Create generation_config.json

As suggested by the author of the qwq32, these are the suggested config that should be used for the token generation.

generation_config.json

@@ -0,0 +1,14 @@
+{
+  "bos_token_id": 151643,
+  "do_sample": true,
+  "eos_token_id": [
+    151645,
+    151643
+  ],
+  "pad_token_id": 151643,
+  "repetition_penalty": 1.0,
+  "temperature": 0.6,
+  "top_k": 40,
+  "top_p": 0.95,
+  "transformers_version": "4.45.2"
+}