refact : fix convert script + zero out KV cache to avoid nans

[ggerganov]

ref: #3329 (comment)

• Copied tokenization from convert-starcoder-hf-to-gguf.py
• ALiBi is prone to random KV cache data, so we have to zero out the cache at the start. Since llama : custom attention mask + parallel decoding + no context swaps #3228, we can access uninitialized KV cache data due to:
  https://github.com/ggerganov/llama.cpp/blob/bdbe11719d81dfdc955b762b6d99796724e292b7/llama.cpp#L5024
  If this data happens to contain nan, then the generation fails

Question: should we first mask the KV tensor and then apply ALiBi?

https://github.com/ggerganov/llama.cpp/blob/bdbe11719d81dfdc955b762b6d99796724e292b7/llama.cpp#L3763-L3771

If that were the case, then the above KV cache initialization wouldn't be needed since any uninitialized values will be masked with -INF

[slaren]

If that were the case, then the above KV cache initialization wouldn't be needed since any uninitialized values will be masked with -INF

But nan - INF is still nan, so I don't think that this would work for removing nans before alibi.