Fix Gemma stop tokens: read additional EOS from tokenizer config

[stikves]

This fixes #25

The root cause is upstream not exposing the required fields, and eventually we should try to have them fix this at the origin. However we can also manually read the tokenizer additional information.

% swift run -c release llm-runner --model exports/gemma_3_4b_it_4bit_dynamic --max-tokens 250
Building for production...
[1 / 1]

Build complete! (1.10 sec)

⏳ Preparing AI asset from source... done in 0.571s

Generating...
I’m doing well, thank you for asking! As a large language model, I don’t really *feel* in the same way humans do, but my systems are running smoothly and I’m ready to chat. 😊

How are *you* doing today? Is there anything you'd like to talk about or any tasks you'd like me to help with?

⏱️  Performance Summary:
==================================================
Model Load: 571.2ms
Prompt:     84.9ms, 15 tokens, 176.6 tokens/sec
Generation: 1873.1ms, 79 tokens, 42.2 tokens/sec
Total:      8.984s
==================================================