6.4,
     "categories": {
+        "writing": 8.425,
+        "roleplay": 8.025,
+        "reasoning": 5.45,
+        "math": 3.2,
+        "coding": 4.95,
+        "extraction": 7.525,
+        "stem": 8.775,
+        "humanities": 9.325
     },
+    "average": 6.959375
 }
 ```
 ## 💻 Usage