Support Trillion 7B

Author: juyoung-trl

README.md

@@ -112,6 +112,7 @@ Instructions for adding support for new models: [HOWTO-add-model.md](docs/develo
 - [x] [RWKV-6](https://github.com/BlinkDL/RWKV-LM)
 - [x] [QRWKV-6](https://huggingface.co/recursal/QRWKV6-32B-Instruct-Preview-v0.1)
 - [x] [GigaChat-20B-A3B](https://huggingface.co/ai-sage/GigaChat-20B-A3B-instruct)
+- [X] [Trillion-7B-preview](https://huggingface.co/trillionlabs/Trillion-7B-preview)
 
 #### Multimodal
 

convert_hf_to_gguf.py

@@ -708,6 +708,9 @@ def get_vocab_base_pre(self, tokenizer) -> str:
         if chkhsh == "7dec86086fcc38b66b7bc1575a160ae21cf705be7718b9d5598190d7c12db76f":
             # ref: https://huggingface.co/UW/OLMo2-8B-SuperBPE-t180k
             res = "superbpe"
+        if chkhsh == "1994ffd01900cfb37395608534236ecd63f2bd5995d6cb1004dda1af50240f15":
+            # ref: https://huggingface.co/trillionlabs/Trillion-7B-preview
+            res = "trillion"
 
         if res is None:
             logger.warning("\n")

convert_hf_to_gguf_update.py

@@ -111,6 +111,7 @@ class TOKENIZER_TYPE(IntEnum):
     {"name": "deepseek-r1-qwen", "tokt": TOKENIZER_TYPE.BPE, "repo": "https://huggingface.co/deepseek-ai/DeepSeek-R1-Distill-Qwen-1.5B"},
     {"name": "gpt-4o",           "tokt": TOKENIZER_TYPE.BPE, "repo": "https://huggingface.co/Xenova/gpt-4o", },
     {"name": "superbpe",         "tokt": TOKENIZER_TYPE.BPE, "repo": "https://huggingface.co/UW/OLMo2-8B-SuperBPE-t180k", },
+    {"name": "trillion",         "tokt": TOKENIZER_TYPE.BPE, "repo": "https://huggingface.co/trillionlabs/Trillion-7B-preview", },
 ]
 
 

include/llama.h

@@ -108,7 +108,8 @@ extern "C" {
         LLAMA_VOCAB_PRE_TYPE_DEEPSEEK3_LLM  = 28,
         LLAMA_VOCAB_PRE_TYPE_GPT4O          = 29,
         LLAMA_VOCAB_PRE_TYPE_SUPERBPE       = 30,
-    };
+        LLAMA_VOCAB_PRE_TYPE_TRILLION       = 31,
+};
 
     enum llama_rope_type {
         LLAMA_ROPE_TYPE_NONE   = -1,

src/llama-vocab.cpp

@@ -1614,6 +1614,9 @@ void llama_vocab::impl::load(llama_model_loader & ml, const LLM_KV & kv) {
                 tokenizer_pre == "superbpe") {
                 pre_type = LLAMA_VOCAB_PRE_TYPE_SUPERBPE;
                 clean_spaces = false;
+            } else if (
+                tokenizer_pre == "trillion") {
+                pre_type = LLAMA_VOCAB_PRE_TYPE_TRILLION;
             } else {
                 throw std::runtime_error(format("unknown pre-tokenizer type: '%s'", tokenizer_pre.c_str()));
             }