Skip to content

Add Trillion 7B model support #12556

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
merged 5 commits into from
Mar 30, 2025
Merged

Add Trillion 7B model support #12556

Show file tree
Hide file tree
Changes from 4 commits
Commits
Show all changes
5 commits
Select commit Hold shift + click to select a range
c259898
Support Trillion 7B
juyoung-trl Mar 25, 2025
c96c0e7
Update llama.h
juyoung-trl Mar 25, 2025
8a26252
Update llama.h
juyoung-trl Mar 25, 2025
a10e37f
Update llama-vocab.cpp for Trillion
juyoung-trl Mar 25, 2025
a509d31
Update llama-vocab.cpp
juyoung-trl Mar 27, 2025
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
1 change: 1 addition & 0 deletions README.md
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -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

Expand Down
3 changes: 3 additions & 0 deletions convert_hf_to_gguf.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -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")
Expand Down
1 change: 1 addition & 0 deletions convert_hf_to_gguf_update.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -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", },
]


Expand Down
1 change: 1 addition & 0 deletions include/llama.h
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -108,6 +108,7 @@ 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 {
Expand Down
5 changes: 5 additions & 0 deletions src/llama-vocab.cpp
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -332,6 +332,7 @@ struct llm_tokenizer_bpe : llm_tokenizer {
case LLAMA_VOCAB_PRE_TYPE_SMOLLM:
case LLAMA_VOCAB_PRE_TYPE_CODESHELL:
case LLAMA_VOCAB_PRE_TYPE_EXAONE:
case LLAMA_VOCAB_PRE_TYPE_TRILLION:
case LLAMA_VOCAB_PRE_TYPE_MINERVA:
regex_exprs = {
"\\p{N}",
Expand Down Expand Up @@ -1614,6 +1615,10 @@ 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;
clean_spaces = false;
} else {
throw std::runtime_error(format("unknown pre-tokenizer type: '%s'", tokenizer_pre.c_str()));
}
Expand Down