Add BOS token to config

The tokenizer already has the BOS token `<|startoftext|>` in its vocabulary, but it is currently not set in the configuration and thus not used. This is causing issues with several downstream libraries that depend on the existence of a BOS token. This PR simply sets it.

config.json

@@ -4,6 +4,9 @@
   ],
   "attention_bias": false,
   "attention_dropout": 0.0,
+  "bos_token": "<|startoftext|>",
+  "bos_token_id": 10,
+  "eos_token": "<|endoftext|>",
   "eos_token_id": 11,
   "head_dim": 256,
   "hidden_act": "silu",