fix: only use eos_token_id as pad_token_id if int (#2774)

LLama 3 has a list of values as eos_token_id:
  "['<|end_of_text|>', '<|eom_id|>', '<|eot_id|>']"
This breaks tokenizer since it expects single value. This
commit uses tokenizer.eos_token_id instead in such a case.

Fixes: #2440

Signed-off-by: Dmitry Rogozhkin <[email protected]>

server/text_generation_server/models/causal_lm.py

@@ -630,7 +630,7 @@ def fallback(
         if tokenizer.pad_token_id is None:
             if model.config.pad_token_id is not None:
                 tokenizer.pad_token_id = model.config.pad_token_id
-            elif model.config.eos_token_id is not None:
+            elif model.config.eos_token_id is not None and isinstance(model.config.eos_token_id, int):
                 tokenizer.pad_token_id = model.config.eos_token_id
             elif tokenizer.eos_token_id is not None:
                 tokenizer.pad_token_id = tokenizer.eos_token_id