Do not print eos (#4654)

* allow models to use customized token ids during export (#4649)

Summary:
LLama3.1's [bos and eos](https://huggingface.co/meta-llama/Meta-Llama-3.1-8B-Instruct/blob/main/tokenizer_config.json) are different from what is hardcoded in the code. This PR updates the export flow to allow read customized token ids instead of hardcoded ones.

It also deletes a few metadata entries that are not used by the runner.

Pull Request resolved: #4649

Differential Revision: D61044259

Pulled By: helunwencser

* Do not print eos

Summary: We don't want to print eos in the response because some eos tokens could be `<|end_of_text|>`.

Differential Revision: D61048254

---------

Co-authored-by: Lunwen He <[email protected]>

Author: helunwencser

examples/models/llama2/runner/runner.cpp

@@ -228,19 +228,19 @@ Error Runner::generate(
       tokens_managed.resize({1, static_cast<int>(token_data.size())});
     }
 
-    // print the token as string, decode it with the Tokenizer object
-    wrapped_callback(ET_UNWRAP(tokenizer_->decode(prev_token, cur_token)));
-
-    if (shouldStop_) {
-      break;
-    }
-
     // data-dependent terminating condition: we have n_eos_ number of EOS
     if (pos >= num_prompt_tokens && cur_token == eos_id_) {
       printf("\n");
       ET_LOG(Info, "\nReached to the end of generation");
       break;
     }
+
+    // print the token as string, decode it with the Tokenizer object
+    wrapped_callback(ET_UNWRAP(tokenizer_->decode(prev_token, cur_token)));
+
+    if (shouldStop_) {
+      break;
+    }
   }
   stats_.inference_end_ms = util::time_in_ms();
   printf("\n");