Update generation_config.json

Extend `eos_token_id` with pad token because that's the token stored in `processor.tokenizer.eos_token_id`. That also simplifies the sample from the model card from
```py
generate_ids = model.generate(**inputs,
eos_token_id=processor.tokenizer.eos_token_id,
**generation_args
)
```
to
```py
generate_ids = model.generate(**inputs,
**generation_args
)
```

generation_config.json

@@ -1,7 +1,10 @@
 {
   "_from_model_config": true,
   "bos_token_id": 1,
-  "eos_token_id": 2,
+  "eos_token_id": [
+    2,
+    32000
+  ],
   "pad_token_id": 32000,
   "transformers_version": "4.38.1"
 }