fix last tokens passing to sample_repetition_penalties function

[ymikhailov]

Bug: currently all previous tokens are passing to llama_sample_repetition_penalties function instead of last penalty_last_n tokens.

Description: llama_sample_repetition_penalties function expects last penalty_last_n tokens. But it gets all previously generated tokens which leads to the algorithm not working correctly.

As you can see in the code below it will use only first penalty_last_n tokens to create token_count dict:

    ...
    // Create a frequency map to count occurrences of each token in last_tokens
    std::unordered_map<llama_token, int> token_count;
    for (size_t i = 0; i < penalty_last_n; ++i) {
        token_count[last_tokens[i]]++;
    }
    ...

This behavior is obviously incorrect which in our case led to the case where our model had a lot of answers with repetitions.

Also in this PR was fixed bug with possible buffer overflow that could cause to segfault in code above.

[abetlen]

@ymikhailov thank you for the fix! Looks good.