Do not add EOS token when tokenizine by default

This PR reduces the confusing about tokenizer loading.

The current setting requires loading the tokenizer with `add_eos_token=False` or the EOS token will be added automatically, leading to weird completion results.

- Before:

```py
tokenizer = AutoTokenizer.from_pretrained("sbintuitions/sarashina2-8x70b", add_eos_token=False)
```

- After:

```py
tokenizer = AutoTokenizer.from_pretrained("sbintuitions/sarashina2-8x70b")
```

`"add_eos_token": false` in `tokenizer_config.json` is the same as `sbintuitions/sarashina2-70b`'s.
https://huggingface.co/sbintuitions/sarashina2-70b/blob/main/tokenizer_config.json#L134

tokenizer_config.json

@@ -131,5 +131,5 @@
   "add_dummy_prefix_space": false,
   "legacy": false,
   "add_bos_token": false,
-  "add_eos_token": true
+  "add_eos_token": false
 }