model : add hunyuan moe (#14425)

* model : add hunyuan moe

* tokenizer ok

* fix tensor name

* cgraph init

* chat template

* wip

* almost working

* skip embed, fix bos

* cleanup

* yarn scaling

* cleanup

* correct rope type

* failed token fix

* ntk alpha freq_base

* tokenization working

* cleanup and pr changes

* vocab_size sanity check

* ntk alpha generic

* Update convert_hf_to_gguf.py

* Apply suggestions from code review

* fix regression

* fix style

---------

Co-authored-by: kooshi <1934337+kooshi@users.noreply.github.com>

src/llama-vocab.cpp

@@ -351,6 +351,7 @@ struct llm_tokenizer_bpe : llm_tokenizer {
                 break;
             case LLAMA_VOCAB_PRE_TYPE_STABLELM2:
             case LLAMA_VOCAB_PRE_TYPE_QWEN2:
+            case LLAMA_VOCAB_PRE_TYPE_HUNYUAN:
                 regex_exprs = {
                     // original regex from tokenizer.json
                     // "(?i:'s|'t|'re|'ve|'m|'ll|'d)|[^\\r\\n\\p{L}\\p{N}]?\\p{L}+|\\p{N}| ?[^\\s\\p{L}\\p{N}]+[\\r\\n]*|\\s*[\\r\\n]+|\\s+(?!\\S)|\\s+"
@@ -1656,6 +1657,10 @@ void llama_vocab::impl::load(llama_model_loader & ml, const LLM_KV & kv) {
                 tokenizer_pre == "seed-coder") {
                 pre_type = LLAMA_VOCAB_PRE_TYPE_SEED_CODER;
                 clean_spaces = false;
+            } else if (
+                tokenizer_pre == "hunyuan") {
+                pre_type = LLAMA_VOCAB_PRE_TYPE_HUNYUAN;
+                clean_spaces = false;
             } else {
                 throw std::runtime_error(format("unknown pre-tokenizer type: '%s'", tokenizer_pre.c_str()));
             }