add evaluations

evals/mmlu/mmlu_nl_Orca-2-7b.json

@@ -0,0 +1,23 @@
+{
+  "results": {
+    "mmlu_nl": {
+      "acc": 0.3597176899142445,
+      "acc_stderr": 0.004180948869028702,
+      "acc_norm": 0.32693329285876904,
+      "acc_norm_stderr": 0.004086644273815536
+    }
+  },
+  "versions": {
+    "mmlu_nl": 0
+  },
+  "config": {
+    "model": "hf-auto",
+    "model_args": "pretrained=microsoft/Orca-2-7b,use_accelerate=True,device_map_option=auto,dtype=bfloat16,load_in_8bit=True",
+    "batch_size": "auto",
+    "device": "cuda",
+    "no_cache": false,
+    "limit": null,
+    "bootstrap_iters": 100000,
+    "description_dict": {}
+  }
+}

evals/mmlu/mmlu_nl_neural-chat-7b-v3-1.json

@@ -0,0 +1,23 @@
+{
+  "results": {
+    "mmlu_nl": {
+      "acc": 0.44752219776883967,
+      "acc_stderr": 0.004331845059975039,
+      "acc_norm": 0.3436290506185019,
+      "acc_norm_stderr": 0.0041374029391109905
+    }
+  },
+  "versions": {
+    "mmlu_nl": 0
+  },
+  "config": {
+    "model": "hf-auto",
+    "model_args": "pretrained=Intel/neural-chat-7b-v3-1,use_accelerate=True,device_map_option=auto,dtype=bfloat16,load_in_8bit=True",
+    "batch_size": "auto",
+    "device": "cuda",
+    "no_cache": false,
+    "limit": null,
+    "bootstrap_iters": 100000,
+    "description_dict": {}
+  }
+}